{"generated":"2026-10-24","n_models":1493,"n_benchmarks":713,"n_scores":39407,"acc_fu":0.8465,"acc_raw":0.6744,"pairs":688749,"rmse_fu":10.57,"rmse_mean":22.79,"sd":0.421,"top":[{"rank":1,"id":"kimi-k3.1-pro","name":"Kimi-K3.1 Pro","provider":"moonshotai","country":"CN","open":false,"launched":"2026-10-23","size":"","score":91.16,"theta":2.456,"lo":1,"hi":8,"n":12,"raw":63.35,"raw_rank":593,"mnar_rank":2},{"rank":2,"id":"gpt-6-astra","name":"GPT-6 Astra","provider":"openai","country":"US","open":false,"launched":"2026-09-03","size":"10000Be","score":91.09,"theta":2.447,"lo":1,"hi":5,"n":84,"raw":73.76,"raw_rank":140,"mnar_rank":1},{"rank":3,"id":"claude-opus-5.5","name":"Claude Opus 5.5","provider":"anthropic","country":"US","open":false,"launched":"2026-09-22","size":"","score":90.83,"theta":2.415,"lo":2,"hi":7,"n":55,"raw":69.29,"raw_rank":272,"mnar_rank":3},{"rank":4,"id":"gemini-4-argon","name":"Gemini 4 Argon","provider":"google","country":"US","open":false,"launched":"2026-09-30","size":"","score":90.53,"theta":2.379,"lo":1,"hi":13,"n":26,"raw":68.65,"raw_rank":304,"mnar_rank":5},{"rank":5,"id":"claude-sonnet-5.5","name":"Claude Sonnet 5.5","provider":"anthropic","country":"US","open":false,"launched":"2026-09-28","size":"","score":90.51,"theta":2.376,"lo":1,"hi":12,"n":21,"raw":70.83,"raw_rank":217,"mnar_rank":4},{"rank":6,"id":"muse-wonder-full","name":"Muse Wonder Full","provider":"meta","country":"US","open":false,"launched":"2026-10-12","size":"","score":90.32,"theta":2.354,"lo":2,"hi":14,"n":10,"raw":61.38,"raw_rank":704,"mnar_rank":7},{"rank":7,"id":"claude-fable-5.1","name":"Claude Fable 5.1","provider":"anthropic","country":"US","open":false,"launched":"2026-09-01","size":"","score":89.99,"theta":2.316,"lo":5,"hi":11,"n":49,"raw":65.94,"raw_rank":446,"mnar_rank":6},{"rank":8,"id":"claude-opus-5.5-max","name":"Claude Opus 5.5 (max)","provider":"anthropic","country":"US","open":false,"launched":"2026-09-22","size":"","score":89.7,"theta":2.283,"lo":2,"hi":22,"n":9,"raw":74.33,"raw_rank":130,"mnar_rank":10},{"rank":9,"id":"claude-opus-5","name":"Claude Opus 5","provider":"anthropic","country":"US","open":false,"launched":"2026-07-24","size":"","score":89.62,"theta":2.274,"lo":7,"hi":13,"n":117,"raw":68.1,"raw_rank":339,"mnar_rank":8},{"rank":10,"id":"muse-wonder","name":"Muse Wonder","provider":"meta","country":"US","open":false,"launched":"2026-10-12","size":"","score":89.55,"theta":2.266,"lo":6,"hi":21,"n":11,"raw":57.8,"raw_rank":881,"mnar_rank":12},{"rank":11,"id":"gpt-6.1-sol","name":"GPT-6.1 Sol","provider":"openai","country":"US","open":false,"launched":"2026-09-29","size":"","score":89.44,"theta":2.255,"lo":3,"hi":19,"n":20,"raw":71.37,"raw_rank":204,"mnar_rank":13},{"rank":12,"id":"claude-fable-5","name":"Claude Fable 5","provider":"anthropic","country":"US","open":false,"launched":"2026-06-09","size":"5000Be","score":89.38,"theta":2.247,"lo":7,"hi":15,"n":110,"raw":68.34,"raw_rank":327,"mnar_rank":9},{"rank":13,"id":"claude-mythos-5","name":"Claude Mythos 5","provider":"anthropic","country":"US","open":false,"launched":"2026-06-09","size":"8000Be","score":89.13,"theta":2.221,"lo":5,"hi":22,"n":31,"raw":76.59,"raw_rank":74,"mnar_rank":11},{"rank":14,"id":"gpt-5.6-sol","name":"GPT-5.6 Sol","provider":"openai","country":"US","open":false,"launched":"2026-07-09","size":"4000Be","score":88.79,"theta":2.185,"lo":12,"hi":18,"n":165,"raw":69.12,"raw_rank":286,"mnar_rank":14},{"rank":15,"id":"deepseek-v4.1-flash-1017","name":"DeepSeek V4.1-Flash-1017","provider":"deepseek","country":"CN","open":true,"launched":"2026-10-17","size":"552B","score":88.39,"theta":2.145,"lo":12,"hi":40,"n":20,"raw":53.91,"raw_rank":1030,"mnar_rank":15},{"rank":16,"id":"minimax-m3.1-flash","name":"MiniMax M3.1 Flash","provider":"minimax","country":"CN","open":true,"launched":"2026-10-19","size":"428B","score":88.29,"theta":2.135,"lo":14,"hi":35,"n":9,"raw":61.99,"raw_rank":671,"mnar_rank":19},{"rank":17,"id":"mimo-v2.6-pro-rl","name":"MiMo V2.6 Pro RL","provider":"xiaomi","country":"CN","open":true,"launched":"2026-09-21","size":"1020B","score":88.27,"theta":2.133,"lo":10,"hi":29,"n":13,"raw":58.06,"raw_rank":867,"mnar_rank":16},{"rank":18,"id":"muse-spark-1.3","name":"Muse Spark 1.3","provider":"meta","country":"US","open":false,"launched":"2026-09-02","size":"","score":88.19,"theta":2.125,"lo":15,"hi":31,"n":15,"raw":61.47,"raw_rank":697,"mnar_rank":17},{"rank":19,"id":"veriloop-e2","name":"VeriLoop E2","provider":"tsinghua","country":"CN","open":true,"launched":"2026-09-22","size":"27B","score":88.17,"theta":2.123,"lo":12,"hi":33,"n":8,"raw":72.38,"raw_rank":179,"mnar_rank":20},{"rank":20,"id":"grok-4.7","name":"Grok 4.7","provider":"xai","country":"US","open":false,"launched":"2026-09-21","size":"2100Be","score":88.14,"theta":2.121,"lo":11,"hi":33,"n":12,"raw":59.7,"raw_rank":795,"mnar_rank":24},{"rank":21,"id":"claude-mythos-preview","name":"Claude Mythos Preview","provider":"anthropic","country":"US","open":false,"launched":"2026-04-07","size":"10000Be","score":88.01,"theta":2.107,"lo":11,"hi":36,"n":27,"raw":71.88,"raw_rank":192,"mnar_rank":23},{"rank":22,"id":"ling-3.1-flash","name":"Ling 3.1 Flash","provider":"antgroup","country":"CN","open":true,"launched":"2026-10-13","size":"560B","score":88,"theta":2.106,"lo":15,"hi":32,"n":20,"raw":66.55,"raw_rank":413,"mnar_rank":22},{"rank":23,"id":"gemini-3.8-flash","name":"Gemini 3.8 Flash","provider":"google","country":"US","open":false,"launched":"2026-09-02","size":"","score":87.98,"theta":2.105,"lo":14,"hi":32,"n":34,"raw":69.28,"raw_rank":274,"mnar_rank":18},{"rank":24,"id":"qwen3.8-max","name":"Qwen3.8-Max","provider":"qwen","country":"CN","open":false,"launched":"2026-08-03","size":"2.4T","score":87.82,"theta":2.09,"lo":18,"hi":32,"n":107,"raw":68.46,"raw_rank":316,"mnar_rank":21},{"rank":25,"id":"grok-4.6","name":"Grok 4.6","provider":"xai","country":"US","open":false,"launched":"2026-08-12","size":"1500Be","score":87.73,"theta":2.081,"lo":17,"hi":33,"n":15,"raw":58,"raw_rank":874,"mnar_rank":26},{"rank":26,"id":"deepseek-v4.1-flash","name":"DeepSeek V4.1-Flash","provider":"deepseek","country":"CN","open":true,"launched":"2026-09-10","size":"552B","score":87.65,"theta":2.073,"lo":21,"hi":34,"n":40,"raw":59.03,"raw_rank":823,"mnar_rank":25},{"rank":27,"id":"glm-5.3","name":"GLM-5.3","provider":"zai","country":"CN","open":true,"launched":"2026-08-14","size":"744B","score":87.5,"theta":2.059,"lo":21,"hi":36,"n":66,"raw":58.46,"raw_rank":851,"mnar_rank":27},{"rank":28,"id":"atria-dawn-preview","name":"Atria-Dawn-Preview","provider":"internlm","country":"CN","open":true,"launched":"2026-09-11","size":"744B","score":87.44,"theta":2.053,"lo":19,"hi":40,"n":18,"raw":65.17,"raw_rank":499,"mnar_rank":29},{"rank":29,"id":"atria-dawn","name":"Atria-Dawn","provider":"internlm","country":"CN","open":true,"launched":"2026-10-23","size":"744B","score":87.44,"theta":2.053,"lo":17,"hi":40,"n":21,"raw":63.95,"raw_rank":560,"mnar_rank":28},{"rank":30,"id":"gpt-6-sol","name":"GPT-6 Sol","provider":"openai","country":"US","open":false,"launched":"2026-09-22","size":"","score":87.42,"theta":2.052,"lo":16,"hi":37,"n":16,"raw":59.98,"raw_rank":778,"mnar_rank":30},{"rank":31,"id":"kimi-k3","name":"Kimi-K3","provider":"moonshotai","country":"CN","open":true,"launched":"2026-07-16","size":"2800B","score":87.04,"theta":2.016,"lo":26,"hi":38,"n":108,"raw":65.72,"raw_rank":465,"mnar_rank":31},{"rank":32,"id":"gemini-3.7-flash","name":"Gemini 3.7 Flash","provider":"google","country":"US","open":false,"launched":"2026-08-13","size":"","score":86.88,"theta":2.002,"lo":22,"hi":47,"n":39,"raw":61.79,"raw_rank":682,"mnar_rank":32},{"rank":33,"id":"mimo-v2.6-flash-rl","name":"MiMo V2.6 Flash RL","provider":"xiaomi","country":"CN","open":true,"launched":"2026-09-21","size":"309B","score":86.84,"theta":1.998,"lo":21,"hi":57,"n":14,"raw":52.65,"raw_rank":1068,"mnar_rank":36},{"rank":34,"id":"hy4-preview","name":"Hy4 preview","provider":"tencent","country":"CN","open":true,"launched":"2026-08-28","size":"770B","score":86.84,"theta":1.998,"lo":29,"hi":40,"n":38,"raw":58.22,"raw_rank":861,"mnar_rank":33},{"rank":35,"id":"naive-n0.5-flash","name":"Naive-N0.5-Flash","provider":"naiveai","country":"CN","open":true,"launched":"2026-09-27","size":"309B","score":86.77,"theta":1.992,"lo":21,"hi":55,"n":10,"raw":60.25,"raw_rank":762,"mnar_rank":37},{"rank":36,"id":"gpt-5.6-terra","name":"GPT-5.6 Terra","provider":"openai","country":"US","open":false,"launched":"2026-07-09","size":"","score":86.74,"theta":1.99,"lo":27,"hi":44,"n":59,"raw":62.41,"raw_rank":651,"mnar_rank":34},{"rank":37,"id":"gpt-5.5","name":"GPT-5.5","provider":"openai","country":"US","open":false,"launched":"2026-04-23","size":"4700Be","score":86.51,"theta":1.969,"lo":29,"hi":45,"n":178,"raw":66.66,"raw_rank":402,"mnar_rank":35},{"rank":38,"id":"claude-haiku-5.5","name":"Claude Haiku 5.5","provider":"anthropic","country":"US","open":false,"launched":"2026-10-07","size":"","score":86.47,"theta":1.965,"lo":19,"hi":62,"n":20,"raw":59.86,"raw_rank":782,"mnar_rank":40},{"rank":39,"id":"claude-opus-4.8","name":"Claude Opus 4.8","provider":"anthropic","country":"US","open":false,"launched":"2026-05-28","size":"5000Be","score":86.28,"theta":1.949,"lo":35,"hi":44,"n":174,"raw":64.29,"raw_rank":548,"mnar_rank":38},{"rank":40,"id":"muse-spark-open","name":"Muse Spark Open","provider":"meta","country":"US","open":true,"launched":"2026-10-15","size":"816B","score":86.08,"theta":1.932,"lo":30,"hi":51,"n":17,"raw":65.92,"raw_rank":448,"mnar_rank":41}],"open":[{"rank":15,"id":"deepseek-v4.1-flash-1017","name":"DeepSeek V4.1-Flash-1017","provider":"deepseek","country":"CN","open":true,"launched":"2026-10-17","size":"552B","score":88.39,"theta":2.145,"lo":12,"hi":40,"n":20,"raw":53.91,"raw_rank":1030,"mnar_rank":15},{"rank":16,"id":"minimax-m3.1-flash","name":"MiniMax M3.1 Flash","provider":"minimax","country":"CN","open":true,"launched":"2026-10-19","size":"428B","score":88.29,"theta":2.135,"lo":14,"hi":35,"n":9,"raw":61.99,"raw_rank":671,"mnar_rank":19},{"rank":17,"id":"mimo-v2.6-pro-rl","name":"MiMo V2.6 Pro RL","provider":"xiaomi","country":"CN","open":true,"launched":"2026-09-21","size":"1020B","score":88.27,"theta":2.133,"lo":10,"hi":29,"n":13,"raw":58.06,"raw_rank":867,"mnar_rank":16},{"rank":19,"id":"veriloop-e2","name":"VeriLoop E2","provider":"tsinghua","country":"CN","open":true,"launched":"2026-09-22","size":"27B","score":88.17,"theta":2.123,"lo":12,"hi":33,"n":8,"raw":72.38,"raw_rank":179,"mnar_rank":20},{"rank":22,"id":"ling-3.1-flash","name":"Ling 3.1 Flash","provider":"antgroup","country":"CN","open":true,"launched":"2026-10-13","size":"560B","score":88,"theta":2.106,"lo":15,"hi":32,"n":20,"raw":66.55,"raw_rank":413,"mnar_rank":22},{"rank":26,"id":"deepseek-v4.1-flash","name":"DeepSeek V4.1-Flash","provider":"deepseek","country":"CN","open":true,"launched":"2026-09-10","size":"552B","score":87.65,"theta":2.073,"lo":21,"hi":34,"n":40,"raw":59.03,"raw_rank":823,"mnar_rank":25},{"rank":27,"id":"glm-5.3","name":"GLM-5.3","provider":"zai","country":"CN","open":true,"launched":"2026-08-14","size":"744B","score":87.5,"theta":2.059,"lo":21,"hi":36,"n":66,"raw":58.46,"raw_rank":851,"mnar_rank":27},{"rank":28,"id":"atria-dawn-preview","name":"Atria-Dawn-Preview","provider":"internlm","country":"CN","open":true,"launched":"2026-09-11","size":"744B","score":87.44,"theta":2.053,"lo":19,"hi":40,"n":18,"raw":65.17,"raw_rank":499,"mnar_rank":29},{"rank":29,"id":"atria-dawn","name":"Atria-Dawn","provider":"internlm","country":"CN","open":true,"launched":"2026-10-23","size":"744B","score":87.44,"theta":2.053,"lo":17,"hi":40,"n":21,"raw":63.95,"raw_rank":560,"mnar_rank":28},{"rank":31,"id":"kimi-k3","name":"Kimi-K3","provider":"moonshotai","country":"CN","open":true,"launched":"2026-07-16","size":"2800B","score":87.04,"theta":2.016,"lo":26,"hi":38,"n":108,"raw":65.72,"raw_rank":465,"mnar_rank":31},{"rank":33,"id":"mimo-v2.6-flash-rl","name":"MiMo V2.6 Flash RL","provider":"xiaomi","country":"CN","open":true,"launched":"2026-09-21","size":"309B","score":86.84,"theta":1.998,"lo":21,"hi":57,"n":14,"raw":52.65,"raw_rank":1068,"mnar_rank":36},{"rank":34,"id":"hy4-preview","name":"Hy4 preview","provider":"tencent","country":"CN","open":true,"launched":"2026-08-28","size":"770B","score":86.84,"theta":1.998,"lo":29,"hi":40,"n":38,"raw":58.22,"raw_rank":861,"mnar_rank":33}],"labs":[{"rank":1,"id":"kimi-k3.1-pro","name":"Kimi-K3.1 Pro","provider":"moonshotai","country":"CN","open":false,"launched":"2026-10-23","size":"","score":91.16,"theta":2.456,"lo":1,"hi":8,"n":12,"raw":63.35,"raw_rank":593,"mnar_rank":2},{"rank":2,"id":"gpt-6-astra","name":"GPT-6 Astra","provider":"openai","country":"US","open":false,"launched":"2026-09-03","size":"10000Be","score":91.09,"theta":2.447,"lo":1,"hi":5,"n":84,"raw":73.76,"raw_rank":140,"mnar_rank":1},{"rank":3,"id":"claude-opus-5.5","name":"Claude Opus 5.5","provider":"anthropic","country":"US","open":false,"launched":"2026-09-22","size":"","score":90.83,"theta":2.415,"lo":2,"hi":7,"n":55,"raw":69.29,"raw_rank":272,"mnar_rank":3},{"rank":4,"id":"gemini-4-argon","name":"Gemini 4 Argon","provider":"google","country":"US","open":false,"launched":"2026-09-30","size":"","score":90.53,"theta":2.379,"lo":1,"hi":13,"n":26,"raw":68.65,"raw_rank":304,"mnar_rank":5},{"rank":6,"id":"muse-wonder-full","name":"Muse Wonder Full","provider":"meta","country":"US","open":false,"launched":"2026-10-12","size":"","score":90.32,"theta":2.354,"lo":2,"hi":14,"n":10,"raw":61.38,"raw_rank":704,"mnar_rank":7},{"rank":15,"id":"deepseek-v4.1-flash-1017","name":"DeepSeek V4.1-Flash-1017","provider":"deepseek","country":"CN","open":true,"launched":"2026-10-17","size":"552B","score":88.39,"theta":2.145,"lo":12,"hi":40,"n":20,"raw":53.91,"raw_rank":1030,"mnar_rank":15},{"rank":16,"id":"minimax-m3.1-flash","name":"MiniMax M3.1 Flash","provider":"minimax","country":"CN","open":true,"launched":"2026-10-19","size":"428B","score":88.29,"theta":2.135,"lo":14,"hi":35,"n":9,"raw":61.99,"raw_rank":671,"mnar_rank":19},{"rank":17,"id":"mimo-v2.6-pro-rl","name":"MiMo V2.6 Pro RL","provider":"xiaomi","country":"CN","open":true,"launched":"2026-09-21","size":"1020B","score":88.27,"theta":2.133,"lo":10,"hi":29,"n":13,"raw":58.06,"raw_rank":867,"mnar_rank":16},{"rank":19,"id":"veriloop-e2","name":"VeriLoop E2","provider":"tsinghua","country":"CN","open":true,"launched":"2026-09-22","size":"27B","score":88.17,"theta":2.123,"lo":12,"hi":33,"n":8,"raw":72.38,"raw_rank":179,"mnar_rank":20},{"rank":20,"id":"grok-4.7","name":"Grok 4.7","provider":"xai","country":"US","open":false,"launched":"2026-09-21","size":"2100Be","score":88.14,"theta":2.121,"lo":11,"hi":33,"n":12,"raw":59.7,"raw_rank":795,"mnar_rank":24},{"rank":22,"id":"ling-3.1-flash","name":"Ling 3.1 Flash","provider":"antgroup","country":"CN","open":true,"launched":"2026-10-13","size":"560B","score":88,"theta":2.106,"lo":15,"hi":32,"n":20,"raw":66.55,"raw_rank":413,"mnar_rank":22},{"rank":24,"id":"qwen3.8-max","name":"Qwen3.8-Max","provider":"qwen","country":"CN","open":false,"launched":"2026-08-03","size":"2.4T","score":87.82,"theta":2.09,"lo":18,"hi":32,"n":107,"raw":68.46,"raw_rank":316,"mnar_rank":21},{"rank":27,"id":"glm-5.3","name":"GLM-5.3","provider":"zai","country":"CN","open":true,"launched":"2026-08-14","size":"744B","score":87.5,"theta":2.059,"lo":21,"hi":36,"n":66,"raw":58.46,"raw_rank":851,"mnar_rank":27},{"rank":28,"id":"atria-dawn-preview","name":"Atria-Dawn-Preview","provider":"internlm","country":"CN","open":true,"launched":"2026-09-11","size":"744B","score":87.44,"theta":2.053,"lo":19,"hi":40,"n":18,"raw":65.17,"raw_rank":499,"mnar_rank":29},{"rank":34,"id":"hy4-preview","name":"Hy4 preview","provider":"tencent","country":"CN","open":true,"launched":"2026-08-28","size":"770B","score":86.84,"theta":1.998,"lo":29,"hi":40,"n":38,"raw":58.22,"raw_rank":861,"mnar_rank":33},{"rank":35,"id":"naive-n0.5-flash","name":"Naive-N0.5-Flash","provider":"naiveai","country":"CN","open":true,"launched":"2026-09-27","size":"309B","score":86.77,"theta":1.992,"lo":21,"hi":55,"n":10,"raw":60.25,"raw_rank":762,"mnar_rank":37}],"categories":[{"id":"faix-text","name":"Text","n":1626,"nb":179,"top":[{"rank":1,"id":"gpt-6-astra","name":"GPT-6 Astra","provider":"openai","score":94.54},{"rank":2,"id":"claude-fable-5.1","name":"Claude Fable 5.1","provider":"anthropic","score":93.41},{"rank":3,"id":"claude-fable-5","name":"Claude Fable 5","provider":"anthropic","score":93.3},{"rank":4,"id":"claude-opus-5","name":"Claude Opus 5","provider":"anthropic","score":93.22},{"rank":5,"id":"claude-mythos-5","name":"Claude Mythos 5","provider":"anthropic","score":92.47}]},{"id":"faix-code","name":"Code","n":756,"nb":38,"top":[{"rank":1,"id":"claude-fable-5","name":"Claude Fable 5","provider":"anthropic","score":93.58},{"rank":2,"id":"kimi-k3","name":"Kimi-K3","provider":"moonshotai","score":91.21},{"rank":3,"id":"claude-mythos-preview","name":"Claude Mythos Preview","provider":"anthropic","score":91.01},{"rank":4,"id":"claude-opus-4.8","name":"Claude Opus 4.8","provider":"anthropic","score":90.67},{"rank":5,"id":"gpt-5.5","name":"GPT-5.5","provider":"openai","score":90.44}]},{"id":"faix-math","name":"Math","n":544,"nb":28,"top":[{"rank":1,"id":"gpt-5.2-thinking-xhigh","name":"GPT-5.2 Thinking (xhigh)","provider":"openai","score":95.03},{"rank":2,"id":"gemini-3.1-pro","name":"Gemini 3.1 Pro","provider":"google","score":95.01},{"rank":3,"id":"seed2.1-pro","name":"Seed2.1 Pro","provider":"bytedance","score":94.94},{"rank":4,"id":"claude-opus-4.5-thinking","name":"Claude Opus 4.5 Thinking","provider":"anthropic","score":94.6},{"rank":5,"id":"gpt-5.5","name":"GPT-5.5","provider":"openai","score":94.48}]},{"id":"faix-stem","name":"STEM","n":941,"nb":35,"top":[{"rank":1,"id":"gpt-5.2-thinking-xhigh","name":"GPT-5.2 Thinking (xhigh)","provider":"openai","score":95.97},{"rank":2,"id":"gemini-3-pro","name":"Gemini 3 Pro","provider":"google","score":95.71},{"rank":3,"id":"claude-opus-4.5-thinking","name":"Claude Opus 4.5 Thinking","provider":"anthropic","score":95.64},{"rank":4,"id":"claude-opus-4.8","name":"Claude Opus 4.8","provider":"anthropic","score":95.62},{"rank":5,"id":"gpt-5.5","name":"GPT-5.5","provider":"openai","score":95.34}]},{"id":"faix-agent","name":"Agent","n":217,"nb":24,"top":[{"rank":1,"id":"claude-fable-5","name":"Claude Fable 5","provider":"anthropic","score":84.96},{"rank":2,"id":"longcat-flash-thinking-2601","name":"LongCat-Flash-Thinking-2601","provider":"meituan","score":82.37},{"rank":3,"id":"glm-5.2","name":"GLM-5.2","provider":"zai","score":82.23},{"rank":4,"id":"qwen3.8-max","name":"Qwen3.8-Max","provider":"qwen","score":81.88},{"rank":5,"id":"gpt-5.5","name":"GPT-5.5","provider":"openai","score":81.61}]},{"id":"faix-visual","name":"Visual","n":529,"nb":91,"top":[{"rank":1,"id":"gpt-6-astra","name":"GPT-6 Astra","provider":"openai","score":88.95},{"rank":2,"id":"qwen3.8-max","name":"Qwen3.8-Max","provider":"qwen","score":88.66},{"rank":3,"id":"qwen3.8-omni-flash","name":"Qwen3.8-Omni-Flash","provider":"qwen","score":88.46},{"rank":4,"id":"qwen3.8-flash-next","name":"Qwen3.8-Flash-Next","provider":"qwen","score":87.52},{"rank":5,"id":"claude-fable-5","name":"Claude Fable 5","provider":"anthropic","score":87.39}]},{"id":"faix-ocr","name":"OCR","n":335,"nb":18,"top":[{"rank":1,"id":"claude-fable-5","name":"Claude Fable 5","provider":"anthropic","score":93.22},{"rank":2,"id":"qwen3.8-max","name":"Qwen3.8-Max","provider":"qwen","score":92.7},{"rank":3,"id":"gpt-5.6-sol","name":"GPT-5.6 Sol","provider":"openai","score":91.75},{"rank":4,"id":"qwen3.8-flash-next","name":"Qwen3.8-Flash-Next","provider":"qwen","score":90.1},{"rank":5,"id":"gemini-3.1-pro","name":"Gemini 3.1 Pro","provider":"google","score":89.29}]},{"id":"faix-voice","name":"Voice","n":67,"nb":25,"top":[{"rank":1,"id":"gemini-3.1-pro","name":"Gemini 3.1 Pro","provider":"google","score":93.15},{"rank":2,"id":"seed2.0-lite","name":"Seed2.0 Lite","provider":"bytedance","score":92.24},{"rank":3,"id":"gemini-3-flash","name":"Gemini 3 Flash","provider":"google","score":92.18},{"rank":4,"id":"stepaudio-3-realtime","name":"StepAudio 3 Realtime","provider":"stepfun","score":92.17},{"rank":5,"id":"gemini-3.8-flash","name":"Gemini 3.8 Flash","provider":"google","score":92.08}]}],"benchmarks":[{"id":"mmlu-pro","name":"MMLU-Pro","topic":"Multi-domain knowledge","difficulty":-0.482,"discrimination":1.14,"n":675},{"id":"mmlu","name":"MMLU","topic":"Multi-domain knowledge","difficulty":-1.587,"discrimination":0.915,"n":647},{"id":"gpqa-diamond","name":"GPQA-diamond","topic":"Graduate-level QA","difficulty":-0.136,"discrimination":1.25,"n":573},{"id":"livecodebench","name":"LiveCodeBench","topic":"Code generation","difficulty":0.279,"discrimination":1.769,"n":572},{"id":"gsm8k","name":"GSM8K","topic":"Math (grade-school)","difficulty":-1.292,"discrimination":1.978,"n":570},{"id":"humaneval","name":"HumanEval","topic":"Code generation","difficulty":-0.957,"discrimination":1.863,"n":505},{"id":"ifeval","name":"IFEval","topic":"Instruction following","difficulty":-1.829,"discrimination":0.798,"n":450},{"id":"math","name":"MATH","topic":"Math (competition)","difficulty":-0.54,"discrimination":2.188,"n":449},{"id":"mbpp","name":"MBPP","topic":"Code generation","difficulty":-1.126,"discrimination":1.339,"n":442},{"id":"bbh","name":"BBH","topic":"Multi-task reasoning","difficulty":-1.232,"discrimination":1.207,"n":425},{"id":"aime-2025","name":"AIME 2025","topic":"Math (competition)","difficulty":0.202,"discrimination":2.837,"n":424},{"id":"hellaswag","name":"HellaSwag","topic":"Commonsense reasoning","difficulty":-2.774,"discrimination":0.666,"n":375},{"id":"humaneval-plus","name":"HumanEval+","topic":"Code generation","difficulty":-0.901,"discrimination":1.524,"n":365},{"id":"ifbench","name":"IFBench","topic":"Instruction following","difficulty":0.393,"discrimination":0.907,"n":347},{"id":"arc-challenge","name":"ARC-Challenge","topic":"Science QA","difficulty":-1.636,"discrimination":1.52,"n":337},{"id":"mbpp-plus","name":"MBPP+","topic":"Code generation","difficulty":-1.02,"discrimination":0.808,"n":328},{"id":"gpqa","name":"GPQA","topic":"Graduate-level QA","difficulty":-0.051,"discrimination":1.116,"n":301},{"id":"mmmu","name":"MMMU","topic":"Multimodal understanding","difficulty":-0.713,"discrimination":0.757,"n":299},{"id":"c-eval","name":"C-Eval","topic":"Chinese exams","difficulty":-1.531,"discrimination":0.92,"n":299},{"id":"winogrande","name":"WinoGrande","topic":"Coreference reasoning","difficulty":-2.646,"discrimination":0.611,"n":286},{"id":"swe-bench-verified","name":"SWE-Bench Verified","topic":"Code repair","difficulty":0.669,"discrimination":1.745,"n":272},{"id":"cmmlu","name":"CMMLU","topic":"Chinese multi-domain","difficulty":-1.539,"discrimination":0.928,"n":256},{"id":"mmlu-redux","name":"MMLU-Redux","topic":"Multi-domain knowledge","difficulty":-1.336,"discrimination":1.123,"n":254},{"id":"ai2d","name":"AI2D","topic":"Diagram understanding (VQA)","difficulty":-2.457,"discrimination":0.716,"n":254},{"id":"math500","name":"MATH500","topic":"Math reasoning","difficulty":-0.856,"discrimination":2.206,"n":253},{"id":"charxiv-rq","name":"CharXiv (RQ)","topic":"Chart reasoning (PDF)","difficulty":0.18,"discrimination":1.067,"n":242},{"id":"hle","name":"HLE","topic":"Multi-domain reasoning","difficulty":2.056,"discrimination":1.412,"n":238},{"id":"aime-2024","name":"AIME 2024","topic":"Math (competition)","difficulty":0.123,"discrimination":3.192,"n":232},{"id":"docvqa","name":"DocVQA","topic":"Document understanding (VQA)","difficulty":-2.801,"discrimination":0.906,"n":229},{"id":"ocrbench","name":"OCRBench V2","topic":"OCR (vision text extraction)","difficulty":-2.233,"discrimination":0.651,"n":227},{"id":"realworldqa","name":"RealWorldQA","topic":"Real-world visual QA","difficulty":-1.892,"discrimination":0.463,"n":224},{"id":"mmmu-pro","name":"MMMU PRO","topic":"Multimodal understanding (hard)","difficulty":0.145,"discrimination":0.953,"n":219},{"id":"agieval","name":"AGIEval (English)","topic":"Exams","difficulty":-0.98,"discrimination":1.01,"n":211},{"id":"chartqa","name":"ChartQA","topic":"Chart understanding (VQA)","difficulty":-2.682,"discrimination":0.623,"n":210},{"id":"mmstar","name":"MMStar","topic":"Multimodal reasoning","difficulty":-1.08,"discrimination":0.591,"n":209},{"id":"mathvista-mini","name":"MathVista-Mini","topic":"Math reasoning (multimodal)","difficulty":-0.845,"discrimination":0.889,"n":203},{"id":"scicode","name":"SciCode (sub)","topic":"Code","difficulty":1.546,"discrimination":0.752,"n":196},{"id":"tau2-telecom","name":"TAU2-Telecom","topic":"Agent tasks (telecom)","difficulty":0.322,"discrimination":2.147,"n":194},{"id":"mmbench-v1.1-en","name":"MMBench v1.1 (EN)","topic":"Multimodal understanding (English)","difficulty":-2.256,"discrimination":0.694,"n":191},{"id":"aa-lcr","name":"AA-LCR","topic":"Long-context reasoning","difficulty":0.616,"discrimination":1.105,"n":190},{"id":"piqa","name":"PIQA","topic":"Physical commonsense","difficulty":-4.494,"discrimination":0.415,"n":182},{"id":"hle-text-only","name":"HLE (Text Only)","topic":"Advanced reasoning","difficulty":2.033,"discrimination":1.462,"n":181},{"id":"mathvision","name":"MathVision","topic":"Math reasoning (multimodal)","difficulty":0.273,"discrimination":1.513,"n":181},{"id":"textvqa","name":"TextVQA","topic":"Text-based VQA","difficulty":-2.934,"discrimination":0.486,"n":179},{"id":"browsecomp","name":"BrowseComp","topic":"Web browsing","difficulty":1.044,"discrimination":2.278,"n":178},{"id":"bigcodebench","name":"BigCodeBench","topic":"Code Generation","difficulty":0.351,"discrimination":0.536,"n":169},{"id":"mmbench-v1.1-cn","name":"MMBench v1.1 (CN)","topic":"Multimodal understanding (Chinese)","difficulty":-1.961,"discrimination":0.737,"n":169},{"id":"blink","name":"BLINK","topic":"Multimodal grounding","difficulty":-0.685,"discrimination":0.532,"n":166},{"id":"aime-2026-i","name":"AIME 2026 I","topic":"Math (competition)","difficulty":-0.062,"discrimination":2.132,"n":164},{"id":"hallusionbench","name":"HallusionBench","topic":"Multimodal hallucination","difficulty":-0.783,"discrimination":0.35,"n":163},{"id":"arc-easy","name":"ARC-Easy","topic":"Science QA","difficulty":-2.331,"discrimination":1.586,"n":163},{"id":"terminal-bench-2.1","name":"Terminal-Bench 2.1","topic":"Agent terminal tasks","difficulty":1.228,"discrimination":2.453,"n":162},{"id":"infovqa","name":"InfoVQA","topic":"Infographic VQA","difficulty":-1.348,"discrimination":0.876,"n":162},{"id":"bfcl-v4","name":"BFCL v4","topic":"Code reasoning","difficulty":0.41,"discrimination":0.827,"n":159},{"id":"triviaqa","name":"TriviaQA","topic":"Open-domain QA","difficulty":-1.388,"discrimination":0.9,"n":156},{"id":"supergpqa","name":"SuperGPQA","topic":"Graduate-level QA","difficulty":0.489,"discrimination":0.897,"n":148},{"id":"drop","name":"DROP","topic":"Reading + reasoning","difficulty":-1.06,"discrimination":1.278,"n":148},{"id":"swe-bench-multilingual","name":"SWE-Bench Multilingual","topic":"Code repair (multilingual)","difficulty":0.805,"discrimination":1.499,"n":146},{"id":"imo-answerbench","name":"IMO AnswerBench","topic":"Math (competition)","difficulty":0.428,"discrimination":1.706,"n":144},{"id":"truthfulqa","name":"TruthfulQA","topic":"Truthfulness / hallucination","difficulty":-1.003,"discrimination":0.426,"n":144}],"fit":{"hypersim":[10.061,0.2,22],"hle-multichoice":[9.144,0.2,43],"aa-omniscience-decision-non-hallucination":[6.672,0.595,13],"omnidocbench-1.5":[5.107,0.503,11],"legal-agent-benchmark-held-out":[4.462,1.055,19],"biology-instruction":[4.346,0.783,23],"nuscenes":[3.9,0.654,12],"chessbench-decision":[3.74,0.459,38],"cl-bench":[3.717,0.604,36],"cl-bench-life":[3.598,0.853,15],"zerobench":[3.356,1.241,48],"quac":[3.208,0.2,19],"programbench-almost-solved":[3.132,1.342,11],"inscit":[3.119,0.388,10],"healthbench-hard":[2.994,0.686,18],"popqa":[2.989,0.305,66],"sunrgbd":[2.906,0.253,19],"exploitgym":[2.867,2.022,15],"doc2dial":[2.814,0.446,10],"doqa":[2.8,0.511,10],"spreadsheetbench-2":[2.794,1.05,15],"gdp-pdf":[2.733,1.675,33],"osworld-2.0-strict":[2.719,1.62,13],"critpt":[2.694,2.159,86],"terminal-bench-3.0":[2.686,1.851,18],"frontierbench":[2.654,2.614,13],"agentworldbench-search":[2.65,0.81,12],"automationbench-aa":[2.64,0.549,16],"vlms-are-biased":[2.631,0.678,12],"mmsibench-circular":[2.618,0.995,10],"terminal-bench-science":[2.577,1.638,14],"posttrainbench":[2.564,1.245,31],"harbor-index":[2.542,1.318,10],"enigmaval":[2.494,1.761,15],"agents-last-exam":[2.465,1.474,58],"swe-marathon":[2.45,2.11,22],"aa-omniscience-accuracy":[2.432,0.909,41],"zerobench-sub":[2.413,0.606,52],"tau3-banking":[2.372,1.321,116],"frontierscience":[2.358,1.519,10],"terminal-bench-4.0":[2.312,3.275,40],"mls-bench-lite":[2.311,1.032,10],"swe-bench-multimodal":[2.308,1.188,19],"cmt-benchmark":[2.305,0.924,17],"visulogic":[2.302,0.51,34],"mol-instructions":[2.289,1.398,23],"automationbench":[2.278,1.709,63],"biomysterybench-hard":[2.277,2.154,21],"frontiercode-main":[2.251,1.614,41],"zerobench-with-tools":[2.189,1.443,23],"chartography":[2.171,1.742,11],"commerceagentbench":[2.156,1.29,10],"apex-agents":[2.15,2.056,70],"frontierscience-research":[2.075,1.914,50],"hle":[2.056,1.412,238],"swe-atlas-refactoring":[2.056,1.635,20],"mmsi-bench":[2.053,0.446,20],"swe-atlas-test-writing":[2.053,1.676,23],"agents-last-exam-score":[2.039,1.02,22],"hle-text-only":[2.033,1.462,181],"eebench":[2.022,1.9,25],"exploitbench":[2.007,2.006,17],"simpleqa-verified":[1.991,0.91,82],"gso-benchmark":[1.985,2.368,30],"visfactor":[1.974,1.117,13],"jobbench":[1.965,2.285,43],"deepswe-v1.0":[1.962,2.258,25],"worldvqa":[1.939,0.724,30],"vals-index":[1.937,1.383,41],"hle-verified":[1.937,0.823,17],"osworld-2.0":[1.934,2.462,31],"frontierfinance":[1.911,0.861,15],"scires-frontiermath-tier-4":[1.91,2.834,20],"deepswe":[1.909,2.79,41],"proofbench-advanced":[1.908,2.077,17],"videomme-v2":[1.897,0.605,27],"deepresearch-bench-ii":[1.89,0.614,14],"frontiercode-extended":[1.88,1.339,41],"swe-atlas-qna":[1.875,1.723,42],"sec-bench-pro":[1.861,1.834,11],"machiavelli":[1.857,0.359,15],"apex-agents-v1.1":[1.855,1.615,53],"vitabench":[1.853,1.003,65],"textquests":[1.85,1.359,18],"tool-decathlon":[1.832,1.412,18],"cwe-bench":[1.831,1.11,11],"usaco":[1.831,1.268,10],"programbench":[1.819,1.171,27],"deep-planning":[1.818,1.599,27],"deepswe-v1.1":[1.817,2.672,70],"sgi-bench":[1.797,0.91,17],"matharena-apex":[1.768,3.511,51],"scireasoner":[1.762,1.927,20],"nl2repo":[1.756,1.613,71],"healthbench-professional":[1.725,0.891,27],"benchcad":[1.722,1.385,14],"astabench":[1.679,1.48,23],"graphwalks-bfs-1m":[1.679,1.651,15],"fsc-147":[1.674,1.566,12],"perceptionbench":[1.663,0.83,11],"hle-with-tools":[1.651,1.147,137],"financeagent-v2":[1.635,0.676,30],"arc-agi-2":[1.631,3.319,119],"toolathlon":[1.629,1.316,61],"workbuddy-bench":[1.608,1.067,12],"babyvision":[1.597,1.494,71],"mrcr-1m":[1.588,1.525,21],"skillsbench":[1.584,1.407,59],"terminal-bench-hard":[1.576,1.848,73],"officeqa-pro":[1.575,1.781,33],"art-agent-red-teaming":[1.57,1.131,35],"scires-frontiermath-tier-1-3":[1.563,2.121,16],"livecodebench-pro-25q2-med":[1.559,2.576,38],"odinw-13":[1.557,0.294,33],"mattools":[1.548,1.549,10],"scicode":[1.546,0.752,196],"frontier-cs":[1.541,1.575,11],"aa-omniscience-non-hallucination":[1.538,1.113,24],"mcp-universe":[1.532,1.314,35],"wildclawbench":[1.531,1.298,53],"vlmsarebiased":[1.523,1.067,21],"workspacebench":[1.521,1.139,15],"scicode-main":[1.51,2.458,31],"bird-sql":[1.504,0.238,34],"multi-swe-bench":[1.493,1.279,30],"hle-overconfidence":[1.488,1.122,15],"topiocqa":[1.486,0.373,10],"mobileworld":[1.48,1.873,19],"frontierswe":[1.471,1.157,19],"agentworldbench-web":[1.464,0.694,12],"superchem":[1.464,1.34,31],"mcpmark":[1.457,2.285,77],"balrog":[1.435,0.944,21],"molecular-iq":[1.435,1.166,19],"sata-bench":[1.433,0.794,38],"bigcodebench-hard":[1.426,0.9,127],"paperbench":[1.422,2.322,32],"arxivmath":[1.422,1.227,18],"gaia2":[1.419,1.759,16],"agentworldbench-terminal":[1.419,0.861,12],"vision2web":[1.415,1.432,22],"deepresearchbench":[1.404,0.841,11],"browsecomp-vl":[1.403,0.864,11],"medxpertqa-text":[1.402,1.142,16],"automationbench-partial":[1.394,1.629,10],"seal-0":[1.393,0.569,41],"swe-bench-pro":[1.39,1.493,133],"xlrs-bench":[1.387,0.428,18],"cybergym":[1.383,2.308,43],"mtvqa":[1.368,0.667,24],"qrecc":[1.365,0.32,10],"tir-bench":[1.359,1.134,16],"browsecomp-plus":[1.349,2.148,28],"terminal-bench-terminus":[1.345,1.596,10],"aethercode":[1.345,1.64,17],"swe-bench-pro-public":[1.343,1.291,91],"osworld-2.1":[1.342,1.19,10],"toolathlon-verified":[1.339,1.484,55],"webarena-verified":[1.334,1.23,19],"simpleqa":[1.333,1.196,117],"mle-bench-lite":[1.32,2.02,37],"agentic-coding":[1.312,1.448,22],"hybridial":[1.308,0.481,10],"egoplan-bench2":[1.3,0.564,13],"usamo-2026":[1.286,2.237,17],"kosimpleqa":[1.285,0.555,13],"babe":[1.279,0.897,11],"babyvision-with-tools":[1.271,2.383,19],"ojbench":[1.271,1.767,70],"benchcad-python-tool":[1.255,1.719,12],"minif2f-test":[1.243,0.478,17],"herobench":[1.238,2.389,21],"terminal-bench-2.1":[1.228,2.453,162],"vct":[1.227,1.114,12],"biomysterybench":[1.214,1.602,29],"chartography-with-tools":[1.197,1.567,16],"agentworldbench-swe":[1.195,1.04,12],"terminal-bench-2.0":[1.189,1.77,112],"paper-bench-code-dev":[1.184,1.951,11],"qwenclawbench":[1.182,1.123,37],"terminal-bench":[1.179,1.962,85],"audio-multichallenge":[1.177,1.206,21],"lpfqa":[1.161,0.653,12],"finsearchcomp":[1.145,1.655,26],"amobench":[1.141,1.847,24],"facts-benchmark-suite":[1.141,1.28,14],"countqa":[1.138,1.114,36],"gdpval":[1.137,1.682,55],"financeagent":[1.119,0.775,10],"livemcp-101":[1.118,2.093,18],"spatialviz":[1.112,0.862,15],"agentworldbench-android":[1.107,0.779,12],"mrcr-256k-8n":[1.102,2.085,11],"sfe":[1.1,0.585,23],"pop909-cl-decision":[1.099,1.492,36],"onemillionbench":[1.097,0.758,13],"defects4j":[1.079,1.197,10],"aicodeking-non-agentic":[1.07,1.146,15],"jobbench-easy":[1.068,1.377,12],"claweval-pass3":[1.052,1.024,68],"bfcl-v3-multi-turn":[1.049,1.235,37],"mmsearch":[1.049,1.767,22],"browsecomp":[1.044,2.278,178],"tau-voice-retail":[1.04,1.455,29],"viewspatial-bench":[1.038,0.296,20],"terminal-bench-lite":[1.019,1.773,10],"arc-agi-1":[0.997,3.148,101],"mcp-atlas":[0.993,1.664,128],"phybench":[0.993,1.778,33],"healthbench":[0.984,0.447,37],"tau-voice-telecom":[0.984,2.061,29],"financeagent-v1.1":[0.98,0.66,29],"vlabench":[0.979,0.626,13],"researchrubrics":[0.974,0.97,27],"crossvid":[0.97,0.625,10],"osworld":[0.968,0.975,24],"osworld-verified":[0.953,1.435,66],"browsecomp-zh":[0.941,1.799,79],"aa-omniscience-decision-accuracy":[0.931,1.569,13],"hipho":[0.917,1.382,26],"surds":[0.913,0.995,18],"matharena-apex-shortlist":[0.912,2.185,27],"big-bench-extra-hard":[0.908,1.407,47],"agentworldbench-os":[0.897,0.86,12],"autocodebench":[0.893,0.863,34],"vabench-point":[0.882,0.556,13],"mrcr-128k-8n":[0.87,1.906,44],"tomato":[0.857,0.952,41],"xbench-deepsearch-2025.10":[0.85,1.45,33],"treebench":[0.846,0.606,17],"medxpertqa-mm":[0.837,1.201,58],"swe-bench":[0.834,1.79,42],"contphy":[0.832,0.744,10],"multichallenge":[0.81,0.828,127],"swe-bench-multilingual":[0.805,1.499,146],"spiral-bench":[0.795,0.932,21],"tau1-airline":[0.793,1.19,13],"blend":[0.781,0.899,12],"emma":[0.762,1.084,11],"deepsearchqa":[0.731,2.092,65],"agentworldbench-mcp":[0.73,0.707,12],"kobolt":[0.713,1.023,24],"minerva-video":[0.713,0.821,10],"longbench-v2":[0.701,0.687,135],"wide-search":[0.701,1.179,85],"gaia":[0.684,1.499,90],"swe-bench-verified":[0.669,1.745,272],"browsecomp-with-content-manager":[0.665,1.399,35],"artifactsbench":[0.646,0.882,53],"refspatialbench":[0.641,0.554,70],"omega":[0.64,1.576,38],"robovqa":[0.632,0.2,13],"mrcr-128k":[0.631,1.448,42],"enamel":[0.629,1.007,10],"mmlongbench-doc":[0.623,0.576,51],"aa-lcr":[0.616,1.105,190],"frontierscience-olympiad":[0.604,0.959,49],"omni-math-hard":[0.602,1.501,18],"screenspot-pro":[0.594,1.258,82],"part-affordance":[0.592,0.715,13],"polymath":[0.572,1.262,69],"aider-polyglot":[0.567,2.848,90],"aider-polyglot-diff":[0.567,2.874,46],"nexus":[0.563,0.735,15],"chartmuseum":[0.552,1.097,47],"fd-bench-v1.5":[0.551,0.856,10],"androidworld":[0.55,1.064,44],"cgbench":[0.546,0.748,12],"erqa":[0.54,0.571,111],"mindcube":[0.522,0.814,51],"autocodebench-lite":[0.516,1.183,38],"aa-index":[0.508,0.313,10],"chartqa-pro":[0.504,0.8,46],"mmmu-pro-vision":[0.503,0.982,49],"jculture":[0.502,0.591,10],"creative-writing-longform":[0.496,0.914,118],"supergpqa":[0.489,0.897,148],"spreadsheetbench-v1":[0.472,1.318,23],"cnmo-2024":[0.469,2.705,18],"beyondaime":[0.464,1.383,34],"tau2-airline":[0.46,1.24,99],"nova-63":[0.457,0.309,29],"mhpp":[0.456,1.311,10],"tau2-airline-verified":[0.452,1.131,11],"habermas-machine-decision":[0.452,0.278,38],"tau-voice-airline":[0.452,0.76,29],"arena-hard-v2-hard-prompt":[0.445,0.999,19],"repobench":[0.445,1.044,10],"vsi-bench":[0.443,0.319,55],"draco":[0.428,0.846,19],"imo-answerbench":[0.428,1.706,144],"omni-math":[0.424,1.293,36],"simplevqa":[0.418,0.667,98],"ocrreasoning":[0.412,0.598,15],"bfcl-v4":[0.41,0.827,159],"jamc-qa":[0.41,0.691,31],"bankertoolbench":[0.41,0.744,14],"dude":[0.405,1.073,11],"livecodebench-pro-25q2-easy":[0.397,2.267,38],"gdpval-rubrics":[0.396,1.283,25],"mrcr-v2":[0.394,1.219,22],"ifbench":[0.393,0.907,347],"microvqa":[0.389,0.548,18],"hmmt-2025":[0.388,2.933,89],"charades-sta":[0.385,1.179,24],"harvey-lab-aa":[0.376,1.122,19],"openeqa":[0.37,0.664,12],"tau3-airline":[0.363,1.365,16],"bigcodebench":[0.351,0.536,169],"hmmt-feb-2026":[0.348,2.02,118],"longbench":[0.348,0.505,32],"rw-search":[0.335,0.993,15],"videoholmes":[0.323,0.59,22],"tau2-telecom":[0.322,2.147,194],"advancedif":[0.321,0.789,11],"livecodebench-v5":[0.309,1.909,105],"arkitscenes":[0.304,0.2,11],"xbench-deepsearch":[0.294,0.766,37],"tau2-retail":[0.284,1.512,113],"livecodebench":[0.279,1.769,572],"jevbench":[0.274,1.56,15],"mathvision":[0.273,1.513,181],"hmmt-feb-2025":[0.271,2.859,96],"all-angles-bench":[0.267,0.564,17],"intphys-2":[0.264,0.347,18],"home-appliance-simulator-decision":[0.254,2.587,38],"mars-bench":[0.245,1.318,12],"alpacaeval":[0.243,1.313,44],"arena-hard-v2":[0.24,1.276,84],"labbench2":[0.235,0.787,11],"realkie-fcc-verified":[0.225,0.507,14],"leetcode-contest":[0.223,2.077,13],"tau3-telecom":[0.206,2.369,18],"qivd":[0.205,0.469,11],"aime-2025":[0.202,2.837,424],"arena-hard-v2-creative-writing":[0.189,1.645,18],"charxiv-rq":[0.18,1.067,242],"jgpqa":[0.17,0.908,41],"osworld-g":[0.169,0.863,53],"ocrbenchv2-cn":[0.165,0.295,54],"q-spatial-bench":[0.156,0.694,13],"lvbench":[0.149,0.773,98],"mmmu-pro":[0.145,0.953,219],"odyssey-math":[0.137,1.158,14],"zebralogic":[0.132,2.835,129],"collie":[0.126,1.959,23],"aime-2024":[0.123,3.192,232],"fd-bench-v3-pass1":[0.122,0.753,12],"codeforces-percentile":[0.106,2.702,23],"videoevalpro":[0.105,0.853,26],"buzzbench":[0.1,1.172,19],"hmmt-nov-2025":[0.092,1.993,79],"olympiadbench":[0.09,2.574,75],"gaia-text-only":[0.089,1.057,47],"phyx":[0.083,0.643,11],"lifebench":[0.07,0.614,21],"wemath":[0.063,1.275,49],"ovbench":[0.057,0.433,17],"vibeval":[0.054,0.976,11],"voicebench-commoneval":[0.053,3.214,12],"videosimpleqa":[0.051,0.658,13],"alpacaeval-2.0":[0.039,1.415,121],"fortress-adversarial":[0.034,0.697,17],"design2code":[0.03,1.977,14],"tau1-retail":[0.022,1.081,13],"kmmlu-pro":[0.015,0.962,71],"livebench":[0.01,1.231,141],"collegemath":[0.003,1.138,24],"math-lvl5":[0.003,2.096,43],"docmath":[-0.002,1.006,43],"logicvista":[-0.004,0.878,65],"kmmlu-redux":[-0.013,1.505,42],"naturalcodebench":[-0.013,1.358,14],"multiimg-qa-avg":[-0.024,0.88,19],"theoremqa":[-0.032,1.77,87],"livecodebench-v3":[-0.04,2.43,45],"judgemark-v2-1":[-0.044,1.164,48],"tau2-retail-verified":[-0.044,1.038,11],"kor-bench":[-0.05,0.997,26],"gpqa":[-0.051,1.116,301],"minerva-math":[-0.052,1.375,67],"fullstackbench":[-0.054,0.615,55],"3dsrbench":[-0.055,0.319,20],"vlms-are-blind":[-0.057,1.19,16],"mask":[-0.059,1.048,61],"mathverse-vision":[-0.06,1.133,21],"aime-2026-i":[-0.062,2.132,164],"naturalquestions":[-0.065,1.2,124],"xnli":[-0.066,0.312,15],"mmiu":[-0.069,0.511,40],"flame-react-eval":[-0.076,1.842,10],"mathvision-with-tools":[-0.086,1.653,10],"mathverse-mini":[-0.096,1.149,69],"graphwalks-bfs":[-0.096,1.234,18],"multipl-e-humaneval":[-0.105,1.355,22],"xbench-deepsearch-2025.05":[-0.108,0.892,18],"multipl-e-mbpp":[-0.115,0.789,22],"claw-eval":[-0.117,0.645,59],"hiddenmath":[-0.117,1.417,11],"charxiv-rq-with-tools":[-0.121,1.033,32],"ocrbenchv2-en":[-0.121,0.357,67],"gpqa-diamond":[-0.136,1.25,573],"jfbench":[-0.144,0.84,10],"mmlu-prox-ja":[-0.154,1.413,41],"mmmu-pro-with-tools":[-0.161,0.765,19],"mathverse":[-0.17,1.332,19],"evalperf":[-0.17,2.42,28],"jhumaneval-plus":[-0.176,0.907,10],"dynamath":[-0.184,0.903,68],"pmc-vqa":[-0.198,0.277,35],"webwalker-qa":[-0.208,0.683,12],"discox":[-0.217,0.76,12],"bfcl-v3-ja":[-0.223,1.385,11],"showdown":[-0.233,0.995,18],"voicebench-alpacaeval":[-0.236,3.437,14],"brumo25":[-0.236,2.119,25],"piobench":[-0.262,0.475,13],"agentdojo":[-0.272,1.955,17],"deepsearchqa-f1":[-0.272,1.11,21],"sysbench":[-0.299,1.463,16],"gsm8k-decision":[-0.299,1.107,38],"mmvu":[-0.306,0.679,68],"aider-code-editing":[-0.314,1.852,51],"webvoyager":[-0.319,0.978,24],"ovobench":[-0.325,0.585,20],"arena-hard":[-0.361,2.466,85],"tau3-retail":[-0.367,0.913,16],"voicebench-ifeval":[-0.372,1.359,23],"m-ifeval-ja":[-0.378,1.018,12],"inverse-ifeval":[-0.385,0.709,12],"deepmind-math":[-0.391,1.975,18],"tvbench":[-0.412,0.572,25],"mmmu-test":[-0.414,0.623,26],"math500-ja":[-0.416,1.674,10],"graphwalks-bfs-256k":[-0.435,0.676,17],"pinchbench":[-0.439,0.972,46],"muirbench":[-0.444,0.887,80],"amc-23":[-0.444,2.019,62],"longmemeval":[-0.448,0.713,10],"videommmu":[-0.451,0.891,92],"toolsandbox":[-0.452,0.968,12],"mm-ifeval":[-0.459,0.689,42],"multi-ifeval":[-0.462,1.026,15],"cosmos-reason-bench":[-0.467,0.404,13],"big-bench-audio":[-0.48,2.151,43],"mmlu-pro":[-0.482,1.14,675],"fd-bench-v3":[-0.511,1.205,10],"gaokao-2023-en":[-0.513,1.409,24],"voicebench-sd-qa":[-0.534,1.281,13],"math":[-0.54,2.188,449],"mirb":[-0.541,0.844,19],"vl-rewardbench":[-0.547,0.464,14],"acebench":[-0.567,0.898,17],"turkishmmlu":[-0.575,1.318,12],"acp-bench-mcq":[-0.577,1.284,14],"sat":[-0.577,0.848,24],"mmlu-prox":[-0.577,0.824,58],"cruxeval":[-0.579,1.616,54],"multipl-e":[-0.587,1.278,126],"wildbench-v2":[-0.589,0.661,20],"bfcl-v3":[-0.602,0.636,125],"creative-writing-v3":[-0.603,1.247,43],"roo-code-evals":[-0.607,1.957,33],"where2place":[-0.608,0.292,28],"ruler-1m":[-0.619,1.235,21],"kmmlu":[-0.623,0.778,29],"include":[-0.623,0.878,66],"livesports-3k":[-0.623,0.649,13],"vlmsareblind":[-0.641,1.451,26],"mme-realworld-cn":[-0.643,0.455,25],"general-tool-use":[-0.652,0.565,18],"csimpleqa":[-0.666,0.563,36],"pixmo-points":[-0.677,0.267,13],"visualwebbench-avg":[-0.677,0.992,25],"voicebench-mmsu":[-0.68,0.98,13],"blink":[-0.685,0.532,166],"gsm8k-ja":[-0.685,0.932,11],"cruxeval-decision":[-0.687,0.9,38],"humaneval-x":[-0.693,1.575,57],"mmmu":[-0.713,0.757,299],"crux-i":[-0.725,1.142,102],"wildvision":[-0.738,1.259,23],"simplevqa-with-tools":[-0.749,0.4,12],"musr":[-0.759,0.625,83],"vqa-rad":[-0.763,1.219,11],"crux-o":[-0.782,1.204,129],"hallusionbench":[-0.783,0.35,163],"indommlu":[-0.783,0.894,12],"motionbench":[-0.794,0.371,55],"medmcqa":[-0.797,0.56,27],"cibench":[-0.802,1.46,13],"multi-if":[-0.81,0.827,128],"mme-realworld-en":[-0.81,0.451,46],"maxife":[-0.817,0.857,29],"jec-qa":[-0.823,0.693,16],"jmmlu":[-0.824,1.186,23],"gsm-plus":[-0.845,1.675,46],"mathvista-mini":[-0.845,0.889,203],"mmvet-v2":[-0.847,0.808,21],"math500":[-0.856,2.206,253],"new-yorker-caption-matching":[-0.856,0.75,38],"ifeval-strict-prompt":[-0.876,1.458,52],"ocnli":[-0.881,0.666,37],"evalplus":[-0.887,1.466,107],"humaneval-plus":[-0.901,1.524,365],"mmmlu":[-0.903,0.954,110],"math-100-ja":[-0.911,1.957,31],"ruler-256k":[-0.917,1.448,11],"pixmocount":[-0.918,0.588,66],"api-bank-decision":[-0.93,1.331,36],"webclick":[-0.932,1.313,18],"medqa":[-0.951,1.144,39],"ruler-512k":[-0.954,1.344,10],"humaneval":[-0.957,1.863,505],"global-mmlu":[-0.971,0.802,44],"longvideobench":[-0.978,0.471,86],"agieval":[-0.98,1.01,211],"arabicmmlu":[-0.983,0.873,16],"charxiv-dq":[-0.991,1.199,142],"voicebench-mmsu-audio":[-0.996,0.558,21],"ccbench":[-0.997,0.345,11],"l-eval":[-0.999,0.989,19],"click":[-1.002,0.803,23],"truthfulqa":[-1.003,0.426,144],"voicebench-bbh":[-1.005,1.093,13],"videomme":[-1.012,0.784,35],"mbpp-plus":[-1.02,0.808,328],"bbh-decision":[-1.022,0.867,38],"egoschema":[-1.025,0.535,62],"mmvet":[-1.039,0.757,102],"drop":[-1.06,1.278,148],"robospatialhome":[-1.064,0.277,48],"mmstar":[-1.08,0.591,209],"infoqa":[-1.11,0.97,49],"mmlu-stem":[-1.115,1.265,94],"mbpp":[-1.126,1.339,442],"hrbench8k":[-1.131,0.64,30],"mgsm":[-1.131,1.437,133],"multilingual-mmlu":[-1.132,1.072,28],"video-mme":[-1.133,0.647,25],"videomme-nosub":[-1.135,0.596,115],"mmlu-med":[-1.14,0.998,11],"medqa-mcmle":[-1.15,1.084,16],"hae-rae-bench":[-1.152,0.962,19],"mathvista":[-1.174,0.734,109],"vcr-en-easy":[-1.177,1.821,27],"frames":[-1.184,0.667,50],"lingoqa":[-1.194,0.416,36],"jhumaneval":[-1.208,1.325,31],"facts-grounding":[-1.218,0.287,74],"bbh":[-1.232,1.207,425],"mlvu":[-1.235,0.641,99],"acp-bench-bool":[-1.254,0.948,14],"screenqa-complex":[-1.284,0.806,12],"squad-v2.0":[-1.288,1.32,33],"mantis":[-1.291,0.79,39],"gsm8k":[-1.292,1.978,570],"global-piqa":[-1.3,0.863,54],"ground-ui-1k":[-1.317,0.853,18],"gaokao-bench":[-1.329,1.273,82],"mmlu-redux":[-1.336,1.123,254],"hrbench4k":[-1.337,0.687,33],"infovqa":[-1.348,0.876,162],"flores":[-1.356,1.082,16],"triviaqa":[-1.388,0.9,156],"spider":[-1.406,0.69,21],"aa-speech-agent-task-success":[-1.406,0.88,22],"cmath":[-1.408,1.68,79],"cladder":[-1.418,0.696,38],"phishnchips":[-1.448,0.466,38],"when2call":[-1.472,0.597,46],"t-eval":[-1.492,0.965,13],"v-star":[-1.498,0.73,70],"videomme-sub":[-1.5,0.62,89],"ruler-128k":[-1.502,0.807,43],"bpomp-decision":[-1.516,1.243,38],"point-bench":[-1.522,0.236,43],"c-eval":[-1.531,0.92,299],"cmmlu":[-1.539,0.928,256],"graphwalks-parents":[-1.554,1.228,13],"mmt-bench":[-1.557,0.408,61],"voicebench-openbookqa":[-1.569,1.128,12],"aa-fdb-backchannel":[-1.572,1.085,32],"tempcompass":[-1.579,0.587,31],"mmlu":[-1.587,0.915,647],"multilingual-mmbench":[-1.619,0.676,12],"global-mmlu-lite":[-1.625,0.716,49],"arc-challenge":[-1.636,1.52,337],"humicroedit-decision":[-1.637,0.28,38],"bbh-zh":[-1.64,0.803,14],"pinchbench-avg":[-1.669,0.483,34],"r-bench":[-1.679,0.655,19],"caselaw-v2":[-1.679,0.2,67],"eqbench":[-1.683,0.867,77],"prontoqa":[-1.684,1.488,10],"chinese-simpleqa":[-1.7,0.399,28],"wmt24-plus-plus":[-1.702,0.563,65],"screenspot-v2":[-1.711,1.041,53],"siqa":[-1.745,0.33,56],"bfcl-decision":[-1.82,1.525,38],"ifeval":[-1.829,0.798,450],"coqa":[-1.841,0.365,10],"factscore":[-1.864,0.733,11],"cfcolor-decision":[-1.874,0.253,38],"belebele":[-1.881,0.866,22],"perceptiontest":[-1.884,0.474,32],"realworldqa":[-1.892,0.463,224],"xcopa":[-1.915,0.464,15],"aa-fdb-pause-handling":[-1.938,1.266,32],"pubmedqa":[-1.959,0.554,13],"mmbench-v1.1-cn":[-1.961,0.737,169],"socialiqa":[-1.974,0.974,21],"local-agent-bench":[-2.002,0.793,16],"race":[-2.003,1.262,66],"seed-bench-2-plus":[-2.019,0.427,35],"tabmwp":[-2.026,0.363,13],"hrm8k":[-2.059,0.752,11],"aa-fdb-interruption":[-2.067,1.065,32],"mmmb":[-2.097,0.719,20],"fortress-benign":[-2.129,0.914,17],"mvbench":[-2.139,0.328,114],"mmc-benchmark":[-2.142,0.718,13],"openbookqa":[-2.162,0.2,97],"llava-bench-in-the-wild":[-2.163,1.006,36],"race-high":[-2.178,0.2,21],"countbench":[-2.184,0.892,96],"wsc":[-2.195,1.002,20],"cc-ocr":[-2.218,0.397,42],"mmbench-cn":[-2.229,0.75,77],"c3":[-2.231,0.919,60],"ocrbench":[-2.233,0.651,227],"crpe":[-2.241,0.617,18],"mmbench-v1.1-en":[-2.256,0.694,191],"hover":[-2.263,0.494,38],"ruler-16k":[-2.306,1.213,27],"arc-easy":[-2.331,1.586,163],"corpusqa":[-2.341,0.2,17],"screenqa-short":[-2.36,0.712,12],"longfact-objects":[-2.365,1.059,11],"chid":[-2.373,1.054,28],"longfact-concepts":[-2.381,1.083,11],"q-bench":[-2.381,0.6,10],"ruler-32k":[-2.414,1.012,34],"commonsenseqa":[-2.421,0.79,104],"da-2k":[-2.454,0.403,13],"ai2d":[-2.457,0.716,254],"wild-jailbreak":[-2.464,0.653,10],"mmbench":[-2.475,0.717,89],"rewardbench":[-2.482,0.599,33],"slake":[-2.518,0.367,39],"mmbench-v1.1-en-dev":[-2.526,0.625,77],"ccpm":[-2.54,0.846,13],"scienceqa":[-2.566,1.066,28],"cluewsc":[-2.598,0.734,49],"winogrande":[-2.646,0.611,286],"omnidocbench":[-2.68,0.495,30],"chartqa":[-2.682,0.623,210],"alpacaeval-1.0":[-2.683,1.226,17],"countbenchqa":[-2.74,0.624,49],"sqa":[-2.747,0.435,10],"hellaswag":[-2.774,0.666,375],"ruler-64k":[-2.786,0.676,38],"docvqa":[-2.801,0.906,229],"xstest":[-2.811,0.809,17],"ruler-8k":[-2.87,1.041,28],"bfcl-v3-live":[-2.884,0.335,19],"copa":[-2.897,1.024,14],"mmhal-bench-hallucination-rate":[-2.905,0.303,18],"textvqa":[-2.934,0.486,179],"race-middle":[-2.964,0.603,36],"olmocr-bench":[-3.013,0.252,15],"screenspot":[-3.136,0.475,36],"seed-bench-img":[-3.149,0.397,69],"websrc":[-3.289,0.813,18],"cv-bench":[-3.297,0.439,70],"embspatialbench":[-3.341,0.318,71],"wildguardtest":[-3.404,0.478,17],"voicebench-mau-v05-15-25":[-3.44,0.259,25],"seedbench":[-3.445,0.366,24],"boolq":[-3.473,0.592,116],"img-qa-avg":[-3.582,0.352,22],"erqa-plus":[-3.784,0.342,13],"writingbench":[-3.861,0.336,40],"cybench":[-3.881,0.2,21],"miabench":[-4.178,0.529,23],"ruler-4k":[-4.209,0.771,16],"roboafford":[-4.391,0.2,17],"bfcl":[-4.399,0.255,23],"piqa":[-4.494,0.415,182],"sciq":[-4.657,0.672,24],"harmbench":[-5.058,0.72,12],"sharerobot-traj":[-5.286,0.238,13],"vabench-visual-trace":[-5.378,0.301,13],"voicebench-advbench":[-5.437,0.747,13],"convfinqa":[-5.539,0.2,10],"mixeval":[-5.567,0.2,32],"textquests-harm":[-5.758,0.226,15],"roborefit":[-5.899,0.241,13],"lambada":[-6.004,0.2,47],"refcoco":[-6.043,0.312,84],"nextqa":[-6.061,0.25,22],"attaq":[-6.078,0.297,18],"aa-fdb-turn-taking":[-6.119,0.617,32],"squad-v1.1":[-6.175,0.394,15],"cmrc2018":[-6.476,0.201,16],"refcocoplus":[-6.867,0.258,22],"vqav2":[-7.152,0.2,72],"hhem-v2.1":[-7.27,0.453,15],"strongreject":[-7.605,0.468,17],"refcocog":[-9.308,0.2,24],"omnidocbench-v1.6":[-9.755,0.227,10],"pope":[-10.472,0.2,50],"do-not-answer":[-14.116,0.2,11]},"core":[{"rank":1,"id":"claude-sonnet-5.5","name":"Claude Sonnet 5.5","provider":"anthropic","score":79.17},{"rank":2,"id":"claude-opus-5.5","name":"Claude Opus 5.5","provider":"anthropic","score":78.12},{"rank":3,"id":"kimi-k3.1-pro","name":"Kimi-K3.1 Pro","provider":"moonshotai","score":77.82},{"rank":4,"id":"claude-fable-5.1","name":"Claude Fable 5.1","provider":"anthropic","score":74.85},{"rank":5,"id":"claude-opus-5","name":"Claude Opus 5","provider":"anthropic","score":74.84},{"rank":6,"id":"gpt-6-astra","name":"GPT-6 Astra","provider":"openai","score":74.41},{"rank":7,"id":"claude-mythos-5","name":"Claude Mythos 5","provider":"anthropic","score":72.23},{"rank":8,"id":"claude-fable-5","name":"Claude Fable 5","provider":"anthropic","score":71.81},{"rank":9,"id":"gpt-5.6-sol","name":"GPT-5.6 Sol","provider":"openai","score":71.53},{"rank":10,"id":"grok-4.7","name":"Grok 4.7","provider":"xai","score":71.06}],"ext":{"kimi-k3.1-pro":[2.456,0.07,63.35],"gpt-6-astra":[2.447,0.035,73.76],"claude-opus-5.5":[2.415,0.04,69.29],"gemini-4-argon":[2.379,0.061,68.65],"claude-sonnet-5.5":[2.376,0.056,70.83],"muse-wonder-full":[2.354,0.082,61.38],"claude-fable-5.1":[2.316,0.035,65.94],"claude-opus-5.5-max":[2.283,0.08,74.33],"claude-opus-5":[2.274,0.026,68.1],"muse-wonder":[2.266,0.077,57.8],"gpt-6.1-sol":[2.255,0.064,71.37],"claude-fable-5":[2.247,0.027,68.34],"claude-mythos-5":[2.221,0.048,76.59],"gpt-5.6-sol":[2.185,0.023,69.12],"deepseek-v4.1-flash-1017":[2.145,0.055,53.91],"minimax-m3.1-flash":[2.135,0.065,61.99],"mimo-v2.6-pro-rl":[2.133,0.057,58.06],"muse-spark-1.3":[2.125,0.059,61.47],"veriloop-e2":[2.123,0.064,72.38],"grok-4.7":[2.121,0.067,59.7],"claude-mythos-preview":[2.107,0.057,71.88],"ling-3.1-flash":[2.106,0.053,66.55],"gemini-3.8-flash":[2.105,0.049,69.28],"qwen3.8-max":[2.09,0.03,68.46],"grok-4.6":[2.081,0.059,58],"deepseek-v4.1-flash":[2.073,0.038,59.03],"glm-5.3":[2.059,0.033,58.46],"atria-dawn-preview":[2.053,0.058,65.17],"atria-dawn":[2.053,0.053,63.95],"gpt-6-sol":[2.052,0.064,59.98],"kimi-k3":[2.016,0.027,65.72],"gemini-3.7-flash":[2.002,0.046,61.79],"mimo-v2.6-flash-rl":[1.998,0.058,52.65],"hy4-preview":[1.998,0.04,58.22],"naive-n0.5-flash":[1.992,0.073,60.25],"gpt-5.6-terra":[1.99,0.035,62.41],"gpt-5.5":[1.969,0.022,66.66],"claude-haiku-5.5":[1.965,0.065,59.86],"claude-opus-4.8":[1.949,0.022,64.29],"muse-spark-open":[1.932,0.063,65.92],"grok-4.5":[1.931,0.05,55.36],"nex-n2.5-pro":[1.927,0.062,66.84],"ornith-1.5-397b":[1.903,0.059,68.43],"gpt-5.4-pro":[1.897,0.06,68.67],"deepseek-v4-pro-0813":[1.89,0.033,54.72],"muse-spark-1.2":[1.877,0.058,59],"qwen3.8-omni-flash":[1.868,0.076,75.59],"fugu-ultra":[1.867,0.094,72.73],"glm-5.3-flash":[1.867,0.036,62.55],"muse-spark-1.1":[1.864,0.061,67.2],"qwen3.8-flash-next":[1.861,0.039,68.56],"deepseek-v4-flash-vision-exp":[1.836,0.057,59.44],"claude-sonnet-5":[1.81,0.035,55.23],"gpt-5.6-luna":[1.808,0.034,63.54],"gemini-3.6-flash":[1.8,0.05,65.69],"physbrain1.5-8b":[1.788,0.171,72.54],"intern-s2-397b":[1.788,0.084,67.76],"deepseek-v4-flash-0731":[1.778,0.032,60.04],"ornith-1.5-122b":[1.76,0.069,69.16],"fugu":[1.76,0.092,70.3],"gpt-5.4":[1.756,0.027,67.64],"seed2.1-pro":[1.746,0.034,66.75],"mirothinker-h1":[1.738,0.095,76.4],"sage-a1.5":[1.73,0.084,62.75],"glm-5.2":[1.726,0.027,58.53],"gpt-6-luna":[1.72,0.065,45.42],"dots3-note-preview":[1.715,0.052,70.66],"intern-s2-preview-397b":[1.704,0.078,65.9],"claude-opus-4.7":[1.704,0.028,63.28],"seed2.1-turbo":[1.702,0.036,66.48],"gpt-5.2-high":[1.7,0.036,71],"gemini-3.1-pro":[1.697,0.022,62.87],"beam":[1.689,0.05,63.67],"gpt-5.2-pro":[1.671,0.065,63.48],"gpt-5.4-thinking":[1.668,0.077,65.31],"nex-n2-pro":[1.656,0.054,62.77],"claude-opus-4.6":[1.654,0.025,65.89],"gemini-3.5-flash":[1.647,0.045,64.04],"gpt-5.2-extra-high":[1.644,0.062,69.07],"gpt-5.3-codex":[1.642,0.082,68.38],"gpt-6-luna-max":[1.641,0.079,56.03],"qwen3.7-max":[1.624,0.033,62.67],"deepseek-v4-pro-thinking-max":[1.622,0.03,64.99],"kimi-k2.7-code":[1.61,0.056,55.23],"ling-3.0-flash-vl":[1.608,0.12,76.96],"deepseek-v4-pro":[1.601,0.029,59.75],"nex-n2.5-mini":[1.601,0.062,54.87],"k2-horizon-375b-a23b":[1.582,0.071,51.55],"ornith-1.0-397b":[1.576,0.059,55.95],"kimi-k2.6-thinking":[1.572,0.03,68.7],"hy3":[1.57,0.033,51.99],"deepseek-v4-pro-thinking":[1.569,0.057,68.93],"mercury-3":[1.563,0.089,63.37],"qwen3.7-plus":[1.559,0.036,65.74],"qwen3.8-27b":[1.553,0.034,68.86],"kimi-k2.6":[1.545,0.048,63.78],"ax-k2":[1.544,0.068,66.93],"occamy-1.0":[1.53,0.069,54.01],"gpt-5.2-thinking-xhigh":[1.527,0.043,69.32],"seed2.0-pro":[1.526,0.034,69.79],"longcat-2.0":[1.524,0.089,78.98],"claude-sonnet-4.6":[1.52,0.033,62.6],"qwen3.6-max-preview":[1.519,0.119,56.13],"gpt-5.2-thinking":[1.516,0.044,68.36],"motif-3":[1.511,0.072,63.16],"seed2.0-lite-0428":[1.51,0.051,67.1],"grok-4.2":[1.507,0.066,63.07],"deepseek-v4-flash":[1.493,0.032,59.23],"yuan3.0-ultra":[1.491,0.228,67.76],"deepseek-v4-flash-thinking-max":[1.486,0.034,60.03],"muse-spark":[1.486,0.05,57.25],"minimax-m3":[1.481,0.039,55.1],"gemini-3-pro":[1.475,0.022,68.6],"stepaudio-3-realtime":[1.474,0.102,80.19],"apodex-1.0":[1.473,0.082,50.41],"mirothinker-v1.5-235b":[1.466,0.1,67.65],"gpt-5.2":[1.463,0.029,64.45],"longcat-flash-thinking-2601":[1.459,0.06,72.72],"glm-5v-turbo":[1.451,0.098,73.44],"kat-coder-pro-v2":[1.443,0.1,71.29],"grm-3.2-sky":[1.44,0.068,73.5],"glm-5.1":[1.436,0.029,60.77],"qwen3.6-plus":[1.43,0.036,67.81],"grok-voice-3.0":[1.422,0.102,88.46],"ornith-1.5-35b-a3b":[1.421,0.047,49.18],"gemini-3-flash":[1.42,0.028,64.87],"inkling":[1.419,0.041,56.06],"claude-opus-4.5-thinking":[1.416,0.046,68.25],"mirothinker-1.7":[1.404,0.093,68.09],"gemini-3-pro-preview":[1.401,0.042,71.07],"ling-3.0-flash":[1.401,0.06,70.4],"inkling-small":[1.396,0.039,59.43],"bigbang-v1":[1.396,0.057,47.9],"qwen3.5-397b-a17b":[1.386,0.028,65.03],"intern-s2-preview":[1.376,0.071,57.75],"deepseek-v4-flash-thinking":[1.366,0.057,63.02],"claude-opus-4.5":[1.366,0.025,65.16],"openpangu-2.0-pro-thinking":[1.363,0.056,66.19],"gpt-6-luna-high":[1.356,0.079,49.1],"glm-5":[1.35,0.036,65.26],"mimo-v2-pro":[1.346,0.092,59.18],"ring-2.6-1t-xhigh":[1.342,0.055,66.75],"longcat-flash-thinking-zigzag":[1.335,0.067,72.52],"nemotron-3.5-bolt-74b-a9b":[1.33,0.085,54.02],"step-3.7-flash":[1.315,0.048,59.78],"muse-glimmer-30b":[1.314,0.045,59.15],"solar-pro-4":[1.307,0.074,65.26],"nemotron-3.5-super-vl-120b-a12b":[1.304,0.044,57.2],"kimi-k2.5-thinking":[1.302,0.029,66.15],"seed2.0-lite":[1.3,0.035,66.56],"mirothinker-1.7-mini":[1.299,0.09,64.87],"qwen3.6-27b":[1.289,0.035,67.54],"mimo-v2.5-pro":[1.286,0.048,40.29],"step-3.5-flash-20260204":[1.286,0.042,58.78],"mai-thinking-1":[1.286,0.077,77.57],"intern-s2-mobius":[1.286,0.087,63.12],"kimi-k2.5":[1.283,0.032,65.24],"gpt-6-luna-medium":[1.279,0.06,52.97],"hy3-preview":[1.278,0.045,47.73],"ornith-1.0-35b":[1.275,0.058,47.76],"gpt-5-codex":[1.273,0.083,56.72],"glm-4.7-thinking":[1.271,0.064,66.3],"solar-open-2-250b":[1.271,0.063,63.89],"gpt-5.4-mini":[1.267,0.038,60.39],"qwen3-max-thinking":[1.264,0.049,68.14],"gpt-5.1-high":[1.257,0.05,57.54],"gpt-5-thinking":[1.251,0.062,60.71],"mimo-v2.5":[1.249,0.051,61.47],"seed1.8":[1.247,0.039,68.77],"gemini-3.5-flash-lite":[1.239,0.057,63.53],"trinity-large-thinking":[1.237,0.095,75.8],"hy-embodied-vlm-1.0":[1.237,0.159,67.21],"nemotron-3-ultra":[1.235,0.038,59.97],"minimax-m2.5":[1.224,0.061,55.63],"mirothinker-v1.0-72b":[1.218,0.102,61.06],"gpt-5.1-thinking":[1.218,0.062,54],"raon-1-mini-preview":[1.218,0.07,62.74],"qwen3.5-122b-a10b":[1.217,0.034,65.47],"oxcoder-9b":[1.215,0.08,53.24],"mirothinker-v1.5-30b":[1.212,0.1,60.86],"xing4.0-29b-a4b":[1.21,0.096,69.56],"grok-voice-1.0":[1.206,0.107,76.79],"deepseek-v3.2-thinking":[1.192,0.032,62.81],"nemotron-3.5-super-vl-120b-a12b-nvfp4":[1.192,0.066,59.48],"qwen3.5-27b":[1.184,0.033,68.43],"apodex-1.0-mini":[1.183,0.064,44.19],"gpt-5":[1.181,0.029,68.54],"comet-60b-a12b-fp8":[1.18,0.065,59.03],"mercury-2.5":[1.177,0.11,50.98],"ternary-bonsai-2-27b":[1.174,0.078,86.92],"kimi-k2-thinking":[1.17,0.039,61.8],"nex-n2-mini":[1.163,0.039,45.69],"gpt-5-high":[1.16,0.027,65.73],"gpt-5-medium":[1.157,0.063,63.46],"comet-60b-a12b":[1.154,0.065,58.56],"claude-haiku-5.5-medium":[1.145,0.063,54.04],"qwen-audio-3.0-realtime-plus":[1.14,0.114,81.6],"step3-vl-10b-pacore":[1.138,0.084,84.84],"qwen3.6-35b-a3b":[1.134,0.027,58.96],"kolibri-1":[1.133,0.065,66.45],"skywork-r1v4":[1.133,0.164,68.21],"openpangu-2.0-flash-thinking":[1.132,0.056,62.28],"spark-x2.6-4b":[1.132,0.065,63.89],"comet-60b-a12b-nvfp4":[1.128,0.066,58.01],"grok-voice-2.0":[1.125,0.103,82.41],"agents-a1":[1.121,0.048,47.57],"agents-a1-4b":[1.12,0.086,57.74],"qwen3.8-27b-ud-q4-k-xl":[1.119,0.077,86.7],"glm-4.7":[1.107,0.047,63.32],"iquest-coder-v1-40b-thinking":[1.107,0.139,86.95],"minimax-m2.7":[1.106,0.035,55.86],"ernie-5.0":[1.104,0.055,77.25],"gemini-3.8-live-extended-thinking-high":[1.104,0.115,84.5],"mimo-v2-flash":[1.094,0.049,61.31],"mai-code-1-flash":[1.093,0.081,58.59],"qwen3.5-35b-a3b":[1.092,0.029,59.84],"nemotron-cascade-2-30b-a3b":[1.09,0.057,65.69],"gpt-5.1":[1.088,0.041,56.93],"ring-2.6-1t-high":[1.082,0.08,75.57],"intern-s1-pro":[1.079,0.063,58.28],"physbrain1.5-2b":[1.079,0.17,66.57],"k-exaone-2.0":[1.078,0.069,67.2],"claude-sonnet-4.5":[1.073,0.025,61.26],"grok-4":[1.072,0.035,56.19],"qwen3.5-omni-plus":[1.071,0.069,73.27],"snowdon-1.1-small":[1.07,0.086,67.15],"nova-2-pro":[1.064,0.077,73.76],"tongyi-deepresearch":[1.063,0.095,60.5],"o3":[1.063,0.034,60.82],"vibethinker-3b":[1.057,0.069,80.21],"eleven-realtime-v1-max":[1.054,0.115,78.35],"neohorse-1-9b":[1.047,0.117,66.62],"deepseek-v3.2":[1.041,0.031,59.74],"gpt-5-mini-high":[1.037,0.033,61.34],"mimo-v2-omni":[1.035,0.12,77.65],"ring-1t-preview":[1.032,0.066,76.78],"nemotron-3-super-120b-a12b":[1.03,0.038,58.84],"ornith-1.5-9b":[1.026,0.063,51.16],"nanbeige4.2-3b":[1.025,0.063,56.1],"k2-horizon-7b":[1.024,0.058,60.91],"hy-embodied-0.5-mot-2b":[1.016,0.247,68.49],"ornith-1.0-9b":[1.013,0.064,41.15],"keye-vl-2.0-30b-a3b":[1.007,0.126,65.41],"nova-2-omni":[1.004,0.093,74.86],"grok-4-fast":[1,0.058,63.63],"claude-4.5-sonnet-thinking":[0.993,0.042,57.81],"gpt-live-1-low":[0.986,0.109,82.69],"gpt-5-2025-08-07":[0.984,0.098,62.95],"nemotron-labs-3-puzzle-75b-a9b":[0.984,0.063,69.92],"gpt-5-low":[0.979,0.065,57.55],"gemma-4-31b-it":[0.963,0.032,64.69],"holo1.5-72b":[0.958,0.132,84.33],"mistral-medium-3.5":[0.953,0.053,56.28],"k-exaone":[0.953,0.047,65.52],"longcat-flash-thinking":[0.949,0.082,71.74],"gemini-3.1-flash-lite":[0.949,0.053,52.9],"o3-high":[0.946,0.038,60.17],"exaone-4.5-33b-thinking":[0.943,0.062,70.55],"ling-2.6-1t":[0.943,0.072,60.11],"deepseek-v3.1-terminus-thinking":[0.941,0.06,61.42],"gpt-live-1-medium":[0.939,0.115,87.06],"gpt-oss-120b-high":[0.937,0.043,65.13],"gpt-realtime-2.0-xhigh":[0.934,0.12,74.28],"gemini-3-flash-preview":[0.932,0.081,65.3],"glm-4.6":[0.927,0.042,59.78],"ovis2.6-80b-a3b":[0.926,0.099,77.44],"o3-2025-04-16":[0.921,0.105,62.89],"qwen3-vl-235b-a22b-thinking":[0.918,0.045,67.73],"ovis2.6-30b-a3b":[0.915,0.091,79.37],"qwen3-235b-a22b-thinking-2507":[0.91,0.034,64.24],"gemini-2.5-pro":[0.907,0.022,63.27],"sarvam-105b":[0.907,0.063,77.22],"minimax-m2.1":[0.906,0.048,57.04],"o4-mini-high":[0.902,0.047,56.47],"rynnbrain1.1-9b":[0.899,0.173,63.14],"gpt-5-mini":[0.898,0.03,63.47],"k2-horizon-3.7b":[0.898,0.061,55.78],"minimax-m2":[0.895,0.047,58.44],"gpt-6-luna-low":[0.891,0.081,45.03],"claude-opus-4.1":[0.889,0.045,61.18],"gpt-5.4-nano":[0.888,0.053,47.52],"claude-opus-4-thinking":[0.885,0.08,65.56],"nanbeige4.1-3b":[0.882,0.072,60.95],"ling-2.5-1t":[0.879,0.072,59.33],"pplx-decider-v1.2":[0.878,0.081,75.49],"claude-sonnet-4-thinking":[0.87,0.091,57.86],"zdtaichu5.0-9b":[0.868,0.068,74.92],"cogito-671b-v2.1":[0.867,0.087,65.79],"iquest-coder-v1-40b-instruct":[0.866,0.065,67.77],"step3-vl-10b-sere":[0.865,0.084,81.2],"deepseek-v3.1-terminus":[0.865,0.047,54.98],"kimi-k2-0905-preview":[0.857,0.078,41.64],"openpangu-2.0-pro":[0.857,0.06,56.1],"telechat3-coder-36b-thinking":[0.857,0.1,75.41],"nova-2-lite":[0.853,0.072,64.95],"o4-mini":[0.852,0.044,48.61],"qwenlong-l1.5-30b-a3b":[0.844,0.084,76.42],"qwen3-235b-2507":[0.843,0.084,57.47],"qianfan-ocr":[0.841,0.188,78.74],"gemma-4-26b-a4b-it":[0.841,0.034,52.85],"seed1.5-vl-thinking":[0.84,0.068,64.9],"embodied-r1.5-8b":[0.838,0.174,64.89],"dots-vlm1":[0.834,0.077,73.91],"intellect-3":[0.828,0.065,75.62],"minicpm-v-4.7-35b-a3b":[0.827,0.092,74.52],"ring-flash-2.0":[0.825,0.073,68.92],"qwen-3-235b-a22b-thinking":[0.821,0.064,77.19],"golongrl-30b-a3b":[0.819,0.086,75.2],"deepseek-v3.1-thinking":[0.819,0.051,54.05],"qwen3-vl-235b-a22b":[0.818,0.055,63.76],"openpangu-r-72b-2512-slow-thinking":[0.816,0.058,74.77],"ling-3.0-tiny":[0.814,0.085,50.21],"qwen3-next-80b-a3b-thinking":[0.814,0.035,66],"iquest-coder-v1-40b-loop-instruct":[0.812,0.065,67.34],"holo2-8b":[0.812,0.137,76.07],"grok-4.1-fast":[0.812,0.051,46.5],"granite-4.2-30b":[0.81,0.059,55],"neohorse-1-4b":[0.81,0.114,62.25],"spark-x2.5-4b":[0.807,0.058,52.99],"vllm-sr-d3":[0.8,0.076,74.34],"laguna-xs-2.1":[0.793,0.092,45.6],"hy-2.0-thinking":[0.793,0.082,42.83],"command-a-plus-05-2026":[0.791,0.064,56.57],"gpt-realtime-2.1-high":[0.788,0.094,75.05],"claude-4.5-haiku":[0.788,0.031,48.84],"nemotron-labs-dory1.0-4b-4loop":[0.787,0.1,42.05],"seed2.0-mini":[0.786,0.044,59.12],"qwen3-vl-235b-a22b-instruct":[0.781,0.131,71.67],"ring-flash-linear-2.0":[0.777,0.073,67.02],"deepseek-v3.2-exp":[0.777,0.042,64.46],"longcat-flash-omni":[0.775,0.103,83.11],"qwen3.5-9b":[0.774,0.028,60.39],"gemma-4-26b-a4b":[0.768,0.063,65.77],"qwen3-vl-32b-thinking":[0.768,0.053,74.39],"deepseek-r1-0528":[0.768,0.035,57.63],"lfm2.5-24b-a2b":[0.764,0.093,57.77],"openreasoning-nemotron-32b":[0.762,0.07,65.08],"clef":[0.76,0.074,69.25],"gpt-oss-120b":[0.76,0.033,56.01],"gpt-5-mini-medium":[0.76,0.067,49.86],"seed-oss-36b-instruct":[0.755,0.071,69.24],"gemini-2.5-pro-preview-06-05":[0.754,0.063,48.22],"openpangu-2.0-flash":[0.753,0.065,56.08],"gpt-oss-swallow-120b-rl-v0.1":[0.753,0.097,79.44],"holo1.5-7b":[0.751,0.132,81.66],"gpt-realtime-2.0-high":[0.742,0.1,73.25],"longcat-flash-lite-sparse":[0.741,0.063,61.07],"clef-flash":[0.733,0.084,68.14],"claude-3.7-sonnet-thinking":[0.732,0.08,66.47],"nemotron-labs-dory1.0-4b":[0.727,0.1,40.86],"tml-interaction-small":[0.727,0.138,74.72],"glm-4.5":[0.727,0.045,54.18],"kimi-k2-instruct-0905":[0.726,0.055,63.55],"qwen3-max-instruct-preview":[0.722,0.075,62.01],"nemotron-3-nano-30b-a3b":[0.72,0.045,61.31],"step3-vl-10b":[0.716,0.061,69.52],"glm-4.5v":[0.715,0.068,67.65],"glm-4.7-flash":[0.715,0.047,61.69],"minicpm5-2b":[0.714,0.052,56.23],"minimax-m1-80k":[0.713,0.059,63.24],"zwz-8b":[0.711,0.169,67.51],"qwen3-coder-480b-a35b-instruct":[0.708,0.053,66.62],"molmo2-er":[0.706,0.218,65.81],"nemotron-labs-3-elastic-30b-a3b":[0.703,0.094,64.82],"qwen3-max":[0.702,0.077,39.99],"qwen3-next-80b-a3b":[0.701,0.086,54.32],"openreasoning-nemotron-14b":[0.701,0.07,62.37],"superapriel-15b-instruct":[0.7,0.079,72.53],"nemotron-cascade-14b-thinking":[0.699,0.058,68.65],"claude-3.7-sonnet-20250219":[0.694,0.081,57.99],"qwen3-swallow-32b-rl-v0.2":[0.693,0.093,77.5],"kimi-k2-instruct":[0.693,0.037,57.48],"ming-flash-omni-2.0":[0.69,0.085,75.22],"qwen3-omni-flash-thinking":[0.689,0.059,79.53],"qwen-drive-1.0-4b":[0.684,0.142,64.5],"nemotron-32b":[0.683,0.064,54.39],"ax-k1":[0.68,0.07,60.71],"gpt-5.4-none":[0.675,0.072,52.14],"marco-deepresearch-8b":[0.672,0.1,49.3],"glm-4.6v":[0.671,0.055,69.42],"ernie-4.5-vl-28b-a3b-thinking":[0.671,0.115,74.77],"o4-mini-2025-04-16":[0.668,0.092,57.07],"glm-4.5-air":[0.664,0.038,60.76],"granite-4.2-8b":[0.66,0.056,53.44],"claude-opus-4":[0.657,0.037,56.86],"gpt-4o-audio":[0.655,0.077,82.32],"mistral-small-4-thinking":[0.654,0.057,58.35],"qwen3-vl-30b-a3b-thinking":[0.654,0.063,71.34],"qwen3-30b-a3b-thinking-2507":[0.652,0.037,62.28],"qwen3-omni-30b-a3b-thinking":[0.648,0.056,79.09],"k2-think":[0.647,0.064,57.4],"claude-sonnet-4":[0.646,0.03,58.01],"minimax-m1-40k":[0.643,0.059,62.51],"gemma-4-12b-it":[0.639,0.038,53.9],"seed-thinking-v1.5":[0.639,0.057,60.35],"qwen3.5-4b":[0.638,0.028,59.95],"o3-mini-high":[0.636,0.05,50.34],"solar-open-100b":[0.636,0.049,55.82],"gemini-2.5-flash-thinking":[0.635,0.044,68.71],"gpt-oss-120b-medium":[0.635,0.046,68.61],"seed-1.5-vl":[0.634,0.069,68.38],"sarvam-30b":[0.634,0.061,71.65],"deepseek-v3.1":[0.633,0.047,64.21],"qwen3-vl-32b-instruct":[0.633,0.047,69.19],"qwen3-235b-a22b":[0.631,0.03,60.8],"mercury-2":[0.63,0.08,52.56],"rynnbrain-30b-a3b":[0.629,0.181,73],"eleven-realtime-v1-mini":[0.628,0.127,73.32],"joyai-llm-flash":[0.628,0.063,72.13],"zaya1-8b":[0.628,0.085,64.88],"mirothinker-v1.0-8b":[0.627,0.09,46.18],"zwz-4b":[0.626,0.17,66.29],"gpt-oss-swallow-20b-rl-v0.1":[0.624,0.093,76.53],"apriel-1.6-15b-thinker":[0.624,0.06,59.51],"o1":[0.623,0.052,63.26],"nemotron-cascade-8b":[0.623,0.058,66.68],"ling-1t":[0.619,0.057,55.44],"qwen-audio-3.0-realtime-flash":[0.615,0.113,74.82],"kimi-k2":[0.614,0.047,47.44],"o3-mini":[0.613,0.05,60.75],"o1-preview-2024-09-12":[0.612,0.072,78.48],"ui-venus-72b":[0.609,0.112,72.89],"nemotron-cascade-8b-thinking":[0.606,0.059,66.4],"clef-omni":[0.605,0.077,66.72],"ministral-3-14b-reasoning":[0.605,0.059,68.36],"gpt-realtime-2.0-medium":[0.602,0.106,73.29],"grok-voice-fast-1.0":[0.601,0.112,62.17],"golongrl-4b":[0.6,0.086,68.12],"mellum2.1-12b-a2.5b-thinking":[0.6,0.086,68.97],"o1-2024-12-17":[0.595,0.054,65.65],"qwen3-vl-8b-thinking":[0.594,0.05,73.55],"motif-2-12.7b-reasoning":[0.594,0.058,80.97],"grok-4-fast-thinking":[0.594,0.077,52.64],"gemini-3.8-live":[0.593,0.112,73.28],"claude-opus-4.1-20250805":[0.592,0.106,57.06],"qwen3-14b-thinking":[0.59,0.057,71.34],"gemini-2.5-flash":[0.587,0.025,60.19],"apriel-1.5-15b-thinker-self-reported":[0.587,0.084,50.01],"gpt-oss-20b-high":[0.584,0.061,62.37],"gpt-oss-swallow-120b-sft-v0.1":[0.584,0.093,78.13],"qwen3-30b-a3b-2507":[0.583,0.063,59.29],"longcat-flash-lite":[0.582,0.062,68.71],"falcon-h1r-7b":[0.579,0.053,57.38],"qwen3.5-omni-flash":[0.578,0.071,66.96],"openpangu-r-7b-2512-slow-thinking":[0.578,0.058,66.15],"gemini-robotics-er-1.5-thinking":[0.575,0.217,62.42],"magistral-medium-1.2":[0.574,0.06,53.25],"claude-3.7-sonnet":[0.574,0.04,63.02],"jev-1.13":[0.573,0.072,69.92],"hypernova-60b-2605":[0.572,0.076,52.46],"qwen3-32b-thinking":[0.57,0.039,64.55],"telechat3-36b-thinking":[0.567,0.069,76.46],"glide-no-thinking":[0.566,0.086,70.75],"k2-high-70b":[0.565,0.073,70.59],"o3-mini-medium":[0.564,0.05,50.89],"deepseek-r1":[0.562,0.034,53.41],"diffusiongemma-26b-a4b":[0.557,0.084,53.9],"gpt-oss-20b":[0.556,0.037,56.18],"jev-1.14":[0.556,0.075,69.13],"qwen3-next-80b-a3b-instruct":[0.556,0.045,65.27],"rynnbrain-8b":[0.554,0.181,72.12],"exaone-4.0-32b-thinking":[0.554,0.065,57.72],"gemini-2.5-flash-preview-09-2025":[0.553,0.063,50.74],"ministral-3-r-8b":[0.552,0.07,68.23],"nemotron-labs-dory1.0-4b-1loop":[0.551,0.099,36.27],"ling-2.6-flash":[0.551,0.074,51.72],"qwen3-32b-thinking-2504":[0.55,0.077,60.5],"toolmind-web-3b":[0.546,0.098,43.2],"olmo-3.1-think-32b":[0.541,0.044,71.73],"k2-think-v2":[0.538,0.075,67.9],"zgcm-1-7b":[0.537,0.061,64.56],"olmo-3-think-32b-dpo":[0.536,0.049,73.42],"gpt-5-nano-high":[0.534,0.062,49.81],"nanbeige4-3b-thinking-2511":[0.529,0.063,52.34],"kimi-k2-0905":[0.528,0.048,47.14],"qwen3-vl-30b-a3b-instruct":[0.524,0.045,64.05],"gpt-oss-20b-medium":[0.524,0.056,70.72],"nvidia-nemotron-3-nano-30b-a3b-bf16":[0.522,0.048,47.76],"agentcpm-explore":[0.522,0.093,48.61],"claude-sonnet-4-20250514":[0.521,0.063,40.17],"longcat-next":[0.52,0.071,65.59],"qwen3-swallow-32b-sft-v0.2":[0.518,0.093,74.68],"apriel-1.5-15b-thinker":[0.517,0.046,52.04],"gemini-3.1-flash-live-high":[0.516,0.092,66.2],"gemini-2.5-flash-preview-05-20":[0.513,0.057,41.36],"minicpm-sala":[0.512,0.066,75.39],"qwen3-235b-a22b-instruct-2507":[0.511,0.047,55.89],"openpangu-r-72b-2512-fast-thinking":[0.504,0.06,66.8],"kanana-2-30b-a3b-thinking-2601":[0.503,0.08,65.93],"llada2.1-flash-q":[0.496,0.055,73.54],"qwen3-omni-flash-instruct":[0.495,0.056,75.74],"openreasoning-nemotron-7b":[0.494,0.046,57.6],"nvidia-nemotron-nano-9b-v2":[0.491,0.047,65.83],"magistral-small-1.2":[0.49,0.072,49.23],"nemotron-3.5-lightning-30b-a3b":[0.488,0.057,56.37],"ui-tars-1.5-7b":[0.485,0.123,73.77],"gpt-4.1-2025-04-14":[0.484,0.11,55.49],"gpt-realtime-2.0":[0.482,0.092,69.28],"infinity-parser2-pro":[0.481,0.176,83.3],"kanana-2-30b-a3b-thinking":[0.481,0.08,64.76],"gpt-oss-swallow-20b-sft-v0.1":[0.48,0.093,74],"gpt-realtime-1.5":[0.479,0.087,69.32],"llada2.0-flash":[0.474,0.046,76.8],"holo1.5-3b":[0.474,0.132,77.95],"qwen3-swallow-32b-cpt-v0.2":[0.469,0.093,75.13],"qwen3-swallow-30b-a3b-rl-v0.2":[0.469,0.093,73.39],"grok-3-mini":[0.468,0.073,52.3],"medmo-8b-next":[0.467,0.15,67.66],"mimo-v2.5-pro-base":[0.466,0.078,80.11],"exaone-4.0-32b":[0.466,0.086,47.34],"qwen3.5-omni-plus-realtime":[0.465,0.154,70.21],"olmo-3-think-32b":[0.461,0.049,69.88],"qwen2.5-vl-72b":[0.459,0.082,70.01],"kolibri-origin":[0.459,0.072,50.07],"gpt-4.1":[0.457,0.032,58.18],"olmo-3-think-32b-sft":[0.456,0.05,71.3],"qwen3-30b-a3b-instruct-2507":[0.453,0.037,68.86],"glm-4.6v-flash":[0.446,0.074,61.42],"pelican-vl-72b":[0.446,0.183,68.39],"motif-2-12.7b-instruct":[0.446,0.058,77.02],"instella-moe-16b-a3b-think":[0.444,0.072,73.22],"o1-preview":[0.443,0.065,75.69],"llada2.1-flash-s":[0.443,0.054,72.34],"telechat3-105b-a4.7b-thinking":[0.442,0.069,73.07],"mistral-large-3":[0.442,0.109,48.55],"deepseek-v3-0324":[0.442,0.041,54.74],"deepseek-r1-0528-qwen3-8b":[0.439,0.053,50.87],"minicpm-o-4.5-thinking":[0.438,0.168,78.77],"rynnbrain-4b":[0.433,0.182,71.69],"vllm-sr-decision-2.0-vega-27b":[0.432,0.074,67.38],"instella-moe-16b-a3b-dpo":[0.43,0.072,72.67],"midm-k-2.5-pro":[0.429,0.114,37.86],"mimo-vl-7b-rl-2508":[0.428,0.127,71.52],"ernie-4.5":[0.427,0.059,75.58],"minicpm4.1-8b":[0.424,0.057,73.64],"grok-3-beta":[0.42,0.063,60.14],"abeja-qwq32b-reasoning-japanese-v1.0":[0.42,0.093,74.34],"granite-4.2-3b":[0.419,0.046,46.66],"ling-flash-2.0":[0.417,0.048,75.81],"r-4b-base":[0.416,0.167,67.5],"ui-venus-7b":[0.415,0.11,68.45],"qwen3-32b":[0.413,0.031,59.51],"llama-nemotron-super-49b-v1.5":[0.409,0.09,45.58],"pplx-decider-flash-v1.2":[0.409,0.08,68.26],"qwq-32b":[0.405,0.05,53.73],"lg-exaone-32b":[0.404,0.076,74.54],"instella-moe-16b-a3b-sft":[0.401,0.072,71.58],"gpt-realtime-2.1":[0.4,0.102,73.45],"glm-4.1v":[0.399,0.08,62.93],"qwen3-4b-2507":[0.394,0.056,44.93],"nemotron-research-goosereason-4b-instruct":[0.388,0.064,71.43],"qwen3-8b-thinking":[0.388,0.045,61.91],"phi-4-reasoning-plus":[0.386,0.048,52.85],"ace-brain-0.5-8b":[0.386,0.176,58.97],"deepseek-r1-distill-qwen-32b":[0.382,0.058,59.46],"vllm-sr-d3-flash":[0.382,0.077,67.47],"qwen3-30b-a3b":[0.38,0.038,65.68],"qwen3-4b-thinking-2507":[0.379,0.047,59.51],"gpt-4.5":[0.375,0.06,61.76],"hyperclovax-seed-think":[0.374,0.087,44.45],"o1-mini":[0.37,0.05,67.61],"mimo-vl-7b-rl":[0.37,0.071,69.4],"apriel-nemotron-15b-thinker":[0.37,0.075,74.05],"qwen3-omni-30b-a3b-instruct":[0.369,0.046,68.38],"deepseek-v3":[0.367,0.036,63.31],"hypernova-60b-2602":[0.366,0.075,46.55],"o1-mini-2024-09-12":[0.366,0.058,69.77],"gpt-realtime":[0.365,0.098,65.43],"llama-3.1-tulu-3-405b":[0.359,0.104,80.01],"nemotron-nano-v2-9b":[0.359,0.071,69.43],"plamo-3.0-prime-thinking":[0.358,0.091,53.57],"llama-4-maverick-17b-128e-instruct":[0.354,0.094,68.35],"qwen3-vl-4b-thinking":[0.351,0.06,60.19],"qwen2.5-vl-72b-instruct":[0.349,0.078,61.64],"mimo-7b-rl":[0.344,0.054,55.4],"qwen3-coder-30b-a3b-instruct":[0.342,0.055,49.03],"olmo-3-think-7b-dpo":[0.341,0.058,63.02],"joyai-vl-interaction":[0.341,0.172,59.34],"zwz-7b":[0.339,0.169,61.13],"autotrust-jev-27b":[0.328,0.074,65.47],"molmopoint-8b":[0.327,0.109,70.66],"llama-3.1-405b":[0.324,0.085,69.71],"autotrust-jev-35b":[0.324,0.079,67.96],"magistral-medium-2506":[0.323,0.061,47.68],"bespoke-nimble-9b-v3":[0.312,0.084,67.65],"olmo-3-think-7b":[0.311,0.041,64.92],"qwen3.8-27b-iq2-xxs":[0.309,0.078,73.43],"qwen3-swallow-30b-a3b-cpt-v0.2":[0.309,0.093,72.31],"robobrain2.5-8b":[0.307,0.175,58.19],"cosmos3-nano":[0.307,0.11,59.65],"kimi-linear-instruct":[0.307,0.054,58.96],"step-3":[0.305,0.09,59.22],"gemini-2.0-pro":[0.302,0.078,67.45],"qwen3-swallow-8b-rl-v0.2":[0.298,0.093,69.6],"magistral-small-2506":[0.293,0.057,44.17],"qwen3-vl-8b-instruct":[0.292,0.036,62.38],"olmo-3-think-7b-sft":[0.291,0.058,61.55],"qwen2.5-omni":[0.29,0.078,72.12],"molmo2-8b":[0.29,0.106,70.23],"medgemma-27b-it":[0.288,0.151,65.3],"qwen2.5-max":[0.288,0.107,76.39],"glm-4.1v-9b":[0.288,0.149,74.63],"llama-3.1-tulu-3-405b-dpo":[0.285,0.111,78.98],"qwen3-swallow-30b-a3b-sft-v0.2":[0.284,0.093,71.2],"k2-medium-70b":[0.279,0.076,67.86],"gpt-4o-2024-11-24":[0.279,0.11,80.53],"qwq-bakeneko-32b":[0.277,0.093,71.27],"deepseek-v4-pro-base":[0.275,0.079,77.75],"gpt-5-minimal":[0.273,0.051,52.88],"tri-21b-think":[0.271,0.085,58.52],"internvl3.5-30b-a3b-flash":[0.27,0.109,65.89],"mimo-vl-7b-sft":[0.267,0.075,70.05],"claude-3.5-sonnet-20241022":[0.265,0.042,60.53],"kimi-k2-base":[0.263,0.056,75.9],"openpangu-r-7b-2512-fast-thinking":[0.263,0.059,57.2],"llama-3.1-nemotron-nano-8b-v1":[0.26,0.072,63.6],"gpt-4.1-mini":[0.258,0.049,44.38],"autotrust-gev-26b-decide":[0.257,0.083,67.38],"manzano-30b":[0.256,0.16,81.56],"webexplorer-8b":[0.254,0.097,34.02],"grok-3":[0.252,0.059,55.08],"gemini-2.0-flash":[0.242,0.072,54.98],"qwen2.5-plus-1127":[0.242,0.074,76.1],"qwen3-14b":[0.233,0.043,57.47],"hunyuan-large-instruct":[0.233,0.081,80.82],"olmo-hybrid-think-7b-sft":[0.233,0.061,61.27],"gemini-2.5-flash-lite":[0.229,0.041,52.25],"nemotron-3-ultra-base":[0.228,0.077,82.94],"kanana-2-30b-a3b-instruct-2601":[0.228,0.093,69.83],"penguin-vl-8b":[0.226,0.114,69.71],"openpangu-vl-7b":[0.22,0.075,73.28],"internvl2.5-78b":[0.215,0.076,69.79],"claude-3.5-sonnet-20240620":[0.21,0.047,71],"plamo-3.0-prime-beta":[0.206,0.091,48.14],"glm-4.1v-9b-thinking":[0.2,0.109,68.27],"gemini-robotics-er-1.5":[0.199,0.217,57.49],"eagle2.5-8b":[0.196,0.118,70.38],"keye-vl-8b":[0.196,0.133,58.12],"gpt-4o-0327":[0.193,0.091,66.08],"youtu-llm-2b":[0.192,0.061,63.76],"medmo-8b":[0.187,0.15,61.81],"olmo-3.1-instruct-32b":[0.186,0.052,69.46],"claude-3.5-sonnet":[0.186,0.056,68.84],"vllm-sr-d3-mini":[0.185,0.077,64.93],"openthinker3-7b":[0.183,0.063,56.68],"nemotron-3-super-120b-a12b-base":[0.181,0.052,73.42],"rnj-1.5":[0.179,0.096,59.36],"spark-x2.5-1.7b":[0.178,0.071,35.99],"ling-3.0-flash-base":[0.178,0.076,66.96],"qwen3-swallow-8b-sft-v0.2":[0.177,0.093,66.56],"mistral-medium-3.1":[0.176,0.08,46.96],"deepseek-v4.1-flash-base":[0.175,0.086,72.05],"deepseek-v4-flash-base":[0.175,0.07,71.57],"pixtral-large-2411":[0.174,0.191,67.7],"seed1.6":[0.174,0.098,67.91],"gpt-realtime-2.1-mini-high":[0.171,0.107,66.21],"nemotron-h-47b-reasoning":[0.169,0.059,39.4],"kat-dev-32b":[0.168,0.067,50.39],"llama-4-scout-17b-16e":[0.167,0.104,61.05],"mistral-small-4":[0.166,0.067,41.05],"qwen3-vl-4b-instruct":[0.165,0.044,62.64],"ling-2.6-1t-base":[0.165,0.068,66.04],"gpt-4o-0513":[0.161,0.179,78.53],"llama-3.1-tulu-3-405b-sft":[0.16,0.111,76.32],"ling-mini-2.0":[0.16,0.049,61.8],"mimo-embodied-7b":[0.159,0.106,58.5],"qwen3-4b-instruct-2507":[0.157,0.044,59.86],"marco-mini-instruct":[0.147,0.091,73.85],"molmo-72b":[0.144,0.125,75.09],"internvl2-pro":[0.14,0.145,77.33],"mistral-medium-3":[0.139,0.06,63.71],"molmo2-4b":[0.139,0.102,66.4],"gpt-4o-2024-08-06":[0.137,0.045,61.36],"deepseek-v3.2-base":[0.134,0.081,75.53],"gpt-4o":[0.134,0.03,56.21],"hunyuan-4b-instruct":[0.13,0.071,48.08],"medmo-4b-next":[0.129,0.15,62.92],"qwq-32b-preview":[0.128,0.074,55.45],"gpt-5-nano":[0.127,0.051,49.86],"gpt-4o-2024-11-20":[0.126,0.057,45.65],"qwen3-8b":[0.126,0.032,52.03],"gemini-3.1-flash-live":[0.124,0.089,60.26],"kanana-2-30b-a3b-instruct":[0.123,0.093,67.5],"mistral-large-instruct-2407":[0.123,0.062,68.49],"gpt-oss-120b-low":[0.123,0.092,43.5],"hy3-preview-base":[0.123,0.058,68.06],"mimo-v2-flash-base":[0.116,0.062,70.18],"llama-4-maverick":[0.116,0.049,41.62],"minicpm-v-4.5-8b":[0.114,0.091,66.5],"qwen2.5-vl-32b-instruct":[0.113,0.125,60.82],"molmo2-o-7b":[0.112,0.122,68.64],"minicpm-o-4.5":[0.111,0.077,69.37],"gpt-5-mini-minimal":[0.11,0.064,56.58],"qwen2-vl-72b":[0.109,0.084,69.14],"qwen2-vl-72b-instruct":[0.105,0.111,70.19],"medix-r1-8b":[0.102,0.151,59.82],"internvl3.5-gpt-oss-20b-a4b":[0.099,0.166,77.24],"granite-4.1-30b":[0.097,0.067,70.57],"gpt-4o-realtime-preview-2024-12-17":[0.096,0.105,63.92],"gpt-4o-2024-05-13":[0.095,0.038,63.89],"ministral-3-14b-instruct":[0.095,0.083,61.86],"molmopoint-o-7b":[0.091,0.169,74.03],"internvl2.5-38b":[0.089,0.076,67.45],"llama-3.1-tulu-3-70b-dpo":[0.089,0.094,74.75],"llama-3.1-tulu-3-70b":[0.089,0.094,74.85],"hermes-3-llama-3.1-405b":[0.083,0.1,75.2],"nemotron-3.5-super-vl-120b-a12b-base":[0.082,0.074,76.71],"robobrain-2.5-4b":[0.078,0.258,57.12],"stable-diffcoder-8b-instruct":[0.075,0.111,59.99],"rnj-1":[0.075,0.097,53.18],"lfm2.5-2.6b":[0.073,0.051,41.18],"mellum2-12b-a2.5b-thinking":[0.073,0.108,59.02],"keye-vl-1.5-8b":[0.072,0.112,68.1],"hunyuan-large":[0.071,0.079,83.15],"trinity-mini":[0.07,0.088,57.28],"gpt-4-1106-preview":[0.07,0.059,69.31],"qwen2.5-72b-instruct":[0.069,0.037,64],"nemotron-3-nano-4b-thinking":[0.069,0.071,42.73],"nemotron-3-nano-4b":[0.067,0.052,38.76],"llada2.1-mini-q":[0.064,0.056,63.35],"youtu-vl-4b-instruct":[0.063,0.082,68.81],"kimi-dev-72b":[0.062,0.066,50.91],"qwen3-4b":[0.058,0.048,62.04],"qwen2.5-math-72b-instruct":[0.058,0.068,67.14],"qwen3-235b-a22b-base":[0.058,0.096,73.52],"holo1-7b":[0.057,0.128,67.88],"olmo-3.1-instruct-32b-dpo":[0.054,0.061,58.84],"qwen2.5-turbo":[0.053,0.068,77.16],"gemini-2.0-flash-001":[0.051,0.096,56.12],"qwen-3-235b-a22b-nonthinking":[0.049,0.086,63.6],"amazon-nova-premier":[0.049,0.084,44.35],"gpt-oss-20b-moe":[0.044,0.11,47.7],"gemini-1.5-pro-002":[0.043,0.069,58.37],"dots.mocr":[0.043,0.165,75.54],"pelican-vl-7b":[0.041,0.183,63.42],"gpt-4-turbo-2024-04-09":[0.039,0.048,65.74],"openpangu-r-7b-diffusion":[0.035,0.097,78.77],"kat-dev-72b-exp":[0.035,0.067,48.14],"cosmos-reason2-8b":[0.029,0.112,60.5],"alodlm-8b":[0.029,0.082,80.32],"deepseek-v3.2-exp-base":[0.028,0.071,73.68],"diffusiongemma-jev":[0.026,0.079,63.85],"gemma-4-e4b-it":[0.025,0.032,48.34],"exaone-4.0-1.2b":[0.021,0.073,50.37],"qwen2.5-32b-instruct":[0.021,0.041,66.45],"gpt-4-turbo":[0.019,0.076,57.24],"telechat2-115b":[0.018,0.116,84.35],"yi-lightning":[0.014,0.088,65.61],"deepseek-v3-base":[0.014,0.061,74.13],"glm-4.5-base":[0.013,0.061,71.36],"ling-1t-base":[0.013,0.065,62.2],"llama-3.1-405b-instruct":[0.009,0.048,62.99],"qwen-turbo-0919":[0.005,0.074,69.33],"kolibri-1-base":[0.005,0.106,81.15],"kimi-vl-a3b-thinking-2506":[0.004,0.081,54.37],"gpt-4o-mini":[0.004,0.048,64.24],"motif-3-base":[0.003,0.097,82.66],"mage-vl":[0.003,0.123,61.74],"exaone-deep-2.4b":[-0.001,0.076,47.29],"llama-3.3-70b-instruct":[-0.001,0.066,63.17],"llada2.1-mini-s":[-0.002,0.055,61.69],"ling-2.5-flash-base":[-0.004,0.076,62.03],"gemma-3-27b":[-0.005,0.065,71.44],"rynnbrain-2b":[-0.005,0.181,66.13],"k2-v2":[-0.009,0.081,66.2],"gpt-4-0613":[-0.013,0.12,68.55],"openreasoning-nemotron-1.5b":[-0.013,0.067,39.81],"mimo-v2.5-base":[-0.017,0.061,66.72],"gpt-realtime-2.1-mini":[-0.019,0.104,63.78],"llama-3.1-405b-instruct-fp8":[-0.019,0.077,70.03],"claude-3.5-haiku-20241022":[-0.02,0.067,42.56],"deepseek-v2.5":[-0.021,0.043,61.61],"videochat-flash-7b":[-0.022,0.183,61.92],"qwen2.5-14b-instruct":[-0.024,0.058,69.34],"llada2.0-mini":[-0.026,0.052,58.77],"minicpm-v-4.6-thinking":[-0.027,0.117,61.95],"plm-8b":[-0.027,0.122,65.24],"lfm2.5-8b-a1b":[-0.03,0.052,37.14],"granite-4.1-8b":[-0.031,0.068,67.21],"gemini-1.5-pro":[-0.035,0.041,61.6],"gpt-5.4-mini-none":[-0.035,0.09,41.6],"qwen3-swallow-8b-cpt-v0.2":[-0.039,0.093,62.92],"gpt-realtime-mini":[-0.04,0.106,63.91],"step-3.5-flash-base":[-0.04,0.058,64.96],"deepseek-coder-v2-instruct":[-0.04,0.045,60.3],"nemotron-3-nano-30b-a3b-base":[-0.045,0.07,78.57],"deepseek-v2-chat-0628":[-0.047,0.066,65.03],"step-3.5-flash-base-midtrain":[-0.05,0.078,69.14],"mistral-3.2-24b":[-0.051,0.087,77.83],"qwen2-math-72b-instruct":[-0.052,0.072,63.27],"joyai-llm-flash-base":[-0.055,0.087,76.27],"mistral-small-3.2-24b-instruct":[-0.056,0.079,64.61],"minicpm-v-4.7-1b":[-0.057,0.125,60.89],"qwen3.5-35b-a3b-base":[-0.057,0.078,70.29],"lingshu-7b":[-0.059,0.15,58.03],"qwen2.5-coder-32b-instruct":[-0.059,0.046,56.52],"deepseek-v3.1-base":[-0.059,0.078,69.86],"mistral-small-3.1-24b-instruct":[-0.062,0.081,62],"deepseek-coder-v2-instruct-0724":[-0.063,0.07,56.91],"gpt-4o-mini-2024-07-18":[-0.065,0.052,56.92],"claude-3-opus-20240229":[-0.066,0.055,58.05],"ling-2.6-flash-base":[-0.067,0.066,59.64],"telechat2-35b":[-0.074,0.115,83.05],"k2-horizon-0.9b":[-0.075,0.085,44.58],"llama-3.1-tulu-3-70b-sft":[-0.076,0.1,70.59],"qwen3-8b-non-thinking":[-0.076,0.047,60],"seed1.5":[-0.077,0.103,70.35],"deepseek-vl2":[-0.077,0.149,78.64],"vllm-sr-decision-2.0-lux-9b":[-0.077,0.073,59.34],"internvl3.5-8b":[-0.078,0.061,60.81],"qwen3-32b-nothinking":[-0.078,0.05,51.07],"manzano-3b":[-0.083,0.16,78.02],"mistral-large-2411":[-0.084,0.101,47.72],"glm-4v-plus":[-0.087,0.164,74.69],"llama-3.1-70b-instruct":[-0.089,0.043,65.53],"k2-low-70b":[-0.091,0.074,56.23],"fanar-2-27b-instruct":[-0.092,0.102,48.28],"gpt-4":[-0.102,0.058,72.7],"qwen2.5-math-7b-instruct":[-0.103,0.072,61.4],"nemotron-3.5-lightning-30b-a3b-base":[-0.107,0.09,74.51],"gemma-3-27b-it":[-0.108,0.037,58.12],"fastvlm-7b":[-0.109,0.181,77.37],"llama-4-scout-17b":[-0.11,0.057,62.6],"mellum2-12b-a2.5b-instruct":[-0.111,0.108,64.72],"kimi-vl-a3b-thinking":[-0.113,0.14,69.26],"qwen3-8b-instruct":[-0.122,0.082,77.22],"kanana-1.5-32.5b-instruct":[-0.122,0.093,61.68],"medmo-4b":[-0.129,0.154,52.66],"llama-3.1-70b":[-0.13,0.08,66.34],"bagel-7b-mot":[-0.133,0.121,66.62],"llada2.2-mini":[-0.134,0.095,48.52],"holo1-3b":[-0.136,0.133,64.86],"qwen2-72b-instruct":[-0.138,0.046,64.96],"internvl2-llama-3-76b":[-0.138,0.074,67.14],"mistral-large-3-base":[-0.142,0.07,68.87],"glm-4-0520":[-0.144,0.097,72.11],"qwen-2.5-72b":[-0.147,0.05,69.53],"hermes-3-llama-3.1-70b":[-0.148,0.098,70.05],"medgemma-1.5-4b-it":[-0.153,0.151,57.12],"llama-3.3-70b":[-0.154,0.059,63.46],"autotrust-jev-9b":[-0.155,0.076,58.59],"kimi-vl-a3b-instruct":[-0.156,0.14,68.07],"minicpm-v-4.6":[-0.158,0.1,60.18],"llada2.0-flash-preview":[-0.158,0.059,65.24],"llada2.1-mini":[-0.159,0.099,45.03],"nvlm-d-72b":[-0.162,0.147,72.48],"gemini-1.5-flash":[-0.162,0.058,62.78],"llava-onevision-2-8b":[-0.166,0.143,51.1],"fleming-vl-8b":[-0.172,0.154,57.18],"wedlm-8b-instruct":[-0.174,0.076,75.02],"qwen2.5-vl-7b":[-0.176,0.056,55.04],"zaya1-vl-8b":[-0.177,0.166,73.59],"skywork-o1-open-llama-3.1-8b":[-0.179,0.069,61.12],"moss-vl-realtime":[-0.18,0.177,51.68],"deepseek-r1-distill-qwen-7b":[-0.182,0.064,46.47],"deepseek-vl2-small":[-0.184,0.149,77.32],"sdar-8b-chat":[-0.186,0.097,73.99],"internvl3.5-4b":[-0.193,0.071,61.3],"ling-flash-base-2.0":[-0.194,0.051,62.52],"qwen2.5-coder-14b-instruct":[-0.195,0.049,50.15],"llama-3.1-nemotron-70b":[-0.2,0.1,71.46],"mellum2-12b-a2.5b-thinking-sft":[-0.201,0.137,65],"plm-3b":[-0.202,0.121,63.63],"midm-2.0-base-instruct":[-0.206,0.126,67.9],"internvl-8b":[-0.209,0.081,65.5],"minicpm5-1b":[-0.21,0.063,44.51],"llama-4-maverick-base":[-0.214,0.086,67.83],"nemotron-labs-twotower-30b-a3b-base":[-0.215,0.087,79.25],"granite-4.0-h-small":[-0.219,0.057,62.68],"higgs-realtime":[-0.221,0.111,61.95],"qwen3-30b-a3b-base":[-0.224,0.063,66.63],"internvl2.5-26b":[-0.224,0.057,67.71],"gemma-3-12b-it":[-0.228,0.045,56.98],"bagel-14b":[-0.229,0.18,74.98],"medgemma-4b-it":[-0.231,0.151,56.65],"lfm2.5-vl-3b":[-0.232,0.105,65.08],"bespoke-nimble-9b-v2":[-0.233,0.084,57.27],"llava-onevision-72b":[-0.235,0.09,65.79],"olmo-3-instruct-7b":[-0.237,0.049,56.54],"yi-coder-9b-chat":[-0.238,0.077,50.75],"gpt-4.1-nano":[-0.239,0.064,40.73],"qwen2-math-7b-instruct":[-0.24,0.069,57.54],"smollm3-3b":[-0.241,0.042,51.36],"d1-3b":[-0.247,0.077,62.77],"gemini-1.0-ultra":[-0.249,0.12,74.87],"penguin-vl-2b":[-0.25,0.115,62.15],"robobrain-2.0":[-0.25,0.183,62.84],"gemini-1.5-flash-002":[-0.255,0.069,55.54],"magicoder-s-ds-6.7b":[-0.257,0.094,57.97],"deepseek-v2-chat-sft":[-0.261,0.068,70.9],"falcon-h1-34b-instruct":[-0.262,0.052,54.78],"qwen2-vl-7b-instruct":[-0.262,0.119,66.1],"claude-3-sonnet-20240229":[-0.264,0.074,63.86],"trinity-large-base":[-0.265,0.104,74.83],"kimi-audio-7b-instruct":[-0.267,0.116,62.11],"ministral-3-8b-instruct":[-0.268,0.089,62.94],"glm-4-air-0605":[-0.268,0.097,69.13],"minicpm4-8b":[-0.269,0.108,81.31],"infinity-parser2-flash":[-0.27,0.176,74.95],"qwen3-vl-2b-thinking":[-0.273,0.093,50.76],"internvl2-40b":[-0.273,0.077,63.12],"codestral-22b-v0.1":[-0.274,0.081,56.23],"deepslate-opal":[-0.276,0.138,60.07],"gemma-4-e2b-it":[-0.276,0.036,44.43],"qwen2.5-32b-base":[-0.278,0.073,72.67],"llama-3.2v-90b-instruct":[-0.279,0.133,70.28],"llava-video-7b":[-0.282,0.183,57.66],"llama-3-70b":[-0.283,0.075,64.37],"gpt-4-0314":[-0.284,0.074,66.59],"qwen2.5-math-1.5b-instruct":[-0.285,0.071,55.85],"olmo-3-instruct-7b-dpo":[-0.285,0.061,46.32],"ling-3.0-tiny-base":[-0.285,0.074,55.48],"lfm2.5-1.2b-jp-202606":[-0.285,0.118,51.11],"llada2.0-mini-preview":[-0.286,0.097,71],"yi-large-preview":[-0.287,0.081,64.38],"claude-3-opus":[-0.288,0.059,64.67],"seed-coder-8b-instruct":[-0.289,0.058,45.81],"opencoder-8b-instruct":[-0.29,0.084,48.23],"hy-1.8b":[-0.295,0.116,67.15],"ouro-2.6b":[-0.299,0.093,75.13],"phi-3.5-moe-instruct":[-0.299,0.104,71.95],"apertus-v1.5-70b-thinking":[-0.3,0.071,51.06],"qwen2-72b":[-0.301,0.068,70.28],"vllm-sr-decision-2.0-nox-4b":[-0.304,0.077,57.25],"internvl3-8b":[-0.306,0.127,51.22],"qwen2.5-coder-32b":[-0.308,0.075,65.86],"olmo-3.1-instruct-32b-sft":[-0.309,0.061,47.71],"mellum2-12b-a2.5b-instruct-sft":[-0.314,0.108,58.76],"motif-2-12.7b-base":[-0.314,0.074,68.54],"kev-9b":[-0.316,0.077,56.03],"apertus-v1.5-8b-thinking":[-0.318,0.071,51.5],"llama-3.1-405b-base":[-0.326,0.065,73.67],"deepseek-coder-33b-instruct":[-0.332,0.063,44.12],"deepseek-v2-chat":[-0.333,0.049,59.1],"glm-4.5-air-base":[-0.339,0.068,65.54],"internlm2_5-20b-chat":[-0.343,0.079,70.52],"ling-2.5-mini-base":[-0.344,0.074,53.5],"cosmos-reason1-7b":[-0.344,0.145,43.38],"llama-3-70b-instruct":[-0.344,0.045,57.48],"codegeex4-all-9b":[-0.345,0.106,47.85],"qwen3.5-2b":[-0.347,0.033,49.31],"qwen2.5-vl-3b":[-0.347,0.086,64.47],"jina-vlm-2.4b-20251117":[-0.348,0.166,72.23],"qwen2.5-7b-instruct":[-0.348,0.041,55.53],"kimi-linear-base":[-0.35,0.08,61.45],"molmo-7b-d":[-0.356,0.124,69.58],"kanana-2-30b-a3b-mid-2601":[-0.357,0.086,72.08],"kanana-2-30b-a3b-base":[-0.357,0.086,72.06],"qwen2-vl-7b":[-0.358,0.082,63.76],"deepseek-r1-distill-llama-8b":[-0.36,0.064,51.41],"numinamath-72b-cot":[-0.361,0.074,52.08],"mixtral-8x22b-instruct-v0.1":[-0.365,0.055,65.76],"llada2.0-uni":[-0.372,0.119,64.77],"llama-3.1-tulu-3-8b":[-0.374,0.091,62.93],"claude-3-sonnet":[-0.379,0.096,64.54],"gpt-5-nano-minimal":[-0.38,0.061,41.31],"codestral-22b":[-0.385,0.078,45.99],"internvl2.5-8b":[-0.387,0.056,65.89],"qwen2.5-14b":[-0.389,0.076,66.03],"granite-4.1-3b":[-0.391,0.067,58.79],"telechat2-7b":[-0.392,0.116,75.25],"gemma-2-27b-it":[-0.396,0.049,53.62],"xverse-moe-a36b":[-0.398,0.105,74.4],"qwen3-vl-2b-instruct":[-0.405,0.055,55.33],"lfm2-24b-a2b":[-0.406,0.094,61.01],"amazon-nova-pro-v1.0":[-0.407,0.104,42],"hy-1.8b-2bit":[-0.408,0.117,63.18],"olmo-hybrid-instruct-7b-dpo":[-0.411,0.061,43.72],"qwen2.5-coder-14b":[-0.411,0.075,63.2],"gpt-4v":[-0.415,0.071,62.53],"marco-nano-instruct":[-0.416,0.093,60.65],"qwen3-8b-base":[-0.418,0.058,63.59],"robobrain-2.0-7b":[-0.419,0.182,56.15],"hy-1.8b-int4gptq":[-0.42,0.113,63.31],"intern-decision-4b":[-0.423,0.077,55.56],"lfm2.5-1.2b-thinking":[-0.426,0.063,40.2],"qwen3.5-9b-base":[-0.426,0.076,55.58],"tev1-4b-experimental":[-0.426,0.083,55.61],"kanana-1.5-32.5b-base":[-0.428,0.086,70.27],"llama-3.1-tulu-3-8b-dpo":[-0.429,0.092,62.35],"deepseek-coder-v2-base":[-0.43,0.084,60.57],"qwen3-1.7b":[-0.431,0.04,48.24],"llm-jp-4-vl-9b":[-0.431,0.103,58.33],"falcon-h1-7b":[-0.431,0.051,49.82],"plamo-3.0-prime":[-0.432,0.09,32.76],"qwen2-math-1.5b-instruct":[-0.434,0.074,50.56],"vllm-sr-d3-nano":[-0.435,0.078,55.77],"gemma-3-27b-vl":[-0.435,0.083,46],"qwen2-57b-a14b-instruct":[-0.435,0.067,59.5],"solar-pro-preview":[-0.437,0.109,68.2],"claude-3-haiku-20240307":[-0.442,0.066,50.62],"qwen3-1.7b-thinking":[-0.442,0.066,45.23],"internlm2.5-7b-chat":[-0.443,0.077,63.41],"kanana-1.5-o-9.8b-instruct-2602":[-0.446,0.092,55.78],"qwen1.5-110b-chat":[-0.446,0.067,56.32],"qwen2.5-coder-7b-instruct":[-0.449,0.046,42.82],"qwen1.5-72b-chat":[-0.451,0.052,62.26],"phi-4-reasoning-vision-15b":[-0.451,0.131,61.81],"gemini-2.5-flash-native-audio-preview-12-2025":[-0.451,0.144,32.3],"mm1.5-30b":[-0.452,0.165,73.04],"mobilellm-r1-950m":[-0.454,0.068,41.92],"kanana-2-30b-a3b-base-2601":[-0.464,0.086,70.19],"deepseek-math-7b-rl":[-0.466,0.084,51.86],"qwen2.5-7b":[-0.467,0.046,58.81],"internlm2-math-plus-20b":[-0.468,0.082,50.16],"apertus-v1.5-70b":[-0.469,0.074,64.53],"gpt-3.5-turbo-1106":[-0.471,0.104,60.67],"deepseek-v2":[-0.476,0.061,68.95],"qwen3.5-4b-base":[-0.477,0.063,64.21],"olmo-3-32b":[-0.479,0.101,68.7],"lfm2-8b-a1b":[-0.481,0.054,46.28],"qwen1.5-110b":[-0.483,0.079,65.54],"yi-1.5-34b-chat":[-0.488,0.067,53.57],"bitcpm-cann-8b":[-0.488,0.108,77.84],"hrm-text-1b":[-0.491,0.111,73.44],"falcon-h1-1.5b-deep":[-0.491,0.056,51.58],"granite-4.0-h-micro":[-0.491,0.07,57.28],"glm-4-9b-chat":[-0.497,0.07,62.96],"glm4-9b":[-0.501,0.077,67.53],"internvl2.5-4b":[-0.501,0.079,60.04],"pixtral-12b":[-0.502,0.129,64.15],"granite-3.3-8b-instruct":[-0.506,0.054,52.03],"mistral-large-2402":[-0.509,0.119,56.76],"gpt-4-1106-vision-preview":[-0.518,0.131,67.11],"llama-3.1-70b-base":[-0.518,0.088,76.49],"amazon-nova-lite-v1.0":[-0.52,0.095,37.13],"internlm-xcomposer2.5":[-0.52,0.125,66.37],"falcon-h1-3b":[-0.521,0.051,46.11],"gemma-2-9b-it":[-0.523,0.047,51.48],"qwen2.5-omni-7b":[-0.529,0.064,56.29],"minicpm3-4b":[-0.534,0.067,56.45],"llava-onevision-7b":[-0.535,0.105,57.99],"internlm2-math-plus-7b":[-0.539,0.082,47.74],"internvl3.5-2b":[-0.542,0.091,58.59],"kanana-2-3b-instruct":[-0.544,0.106,50.31],"qwen-2.5-3b-instruct":[-0.547,0.069,46.1],"phind-codellama-34b-v2":[-0.549,0.103,46.99],"granite-3.2-8b-instruct":[-0.55,0.085,60.77],"minicpm-v-2_6":[-0.552,0.088,60.38],"qwen2.5-coder-7b":[-0.553,0.073,58.43],"lfm2.5-1.2b-instruct":[-0.553,0.071,47.07],"codellama-70b-instruct":[-0.553,0.102,48.86],"llama-3-70b-base":[-0.554,0.059,67.81],"gemma-3-4b-it":[-0.556,0.044,49.47],"olmo-hybrid-instruct-7b-sft":[-0.557,0.061,37.99],"llada-o":[-0.558,0.121,60.76],"gemma-3-12b":[-0.559,0.074,61.4],"exaone-3.5-7.8b-instruct":[-0.561,0.13,61.72],"mixtral-8x22b":[-0.564,0.057,64.7],"olmo-2-32b-base":[-0.566,0.078,69.97],"granite-4.0-micro":[-0.567,0.064,52.31],"mathstral-7b":[-0.569,0.067,44.18],"ministral-3-3b-base":[-0.57,0.124,58.02],"molmo-7b-o":[-0.572,0.13,67.92],"falcon3-10b":[-0.574,0.058,50.97],"lfm2-2.6b":[-0.576,0.066,49.33],"phi-3-medium-4k-instruct":[-0.576,0.094,63.09],"deepseek-coder-v2-lite-instruct":[-0.577,0.041,43.66],"qwen2-7b-instruct":[-0.577,0.045,49.54],"numinamath-7b-cot":[-0.582,0.084,49.12],"gemma-2-27b":[-0.585,0.067,54.77],"granite-4.0-h-tiny":[-0.587,0.045,45.62],"yi-1.5-34b":[-0.588,0.071,60.56],"internvl2-26b":[-0.589,0.055,61],"internvl3-2b":[-0.597,0.113,62.97],"codeqwen1.5-7b-chat":[-0.597,0.086,44.11],"qwen2.5-coder-3b-instruct":[-0.599,0.058,45.93],"ministral-8b-instruct":[-0.599,0.1,58.54],"starcoder2-15b-instruct-v0.1":[-0.602,0.1,49.51],"qwen1.5-72b":[-0.603,0.062,64.07],"internvl2-8b":[-0.604,0.056,61.33],"lfm2.5-350m":[-0.605,0.118,35.1],"deepseek-coder-6.7b-instruct":[-0.605,0.062,44.34],"deepseek-llm-67b-chat":[-0.606,0.061,65.11],"alodlm-1.7b":[-0.607,0.083,65.45],"openpangu-7b-diffusion-base":[-0.608,0.096,65.26],"lfm2-vl-3b":[-0.611,0.111,58.84],"ouro-1.4b":[-0.612,0.084,65.94],"glm-4-9b-chat-1m":[-0.613,0.073,65.22],"qwen2.57b-a14b":[-0.615,0.07,59.67],"yi-1.5-9b-chat":[-0.619,0.068,51.05],"fanar-1-9b-instruct":[-0.619,0.086,42.23],"yi-34b-chat":[-0.62,0.11,66.56],"claude-3-haiku":[-0.622,0.088,58.92],"deepseek-r1-distill-qwen-1.5b":[-0.622,0.067,41.05],"llama-3.2v-11b-instruct":[-0.626,0.139,66.03],"command-r-plus":[-0.627,0.066,52.07],"qwen1.5-32b-chat":[-0.633,0.062,55.41],"phi-3-mini-4k-instruct":[-0.634,0.073,57.01],"instella-moe-16b-a3b-base":[-0.638,0.092,77.33],"falcon-h1-1.5b":[-0.638,0.058,45.47],"olmo-3-7b-sft":[-0.639,0.059,34.91],"gpt-3.5-turbo-0125":[-0.64,0.064,50.66],"apertus-v1.5-8b":[-0.646,0.074,58.89],"falcon3-7b":[-0.647,0.057,48.68],"trinity-large-truebase":[-0.647,0.095,66.92],"qwen-vl-max":[-0.649,0.115,63.99],"internlm-xcomposer2-4khd-7b":[-0.649,0.126,65.78],"nemotron-nano-12b-v2-base":[-0.65,0.09,70.78],"mistral-nemo-instruct-2407":[-0.654,0.074,45.53],"phi-3.5-mini-instruct":[-0.661,0.057,49.18],"eurollm-22b":[-0.662,0.07,59.51],"moonlight-base":[-0.664,0.066,56.59],"cogvlm2-llama3-chat-19b":[-0.665,0.145,69.19],"llama-3.1-tulu-3-8b-sft":[-0.671,0.1,57.43],"llama-3.1-8b-instruct":[-0.672,0.035,44.15],"kanana-2-1.3b-instruct":[-0.676,0.107,47.73],"fast-dllm-v2-7b":[-0.684,0.094,57.93],"glm-4v-9b":[-0.685,0.132,65.66],"gpt-3.5-turbo":[-0.688,0.07,55.38],"deepseek-coder-7b-instruct-v1.5":[-0.688,0.089,62.4],"qwen2-7b":[-0.691,0.063,57.13],"granite-3.1-8b-instruct":[-0.696,0.078,55.24],"mimo-7b-base":[-0.698,0.086,62.62],"cambrian-34b":[-0.699,0.108,64.58],"step-audio-2-mini":[-0.701,0.089,51.55],"exaone-3.5-2.4b-instruct":[-0.703,0.128,55.78],"granite-4.0-tiny-preview":[-0.705,0.093,57.1],"gemini-1.0-pro":[-0.706,0.086,62.95],"llama-3.1-8b":[-0.706,0.066,53.79],"baichuan-omni":[-0.707,0.134,63.84],"olmo-2-0325-32b-instruct":[-0.71,0.063,39.17],"step-1v-32k":[-0.712,0.17,64.82],"llm-jp-4-vl-9b-beta":[-0.713,0.1,54.99],"qwen1.5-32b":[-0.714,0.071,59.75],"internvl-chat-v1.5":[-0.719,0.083,55.94],"aquila-vl-2b":[-0.719,0.116,63.06],"internlm2-chat-20b":[-0.72,0.068,58.56],"gpt-3.5":[-0.729,0.087,67.07],"minicpm-llama3-v2.5":[-0.731,0.125,64.96],"gemini-pro":[-0.733,0.091,66.57],"llama3.0-70b":[-0.741,0.086,60.35],"qwen2.5-coder-1.5b-instruct":[-0.746,0.1,42.57],"trinity-mini-base":[-0.746,0.099,65.98],"vllm-sr-d3-lite":[-0.748,0.078,51.33],"qwen2.5-3b":[-0.75,0.05,49.47],"dream-7b-base":[-0.752,0.084,58.39],"moonlight-instruct":[-0.753,0.065,43.27],"plamo-2.2-prime":[-0.756,0.1,29.53],"bitcpm-cann-3b":[-0.761,0.108,72.32],"deepseek-vl2-tiny":[-0.763,0.148,69.19],"granite-3.3-2b-instruct":[-0.773,0.071,53.68],"command-r":[-0.776,0.089,39.13],"olmo-hybrid-7b":[-0.777,0.086,60.91],"minicpm-o-2.6":[-0.78,0.072,49.8],"gemma-3-pt-27b":[-0.782,0.083,66.32],"ministral-3-3b-instruct":[-0.787,0.076,55.2],"deepseek-llm-67b-base":[-0.789,0.07,66.5],"qwen3-4b-base":[-0.79,0.115,61.52],"dream-7b-instruct":[-0.793,0.069,56.34],"deepseek-math-7b":[-0.794,0.073,53.24],"llada-v":[-0.796,0.12,57.32],"qwen3.5-2b-base":[-0.8,0.094,72.89],"chatglm3-6b-base":[-0.801,0.072,61.14],"cambrian-1-34b":[-0.803,0.138,67.18],"olmo-3-7b":[-0.804,0.061,62.42],"qwen3-0.6b":[-0.807,0.049,28.7],"internlm2-20b":[-0.81,0.073,57.6],"gemma-2-9b":[-0.811,0.055,51.92],"yi-1.5-9b":[-0.811,0.088,53.73],"xverse-65b":[-0.817,0.121,68.56],"xverse-65b-2":[-0.82,0.099,65.67],"qwen2-vl-2b-instruct":[-0.82,0.117,60.35],"apertus-70b":[-0.822,0.081,61.49],"yi-1.5-6b-chat":[-0.825,0.082,43.96],"mm1.5-7b":[-0.826,0.184,65.59],"internlm2-chat-20b-sft":[-0.829,0.069,56.5],"phi-3-vision-4b":[-0.831,0.13,64.5],"llama-3-8b-instruct":[-0.831,0.05,51.2],"qwen2-vl-2b":[-0.837,0.093,54.74],"qwen2.5-coder-3b":[-0.841,0.075,50.84],"fastvlm-1.5b":[-0.842,0.157,64.45],"hyperclovax-seed-omni-8b":[-0.842,0.072,50.7],"magpie-8b":[-0.845,0.115,48.95],"north-micro-vision-instruct":[-0.854,0.124,61.66],"molmoe-1b":[-0.863,0.138,64.63],"dbrx-instruct-preview":[-0.864,0.104,60.52],"mini-gemini-hd-34b":[-0.867,0.155,59.42],"kanana-2-3b-base":[-0.876,0.093,51.04],"qwen-14b":[-0.881,0.065,67.78],"qwen1.5-14b-chat":[-0.881,0.125,62.57],"llava-next-34b":[-0.884,0.111,61.8],"internvl-u":[-0.887,0.12,56.78],"deepseek-coder-v2-lite-base":[-0.892,0.072,50.83],"internvl2-4b":[-0.894,0.079,53.33],"internvl-chat-v1.2":[-0.895,0.163,62.41],"marin-32b-mantis":[-0.895,0.085,67.48],"codestral-12b-instruct":[-0.896,0.126,36.21],"mixtral-8x7b":[-0.896,0.06,53.11],"llama-3.1-8b-base":[-0.901,0.049,51.25],"gemma-3n-e2b-it":[-0.91,0.081,44.78],"internlm-xcomposer2-vl-7b":[-0.913,0.113,60.72],"gemma-3-4b":[-0.913,0.088,44.72],"llama-3.2-3b-instruct":[-0.919,0.059,33.29],"codellama-34b":[-0.92,0.081,49.46],"gemini-1.0-pro-vision":[-0.922,0.218,61.6],"tigerbot-70b-chat":[-0.922,0.137,68.31],"llada-moe-7b-a1b-base":[-0.922,0.095,54.26],"smollm3-3b-base":[-0.923,0.094,72.43],"llama-3.1-swallow-8b-instruct-v0.5":[-0.925,0.093,40.37],"lfm2-vl-1.6b":[-0.925,0.203,52.48],"vila1.5-40b":[-0.928,0.132,52.95],"telechat2-3b":[-0.928,0.111,62.23],"apertus-70b-instruct":[-0.93,0.048,34.2],"marin-8b-instruct":[-0.936,0.073,48.36],"deepseek-coder-1.3b-instruct":[-0.937,0.084,35.19],"internlm2-7b":[-0.938,0.073,54.57],"mixtral-8x7b-instruct-v0.1":[-0.938,0.053,50.52],"trinity-nano-base":[-0.941,0.085,66.26],"codellama-34b-instruct":[-0.95,0.093,32.9],"mm1.5-3b":[-0.952,0.16,66.44],"llama-3-8b":[-0.955,0.066,52.41],"yi-34b":[-0.957,0.103,60.24],"phi-4-multimodal-instruct":[-0.959,0.127,50.51],"falcon-180b":[-0.963,0.113,65.05],"granite-4.0-1b":[-0.963,0.071,36.86],"lfm2.5-vl-1.6b":[-0.963,0.084,51.24],"qwen2.5-1.5b-instruct":[-0.967,0.058,38.05],"qwen3-1.7b-base":[-0.969,0.086,50.7],"aquila2-34b":[-0.969,0.111,68.78],"llama-2-70b":[-0.971,0.066,62.53],"yi-coder-1.5b-chat":[-0.973,0.106,36.41],"falcon3-3b":[-0.975,0.058,39.59],"internlm2-chat-7b":[-0.979,0.067,53.62],"qwen1.5-14b":[-0.983,0.092,60.3],"qwen-vl-plus":[-0.984,0.112,60.45],"internlm2-chat-7b-sft":[-0.984,0.069,52.96],"deepseek-coder-33b-base":[-0.985,0.073,46.6],"granite-3.2-2b-instruct":[-0.988,0.081,46.44],"marin-8b-base":[-0.991,0.089,56.44],"lfm2.5-230m":[-0.993,0.117,30.74],"granite-4.0-h-1b":[-0.995,0.091,41.45],"hy-0.5b":[-0.995,0.11,45.28],"falcon-h1-0.5b-instruct":[-0.997,0.058,36.02],"xverse-13b-2":[-1.001,0.112,64.68],"llada-8b-base":[-1.005,0.096,51.96],"granite-3.1-2b-instruct":[-1.008,0.078,44.98],"marin-32b-bison":[-1.012,0.089,65.17],"granite-3.3-8b-base":[-1.017,0.083,54.15],"qwen2.5-1.5b":[-1.021,0.05,39.23],"internvl2.5-2b":[-1.023,0.056,52.97],"vita":[-1.028,0.128,59.32],"llada-8b-instruct":[-1.03,0.078,48.56],"gemma-2-2b-it":[-1.032,0.07,37.02],"yi-1.5-6b":[-1.033,0.092,50.88],"eurollm-9b-instruct-2512":[-1.033,0.074,47.67],"solar-10.7b-instruct-v1.0":[-1.034,0.095,60.8],"kanana-2-1.3b-base":[-1.038,0.093,44.86],"llava-next-llama3":[-1.038,0.174,64.3],"internvl3.5-1b":[-1.039,0.203,50.16],"mobilemoe-l":[-1.04,0.078,57.06],"tinyswallow-1.5b-instruct":[-1.046,0.119,30.89],"trida-7b":[-1.052,0.099,51.09],"starcoder2-15b":[-1.058,0.069,42.16],"tigerbot-70b-base":[-1.062,0.125,66.17],"nemotronlabs-voicechat-11b":[-1.065,0.113,48.54],"orion-14b-base":[-1.065,0.077,66.14],"stablebeluga2-70b":[-1.065,0.085,59.74],"llama-3.2-3b-base":[-1.07,0.066,37.83],"bunny-llama3-8b":[-1.073,0.188,61.19],"qwen2.5-coder-1.5b":[-1.075,0.075,44.06],"cambrian-1-8b":[-1.077,0.141,65.47],"vllm-sr-decision-2.0-sol-2b":[-1.079,0.084,46.89],"gemma-4-e4b":[-1.08,0.105,62.46],"qwen-14b-chat":[-1.083,0.066,53.61],"internlm-20b":[-1.089,0.07,65.36],"meta-llama-3-8b-instruct":[-1.093,0.129,58.76],"llama-3-8b-base":[-1.099,0.069,52.02],"qwen3.5-0.8b-thinking":[-1.107,0.06,38.76],"gemma-7b":[-1.107,0.065,51.79],"llama-3-8b-instruct-gradient-1048k":[-1.112,0.087,54.26],"olmo-2-1124-7b-instruct":[-1.117,0.062,28.22],"internvl2.5-1b":[-1.12,0.077,49.78],"phi-3.5-vision-instruct":[-1.122,0.084,52.34],"deepseek-v2-lite-chat":[-1.125,0.054,44.13],"telechat-12b":[-1.129,0.096,56.45],"qwen1.5-7b":[-1.13,0.071,47.55],"mm1-30b":[-1.132,0.153,63.68],"deepseek-coder-7b-base-v1.5":[-1.133,0.094,50.26],"qwen3.5-0.8b":[-1.134,0.052,42.89],"jamba-v0.1":[-1.14,0.115,60.3],"fastvlm-0.5b":[-1.14,0.175,65.8],"qwen1.5-moe-a2.7b":[-1.141,0.1,51.77],"codellama-13b":[-1.143,0.085,44.11],"llama-2-70b-chat":[-1.146,0.104,63.03],"minicpm-moe-8x2b":[-1.15,0.103,49.36],"codellama-13b-instruct":[-1.157,0.104,32.22],"qwen1.5-7b-chat":[-1.158,0.058,45.54],"bitcpm-cann-1b":[-1.158,0.108,63.42],"strands-decider-2b":[-1.159,0.081,43.21],"llama-3.2-3b":[-1.166,0.073,45.59],"nemotron-nano-12b-v2-vl":[-1.169,0.155,34.4],"apertus-8b-instruct":[-1.17,0.052,36.16],"map-neo-7b-instruct":[-1.171,0.073,48.65],"yi-9b":[-1.172,0.096,56.47],"xverse-moe-a4.2b":[-1.176,0.112,60.14],"qwen3-0.6b-base":[-1.18,0.118,50.72],"xgen-mm-interleave-4b":[-1.181,0.169,61.08],"internlm2-base-20b":[-1.182,0.084,49.88],"phi-2":[-1.183,0.08,48.28],"llm-jp-3.1-1.8b-instruct4":[-1.187,0.117,28.72],"qwen3-0.8b":[-1.188,0.059,30.39],"olmo-2-1124-7b":[-1.192,0.097,50.48],"apertus-8b":[-1.194,0.088,52.26],"qwen-7b":[-1.198,0.071,58.36],"deepseek-coder-6.7b-base":[-1.2,0.069,41],"idefics2-8b":[-1.2,0.145,57.27],"gemma-1.1-7b-it":[-1.202,0.078,39.57],"internlm2.5-1.8b-chat":[-1.203,0.081,47.31],"sarashina2.2-1b-instruct-v0.1":[-1.219,0.116,26.46],"chatglm3-6b":[-1.219,0.067,47.44],"minicpm-2b-sft":[-1.22,0.084,50.83],"llava-internlm2-20b-qlora":[-1.225,0.17,58.16],"qwen2.5-coder-0.5b-instruct":[-1.226,0.11,30.55],"qwen2-1.5b-instruct":[-1.226,0.062,35.08],"phi-3.5-vision-4b":[-1.227,0.177,59.72],"qwen2-1.5b":[-1.227,0.069,44.78],"cogagent-18b":[-1.235,0.15,52.89],"mobilemoe-m":[-1.239,0.078,51.89],"llava-1.6-13b":[-1.242,0.148,57.03],"palm-540b":[-1.243,0.105,69.67],"map-neo-7b-sft":[-1.244,0.074,49.54],"gemma-2-7b":[-1.246,0.091,56.29],"codeqwen1.5-7b":[-1.248,0.076,41.02],"deepseek-llm-7b-chat":[-1.249,0.067,54],"intern-decision-2b":[-1.25,0.079,45.41],"bluelm-7b-chat":[-1.252,0.1,49.1],"x-omni":[-1.277,0.135,41.9],"mistral-7b-instruct-v0.2":[-1.285,0.056,49.03],"llama-1-65b":[-1.292,0.075,58.02],"deepseek-v2-lite":[-1.293,0.067,56.99],"lfm2.5-vl-450m":[-1.297,0.133,47.39],"mistral-7b":[-1.303,0.064,48.22],"mistral-7b-v0.1":[-1.303,0.061,47.82],"cogvlm-17b-chat":[-1.305,0.127,58.97],"minicpm-2b-dpo-fp32":[-1.307,0.087,52.91],"gemma-3-1b-it":[-1.309,0.051,30.38],"deepseek-moe-16b-chat":[-1.311,0.076,52.01],"mm1.5-1b":[-1.313,0.184,57.48],"codellama-7b-instruct":[-1.329,0.09,24.48],"deepseek-vl-7b":[-1.334,0.095,53.13],"qwen2.5-0.5b-instruct":[-1.337,0.062,22.19],"baichuan2-13b-base":[-1.339,0.061,55.52],"tigerbot-13b-chat":[-1.342,0.12,59.88],"skywork-13b-base":[-1.344,0.071,60],"solar-10.7b-v1.0":[-1.349,0.1,50.94],"llama-3.2-1.24b":[-1.349,0.079,27.77],"internlm2-base-7b":[-1.351,0.076,47.58],"yi-6b-chat":[-1.352,0.093,51.52],"vllm-sr-d3-edge":[-1.357,0.078,43.84],"t5gemma-2-4b-4b":[-1.366,0.067,52.55],"llava-next-7b":[-1.368,0.204,54.03],"minicpm-v-2.0-3b":[-1.371,0.119,58.4],"smolvlm2-2.2b":[-1.374,0.091,45.54],"starcoderbase-16b":[-1.377,0.099,33.49],"qwen-7b-chat":[-1.388,0.065,46.79],"minicpm4-0.5b":[-1.388,0.108,57.71],"sharegpt4v-7b":[-1.388,0.141,49.83],"yi-vl-34b":[-1.39,0.169,50.51],"qwen1.5-4b":[-1.394,0.098,43.09],"xverse-7b":[-1.397,0.133,53.31],"internvl2-2b":[-1.405,0.054,47.28],"granite-4-h-300m":[-1.409,0.111,26.72],"internlm-chat-20b":[-1.41,0.132,56.02],"starcoder2-7b":[-1.416,0.074,35.55],"tev1-0.8b-experimental":[-1.417,0.083,41.81],"telechat-7b":[-1.417,0.096,46.05],"vllm-sr-decision-2.0-eos-0.8b":[-1.417,0.078,39.42],"olmoe-1b-7b-base":[-1.419,0.106,47.34],"map-neo-7b":[-1.424,0.078,49.51],"llama-1-33b":[-1.425,0.076,53.54],"zephyr-7b-beta":[-1.426,0.115,39.66],"olmoe-1b-7b":[-1.427,0.053,38.76],"lfm2-350m":[-1.43,0.096,27.69],"aquila2-7b":[-1.435,0.127,59.39],"gpt-3":[-1.448,0.114,63.99],"qwen2.5-0.5b":[-1.448,0.05,27.17],"internlm2-chat-1.8b":[-1.45,0.079,42.07],"codellama-7b":[-1.452,0.074,40.87],"smollm2-1.7b-instruct":[-1.467,0.057,38.49],"llama-3.2-1b-instruct":[-1.468,0.054,19.23],"stablelm-zephyr-3b":[-1.473,0.087,45.81],"rakutenai-2.0-mini-instruct":[-1.477,0.116,22.46],"internlm-chat-7b":[-1.478,0.092,51.36],"minicpm-1b-sft":[-1.481,0.088,45.67],"sphinx-2k":[-1.498,0.197,59.79],"monkey":[-1.508,0.171,51.66],"olmo-2-0425-1b-instruct":[-1.509,0.059,36.89],"vllm-sr-decision-2.0-kai-0.6b":[-1.511,0.078,37.11],"paligemma-mix-3b":[-1.511,0.18,52.43],"baichuan2-13b-chat":[-1.512,0.067,45.3],"falcon-40b":[-1.516,0.085,49.61],"gemma-3-1b":[-1.516,0.063,31.84],"intern-decision-0.8b":[-1.521,0.077,39.02],"granite-4-300m":[-1.534,0.101,23.71],"falcon3-1b":[-1.538,0.06,25.79],"internvl2-1b":[-1.543,0.072,45.39],"mistral-7b-instruct-v0.1":[-1.543,0.086,46.66],"starcoder2-3b":[-1.546,0.076,33.04],"bluelm-7b-base":[-1.547,0.097,42.78],"qwen2.5-coder-0.5b":[-1.553,0.077,31.87],"bitcpm-cann-0.5b":[-1.555,0.109,51.98],"yi-6b":[-1.558,0.091,48.28],"mobilellm-p1-base":[-1.571,0.134,56.17],"mobilemoe-s":[-1.578,0.078,42.8],"d1-omni-600m":[-1.585,0.072,40.61],"llama-2-13b":[-1.589,0.062,50.11],"internlm-xcomposer":[-1.589,0.168,49.77],"tigerbot-13b-base":[-1.593,0.12,55.57],"deepseek-coder-1.3b-base":[-1.593,0.076,28.65],"qwen-vl-chat":[-1.604,0.124,59.76],"deepseek-llm-7b-base":[-1.604,0.071,50.54],"baichuan2-7b-chat":[-1.605,0.068,43.34],"gemma-2-2b":[-1.607,0.065,36.69],"qwen2-0.5b-instruct":[-1.609,0.082,23.86],"internlm-7b":[-1.618,0.076,49.48],"janus-pro-7b":[-1.62,0.113,43.24],"yi-vl-6b":[-1.622,0.156,48.99],"qwen1.5-1.8b-chat":[-1.624,0.108,37.09],"baichuan2-7b-base":[-1.624,0.067,47.36],"llava-1.5-13b":[-1.632,0.115,50.8],"emu2-chat":[-1.636,0.155,51.84],"llava-onevision-0.5b":[-1.641,0.114,43.83],"xverse-13b":[-1.646,0.078,48.49],"baichuan-13b-base":[-1.647,0.072,47.02],"lfm2-vl-450m":[-1.65,0.138,42.78],"qwen2-0.5b":[-1.66,0.073,32.66],"qwen1.5-1.8b":[-1.66,0.085,42.93],"mpt-30b":[-1.664,0.088,44.56],"llama-3.2-1.24b-base":[-1.671,0.065,21.63],"deepseek-moe-16b-base":[-1.68,0.073,47.94],"gemma-4-e2b":[-1.682,0.099,54.61],"huginn-3.5b":[-1.686,0.111,41.12],"chatglm2-6b":[-1.689,0.072,47.45],"smollm2-1.7b-base":[-1.695,0.096,34.22],"gemma-2b":[-1.711,0.078,36.3],"mplug-owl2":[-1.711,0.167,53.33],"gliner2.5-decide":[-1.714,0.077,31.82],"chatglm2-6b-base":[-1.725,0.091,45.29],"gemini-nano-2":[-1.727,0.123,45.32],"telechat-1b":[-1.732,0.093,35.65],"minicpm-v":[-1.743,0.172,50.25],"mobilellm-p1":[-1.754,0.081,40.62],"emu3-8b":[-1.766,0.134,42.55],"janus-pro-1.5b":[-1.772,0.206,44.72],"open-llama-13b":[-1.775,0.117,53.68],"llama-2-13b-chat":[-1.775,0.068,43.27],"llama-1-13b":[-1.795,0.071,45.65],"olmo-1.7-7b":[-1.81,0.081,42.8],"moshi":[-1.81,0.12,38.97],"qwen-vl":[-1.813,0.15,58.67],"qwen-1.8b":[-1.818,0.08,43.5],"laya":[-1.859,0.087,30.74],"llama-2-7b":[-1.874,0.058,41.28],"vicuna-13b":[-1.879,0.077,30.83],"lumina-dimoo":[-1.881,0.14,34.92],"llama-2-7b-chat":[-1.89,0.057,37.82],"llava-1.5-7b":[-1.901,0.125,45.04],"alpamayo-1.5-10b":[-1.906,0.164,20.13],"llama-3.2-1b":[-1.934,0.082,39.71],"mpt-7b":[-1.978,0.075,39.87],"chinese-alpaca-plus-13b":[-1.995,0.086,28.4],"llama-1-7b":[-2.002,0.072,40.73],"deepseek-vl-1.3b":[-2.013,0.111,47.05],"qwen1.5-0.5b":[-2.024,0.101,24.84],"t5gemma-2-1b-1b":[-2.027,0.07,38.92],"smolvlm2-0.5b":[-2.05,0.134,37.95],"olmo-7b-instruct":[-2.058,0.07,36.4],"baichuan-7b":[-2.059,0.085,31.4],"idefics-80b-instruct":[-2.087,0.163,40.5],"vicuna-7b":[-2.087,0.086,37.69],"falcon-7b":[-2.141,0.081,35.85],"qwen1.5-0.5b-chat":[-2.141,0.109,26.02],"llava-v1-7b":[-2.142,0.179,39.65],"amberchat":[-2.152,0.072,30.88],"instructblip-7b":[-2.171,0.161,44.09],"amber-7b":[-2.222,0.083,31.78],"gemma-3-270m-it":[-2.27,0.07,23.73],"alpaca-7b":[-2.292,0.101,29.63],"olmo-7b":[-2.295,0.082,32.78],"smollm2-360m-instruct":[-2.298,0.07,27.14],"pythia-6.9b":[-2.303,0.08,35.86],"pythia-12b":[-2.312,0.082,36.6],"smollm2-135m-instruct":[-2.335,0.101,21.71],"tinyllama-1.1b":[-2.399,0.091,25.37],"smollm1-1.7b-pretrained":[-2.454,0.147,39.24],"gemma-3-pt-270m":[-2.541,0.114,35.23],"chatglm-6b":[-2.549,0.1,25.94],"smollm2-360m-base":[-2.587,0.108,8.72],"t5gemma-2-270m-270m":[-2.608,0.073,27.63],"minigpt-4-v1-7b":[-2.667,0.186,26.94],"openflamingo-v2":[-2.718,0.183,26.74],"smollm2-135m-base":[-2.739,0.132,27.49]},"scopes":{"decision":{"sd":0.36,"ext":{"d1-ultra":[1.318,0.194,64.8],"pplx-decider-v1.2":[1.284,0.087,75.49],"vllm-sr-d3":[1.264,0.08,74.34],"clef-flash":[1.16,0.091,68.14],"clef":[1.135,0.078,69.25],"clef-omni":[1.009,0.086,66.72],"glide":[0.999,0.177,51.37],"pplx-decider-v1.1-27b":[0.974,0.181,52.42],"glide-no-thinking":[0.851,0.089,70.75],"jev-1.14":[0.815,0.081,69.13],"jev-1.13":[0.772,0.074,70.2],"vllm-sr-d3-flash":[0.747,0.08,67.47],"mercury-decide":[0.732,0.187,51.72],"autotrust-jev-35b":[0.717,0.083,67.96],"vllm-sr-decision-2.0-vega-27b":[0.714,0.078,67.38],"celeris-1-decision":[0.682,0.191,47.83],"pplx-decider-flash-v1.2":[0.682,0.084,68.26],"microsoft-decision-1":[0.61,0.189,51.03],"autotrust-gev-26b-decide":[0.594,0.086,67.38],"autotrust-jev-27b":[0.575,0.079,65.47],"d1":[0.554,0.19,47.43],"bespoke-nimble-9b-v3":[0.54,0.09,67.65],"vllm-sr-d3-mini":[0.489,0.08,64.93],"gpt-6-luna-decisions":[0.363,0.177,46.03],"h2o-lightning-4b-nemotron-nano":[0.282,0.239,88.13],"h2o-lightning-4b":[0.267,0.198,83.45],"pplx-decider-v1-27b":[0.265,0.271,78.8],"semif":[0.248,0.239,86.62],"diffusiongemma-jev":[0.213,0.085,63.85],"vllm-sr-decision-2.0-lux-9b":[0.086,0.078,59.34],"jevk5":[-0.002,0.239,90.36],"autotrust-jev-9b":[-0.026,0.081,58.59],"bespoke-nimble-9b-v2":[-0.106,0.088,57.27],"d1-3b":[-0.168,0.089,58.04],"vllm-sr-decision-2.0-nox-4b":[-0.2,0.081,57.25],"kev-9b":[-0.211,0.082,56.03],"vllm-sr-d3-nano":[-0.318,0.083,55.77],"intern-decision-4b":[-0.352,0.079,57.94],"tev1-4b-experimental":[-0.368,0.087,55.61],"vllm-sr-d3-lite":[-0.74,0.083,51.33],"vllm-sr-decision-2.0-sol-2b":[-1.177,0.089,46.89],"strands-decider-2b":[-1.264,0.082,47.28],"intern-decision-2b":[-1.398,0.081,48.06],"vllm-sr-d3-edge":[-1.54,0.083,43.84],"tev1-0.8b-experimental":[-1.663,0.086,41.81],"vllm-sr-decision-2.0-eos-0.8b":[-1.686,0.082,39.42],"vllm-sr-decision-2.0-kai-0.6b":[-1.758,0.081,37.11],"intern-decision-0.8b":[-1.78,0.077,41.96],"d1-omni-600m":[-1.868,0.08,36.14],"gliner2.5-decide":[-2.085,0.084,31.82],"laya":[-2.231,0.089,34.9]},"benchmarks":[{"id":"when2call","name":"When2Call","topic":"Tool calling","difficulty":-1.383,"discrimination":0.717,"n":46},{"id":"hle-multichoice","name":"HLE-MultiChoice","topic":"Advanced reasoning","difficulty":10.008,"discrimination":0.2,"n":43},{"id":"bbh-decision","name":"BBH (decision)","topic":"Multi-task reasoning","difficulty":-1.142,"discrimination":0.675,"n":39},{"id":"winogrande","name":"WinoGrande","topic":"Coreference reasoning","difficulty":-1.885,"discrimination":0.834,"n":39},{"id":"chessbench-decision","name":"ChessBench (decision)","topic":"Chess","difficulty":4.939,"discrimination":0.362,"n":38},{"id":"sata-bench","name":"SATA-Bench","topic":"Multiple-answer QA","difficulty":2.005,"discrimination":0.62,"n":38},{"id":"habermas-machine-decision","name":"Habermas Machine (decision)","topic":"Deliberation / preference","difficulty":0.911,"discrimination":0.201,"n":38},{"id":"gpqa-diamond","name":"GPQA-diamond","topic":"Graduate-level QA","difficulty":0.864,"discrimination":0.402,"n":38},{"id":"home-appliance-simulator-decision","name":"Home appliance simulator (decision)","topic":"Device control","difficulty":0.526,"discrimination":2.007,"n":38},{"id":"mmlu-pro","name":"MMLU-Pro","topic":"Multi-domain knowledge","difficulty":-0.081,"discrimination":0.793,"n":38},{"id":"gsm8k-decision","name":"GSM8K (decision)","topic":"Math (grade-school)","difficulty":-0.212,"discrimination":0.869,"n":38},{"id":"cruxeval-decision","name":"CRUXEval (decision)","topic":"Code reasoning","difficulty":-0.687,"discrimination":0.694,"n":38},{"id":"new-yorker-caption-matching","name":"New Yorker caption matching","topic":"Humor understanding","difficulty":-0.898,"discrimination":0.599,"n":38},{"id":"musr","name":"MuSR","topic":"Reasoning","difficulty":-1.309,"discrimination":0.343,"n":38},{"id":"mmlu","name":"MMLU","topic":"Multi-domain knowledge","difficulty":-1.33,"discrimination":0.862,"n":38},{"id":"hellaswag","name":"HellaSwag","topic":"Commonsense reasoning","difficulty":-1.616,"discrimination":1.291,"n":38},{"id":"phishnchips","name":"PhishNChips","topic":"Phishing detection","difficulty":-1.628,"discrimination":0.366,"n":38},{"id":"cladder","name":"CLadder","topic":"Causal reasoning","difficulty":-1.671,"discrimination":0.514,"n":38},{"id":"bpomp-decision","name":"BPoMP (decision)","topic":"Preference prediction","difficulty":-1.742,"discrimination":0.979,"n":38},{"id":"humicroedit-decision","name":"Humicroedit (decision)","topic":"Humor judgement","difficulty":-1.945,"discrimination":0.215,"n":38},{"id":"arc-challenge","name":"ARC-Challenge","topic":"Science QA","difficulty":-1.983,"discrimination":1.27,"n":38},{"id":"bfcl-decision","name":"BFCL (decision)","topic":"Function calling","difficulty":-2.142,"discrimination":1.195,"n":38},{"id":"cfcolor-decision","name":"cfcolor (decision)","topic":"Color perception","difficulty":-2.196,"discrimination":0.2,"n":38},{"id":"hover","name":"HoVer","topic":"Claim verification","difficulty":-2.577,"discrimination":0.408,"n":38},{"id":"arc-easy","name":"ARC-Easy","topic":"Science QA","difficulty":-2.861,"discrimination":1.249,"n":38},{"id":"pop909-cl-decision","name":"POP909-CL (decision)","topic":"Music understanding","difficulty":1.594,"discrimination":1.164,"n":36},{"id":"api-bank-decision","name":"API-Bank (decision)","topic":"Tool use","difficulty":-0.996,"discrimination":1.053,"n":36},{"id":"jevbench","name":"JevBench (Benchmark Heaven)","topic":"Typed decisions","difficulty":0.412,"discrimination":1.134,"n":22},{"id":"aa-omniscience-decision-non-hallucination","name":"AA-Omniscience-Decision Non-Hallucination Rate","topic":"Knowledge and hallucination","difficulty":3.049,"discrimination":0.835,"n":13},{"id":"aa-omniscience-decision-accuracy","name":"AA-Omniscience-Decision Accuracy","topic":"Knowledge and hallucination","difficulty":2.157,"discrimination":0.449,"n":13},{"id":"wildguardtest","name":"WildGuardTest","topic":"Safety","difficulty":-1.664,"discrimination":0.952,"n":13},{"id":"jevbench-public-hard","name":"JevBench public (hard)","topic":"Typed decisions","difficulty":-1.682,"discrimination":0.489,"n":11},{"id":"jevbench-public-original","name":"JevBench public (original/standard)","topic":"Typed decisions","difficulty":-3.155,"discrimination":1.161,"n":10},{"id":"jevbench-public-easy","name":"JevBench public (easy)","topic":"Typed decisions","difficulty":-10.442,"discrimination":0.439,"n":10}]},"faix-agent":{"sd":0.397,"ext":{"claude-fable-5":[2.009,0.218,84.63],"longcat-flash-thinking-2601":[1.767,0.195,88.13],"glm-5.2":[1.756,0.183,74.39],"qwen3.8-max":[1.725,0.199,80.6],"gpt-5.5":[1.702,0.137,76.9],"claude-opus-4.6":[1.657,0.12,70.55],"claude-opus-4.8":[1.656,0.202,75.58],"gemini-3.1-pro":[1.628,0.121,69.52],"gpt-5.4":[1.624,0.123,70.85],"kimi-k2.6":[1.58,0.197,84.28],"glm-5.3-flash":[1.513,0.148,75.19],"glm-5.1":[1.497,0.135,74.01],"claude-opus-4.5-thinking":[1.483,0.188,82.13],"claude-opus-4.7":[1.477,0.166,77.06],"gpt-5.6-sol":[1.431,0.188,76.18],"qwen3.7-plus":[1.383,0.162,68.16],"gpt-5.2":[1.375,0.134,69.13],"claude-opus-4.5":[1.374,0.123,66.99],"gpt-5.6-luna":[1.363,0.188,66.35],"deepseek-v4-flash-0731":[1.362,0.153,75.58],"deepseek-v4-pro-thinking-max":[1.321,0.135,75.31],"qwen3.8-flash-next":[1.308,0.156,75.83],"claude-sonnet-4.6":[1.296,0.142,69.2],"longcat-flash-thinking-zigzag":[1.295,0.195,86.9],"qwen3.7-max":[1.274,0.14,72.44],"kimi-k3":[1.258,0.229,77.05],"glm-5":[1.239,0.136,62.5],"kimi-k2.6-thinking":[1.228,0.132,71.33],"gpt-5.2-thinking-xhigh":[1.192,0.193,72.17],"inkling":[1.179,0.194,60.5],"gemini-3-pro":[1.16,0.122,61.21],"deepseek-v4-pro-thinking":[1.13,0.199,63.97],"ring-2.6-1t-high":[1.113,0.195,84.26],"qwen3.6-plus":[1.111,0.162,61.54],"qwen3.5-397b-a17b":[1.075,0.127,67.41],"deepseek-v4-pro":[1.06,0.187,65.53],"mimo-v2.5":[1.04,0.186,56.88],"claude-sonnet-4.5":[1.037,0.131,62.39],"gemini-3.5-flash":[1.024,0.264,54.54],"deepseek-v4-flash-thinking-max":[0.968,0.144,61.52],"minimax-m3":[0.96,0.161,67.72],"qwen3.8-27b":[0.937,0.155,66.53],"qwen3.5-27b":[0.919,0.147,64.15],"deepseek-v4-flash-thinking":[0.913,0.199,58.77],"qwen3.6-27b":[0.91,0.186,61.4],"qwen3.6-35b-a3b":[0.893,0.14,58.93],"ring-2.6-1t-xhigh":[0.893,0.168,77.88],"glm-4.7-flash":[0.886,0.197,75.63],"kimi-k2.5-thinking":[0.874,0.124,59.02],"muse-spark":[0.867,0.168,77.57],"gpt-5":[0.862,0.107,57.86],"deepseek-v3.2-thinking":[0.862,0.126,58.93],"nex-n2-mini":[0.84,0.294,63.31],"kolibri-1":[0.819,0.195,80.43],"seed1.8":[0.813,0.223,66.3],"gpt-5.4-mini":[0.809,0.145,65.99],"kimi-k2.5":[0.731,0.164,54.76],"qwen3.5-122b-a10b":[0.726,0.141,61.08],"deepseek-v4-flash":[0.71,0.187,58.7],"inkling-small":[0.699,0.166,72.07],"areal-sea-235b-a22b":[0.696,0.195,81],"qwen3.5-35b-a3b":[0.694,0.133,62.68],"gpt-5.4-nano":[0.691,0.15,61.82],"glm-4.7":[0.691,0.26,49.37],"nemotron-3-ultra":[0.684,0.154,65.88],"holo2-235b-a22b":[0.678,0.223,84.57],"minimax-m2.7":[0.668,0.149,61.84],"qwen3-max-thinking":[0.662,0.172,59.64],"gemini-3-pro-preview":[0.648,0.154,63.88],"kimi-k2-thinking":[0.645,0.151,49.67],"gemma-4-31b-it":[0.624,0.172,46.15],"gpt-5-codex":[0.604,0.233,46.2],"mimo-v2-flash":[0.601,0.171,54.17],"deepseek-v3.2":[0.599,0.149,54.83],"nemotron-3.5-super-vl-120b-a12b":[0.592,0.181,70.37],"gpt-5-thinking":[0.55,0.312,66],"gemini-3-flash":[0.538,0.153,60.54],"gpt-5-high":[0.521,0.147,57.83],"gpt-5.1":[0.516,0.187,71.94],"holo2-30b-a3b":[0.516,0.205,79.15],"longcat-flash-lite-sparse":[0.483,0.177,58.16],"comet-60b-a12b-fp8":[0.429,0.178,73.63],"holo1.5-72b":[0.386,0.223,80.36],"mai-code-1-flash":[0.358,0.194,59.23],"comet-60b-a12b":[0.354,0.18,73.33],"comet-60b-a12b-nvfp4":[0.298,0.197,71.75],"qwen3-vl-30b-a3b-instruct":[0.292,0.262,59.07],"minimax-m2":[0.263,0.137,48.61],"north-mini-code-1.0":[0.261,0.226,35.77],"gpt-5-mini-high":[0.222,0.127,52.29],"grok-4":[0.199,0.129,49.98],"o3":[0.197,0.117,53.83],"holo2-8b":[0.196,0.205,73.12],"claude-4.5-haiku":[0.185,0.125,47.24],"nemotron-3.5-super-vl-120b-a12b-nvfp4":[0.173,0.182,71.2],"qwen3.5-4b":[0.164,0.142,52.69],"claude-opus-4.1":[0.149,0.117,47.3],"holo2-4b":[0.145,0.223,77.63],"claude-4.5-sonnet-thinking":[0.135,0.158,53.57],"ui-venus-72b":[0.135,0.227,72.22],"holo1.5-7b":[0.132,0.223,76.23],"qwen3.5-9b":[0.126,0.153,39.18],"kimi-k2-0905-preview":[0.089,0.226,46.9],"qwen3-vl-30b-a3b-thinking":[0.08,0.223,75.5],"seed-1.5-vl":[0.071,0.261,53.9],"command-a-plus-05-2026":[0.055,0.168,45.73],"claude-sonnet-4":[0.024,0.109,52.63],"kimi-k2-instruct-0905":[-0.007,0.176,51.75],"qwen3-vl-32b-instruct":[-0.032,0.261,51.67],"nemotron-3-super-120b-a12b":[-0.046,0.146,52.41],"joyai-llm-flash":[-0.055,0.195,67.13],"claude-sonnet-4-thinking":[-0.061,0.172,46.82],"kimi-k2-0905":[-0.068,0.182,46.97],"qwen3-coder-480b-a35b-instruct":[-0.081,0.241,45.05],"deepseek-v3.1":[-0.105,0.21,42.84],"grok-code-fast-1":[-0.122,0.153,37.1],"k-exaone":[-0.126,0.171,60.38],"glm-4.6":[-0.131,0.151,46.8],"exaone-4.5-33b-thinking":[-0.146,0.195,69.13],"qwen3-vl-235b-a22b-thinking":[-0.167,0.162,62.3],"longcat-flash-lite":[-0.188,0.182,59.41],"grok-4-fast":[-0.203,0.153,34.35],"kimi-k2-0711-preview":[-0.204,0.243,40.77],"qwen2.5-vl-72b":[-0.212,0.236,63.75],"nova-2-lite":[-0.227,0.167,44.37],"qwen3-vl-4b-thinking":[-0.231,0.223,69.6],"ui-venus-7b":[-0.237,0.205,64.91],"qwen3-vl-8b-thinking":[-0.254,0.223,68.93],"qwen3-vl-8b-instruct":[-0.257,0.261,46.67],"qwen3-max-instruct-preview":[-0.258,0.228,24.06],"devstral-small-2":[-0.273,0.226,25.07],"claude-opus-4":[-0.28,0.163,55.38],"gpt-5-mini":[-0.283,0.119,38.42],"holo1.5-3b":[-0.292,0.223,70.17],"gemma-4-26b-a4b-it":[-0.296,0.146,40.89],"o4-mini":[-0.301,0.144,41.56],"kimi-k2-instruct-0711":[-0.308,0.293,34.78],"gemma-4-12b-it":[-0.309,0.171,24.12],"kimi-k2-instruct":[-0.31,0.129,39.9],"gpt-oss-120b-high":[-0.375,0.163,48.7],"kolibri-origin":[-0.377,0.195,61.57],"ui-tars-1.5-7b":[-0.378,0.209,59.57],"holotron-12b":[-0.383,0.223,66.3],"glm-4.5":[-0.397,0.165,40.56],"holo1-7b":[-0.418,0.223,65.19],"nemotron-labs-3-puzzle-75b-a9b":[-0.429,0.182,51.12],"qwen3-vl-4b-instruct":[-0.431,0.261,43.23],"gemini-2.5-pro":[-0.436,0.108,40.77],"deepseek-v3.2-exp":[-0.438,0.198,42.54],"deepseek-v3.1-terminus":[-0.463,0.174,28.07],"apriel-1.6-15b-thinker":[-0.47,0.174,49.53],"longcat-next":[-0.482,0.172,53.86],"glm-4.5-air":[-0.511,0.146,44.5],"kimi-k2":[-0.585,0.164,42.72],"qwen3-vl-2b-instruct":[-0.585,0.261,39.4],"gpt-4.1":[-0.591,0.117,43.29],"openpangu-r-72b-2512-slow-thinking":[-0.597,0.162,64.48],"solar-open-100b":[-0.608,0.168,40.8],"gpt-4.1-2025-04-14":[-0.61,0.35,35.77],"claude-3.7-sonnet":[-0.61,0.16,38.18],"qwen3-235b-a22b-instruct-2507":[-0.611,0.247,33.96],"glm-4.6v-flash":[-0.627,0.261,39.5],"holo1-3b":[-0.655,0.223,60.49],"gpt-oss-120b-medium":[-0.743,0.195,56.2],"qwen3-235b-a22b-thinking-2507":[-0.745,0.123,46.9],"qwen3.5-2b":[-0.753,0.196,28.7],"apriel-1.5-15b-thinker":[-0.765,0.202,41.62],"openpangu-r-72b-2512-fast-thinking":[-0.769,0.162,58.72],"openpangu-r-7b-2512-slow-thinking":[-0.792,0.162,58.66],"qwen3-next-80b-a3b-thinking":[-0.792,0.162,59.12],"nemotron-3-nano-30b-a3b":[-0.792,0.195,54.5],"qwen2.5-vl-72b-instruct":[-0.8,0.293,26.27],"gemini-2.5-flash":[-0.842,0.106,31.43],"deepseek-r1":[-0.867,0.286,38.5],"gpt-oss-120b":[-0.879,0.132,32.97],"gpt-5-mini-minimal":[-0.897,0.261,32.9],"deepseek-r1-0528":[-0.904,0.133,41.87],"openpangu-r-7b-2512-fast-thinking":[-0.942,0.162,54.62],"mistral-small-4-thinking":[-0.964,0.195,48.13],"qwen2.5-vl-7b":[-0.969,0.205,48.65],"gemini-2.5-flash-thinking":[-0.991,0.154,49.37],"deepseek-v3-0324":[-1.027,0.18,49.1],"qwen2.5-vl-3b":[-1.037,0.223,51.94],"gemini-2.5-flash-preview-09-2025":[-1.041,0.174,42.25],"gpt-4.1-mini":[-1.067,0.136,21.68],"gpt-oss-20b":[-1.075,0.199,30.89],"nemotron-labs-3-elastic-30b-a3b":[-1.126,0.195,45.34],"qwen3-235b-a22b":[-1.139,0.115,38.44],"nvidia-nemotron-3-nano-30b-a3b-bf16":[-1.167,0.163,32.82],"qwen3-30b-a3b-thinking-2507":[-1.214,0.157,43.98],"o3-mini-high":[-1.226,0.181,39.35],"exaone-4.0-32b-thinking":[-1.247,0.195,47.73],"qwen3-30b-a3b":[-1.252,0.162,47.43],"nemotron-3-nano-4b-thinking":[-1.263,0.197,35.37],"deepseek-v3":[-1.331,0.189,26.1],"gpt-4o-2024-11-20":[-1.349,0.244,31.37],"gemma-4-e4b-it":[-1.382,0.141,19.89],"nemotron-3-nano-4b":[-1.385,0.199,30.3],"qwen2.5-coder-32b-instruct":[-1.434,0.332,25.77],"gpt-4o":[-1.455,0.194,28.53],"qwen3-32b-thinking":[-1.471,0.126,33.86],"gemini-2.5-flash-lite":[-1.5,0.183,28.61],"gemma-4-e2b-it":[-1.576,0.162,13.88],"qwen3-next-80b-a3b-instruct":[-1.582,0.149,38.47],"seed-coder-8b-instruct":[-1.618,0.339,22.5],"kimi-linear-instruct":[-1.621,0.185,24.63],"llama-4-maverick":[-1.751,0.175,10.67],"qwen3-8b-thinking":[-1.873,0.193,20.43],"qwen3-32b-nothinking":[-1.897,0.185,30.9],"apertus-70b-instruct":[-1.912,0.199,20.13],"qwen3-14b":[-1.958,0.255,20.15],"qwen3-32b":[-2.044,0.134,17.96],"qwen2.5-coder-7b-instruct":[-2.198,0.343,14.67],"qwen3-30b-a3b-instruct-2507":[-2.338,0.195,29.97],"qwen3-omni-30b-a3b-instruct":[-2.343,0.19,33.12],"qwen3-8b":[-2.663,0.151,13.15],"nemotron-nano-12b-v2-vl":[-2.711,0.205,16]},"benchmarks":[{"id":"tau2-telecom","name":"TAU2-Telecom","topic":"Agent tasks (telecom)","difficulty":-0.72,"discrimination":1.755,"n":141},{"id":"tau2-retail","name":"TAU2-Retail","topic":"Agent tasks (retail)","difficulty":-1.965,"discrimination":0.507,"n":100},{"id":"tau2-airline","name":"TAU2-Airline","topic":"Agent tasks (airline)","difficulty":-1.02,"discrimination":0.57,"n":96},{"id":"terminal-bench-2.0","name":"Terminal-Bench 2.0","topic":"Agent terminal tasks","difficulty":0.639,"discrimination":1.101,"n":85},{"id":"mcp-atlas","name":"MCP-Atlas","topic":"Agent evaluation","difficulty":0.419,"discrimination":1.202,"n":81},{"id":"swe-bench-pro-public","name":"SWE-Bench Pro (Public)","topic":"Software engineering","difficulty":0.862,"discrimination":0.895,"n":70},{"id":"terminal-bench","name":"Terminal-Bench","topic":"Agent terminal tasks","difficulty":0.633,"discrimination":0.777,"n":65},{"id":"gaia","name":"GAIA","topic":"General AI tasks","difficulty":-0.633,"discrimination":0.693,"n":63},{"id":"mcpmark","name":"MCPMark","topic":"Agent tool-use (MCP)","difficulty":1.129,"discrimination":1.204,"n":61},{"id":"terminal-bench-hard","name":"Terminal-Bench Hard","topic":"Agent terminal tasks","difficulty":1.53,"discrimination":0.761,"n":56},{"id":"osworld-g","name":"OSWorld-G","topic":"GUI agents","difficulty":-0.594,"discrimination":0.796,"n":44},{"id":"androidworld","name":"AndroidWorld","topic":"Mobile agents","difficulty":-0.152,"discrimination":0.763,"n":38},{"id":"mcp-universe","name":"MCP Universe","topic":"Agent evaluation","difficulty":1.287,"discrimination":0.696,"n":33},{"id":"autocodebench-lite","name":"AutoCodeBench-Lite","topic":"Autonomous coding","difficulty":-0.902,"discrimination":0.683,"n":29},{"id":"autocodebench","name":"AutoCodeBench","topic":"Autonomous coding","difficulty":-0.235,"discrimination":0.49,"n":26},{"id":"showdown","name":"Showdown","topic":"GUI agents","difficulty":-1.111,"discrimination":0.795,"n":22},{"id":"webclick","name":"WebClick","topic":"GUI agents","difficulty":-1.75,"discrimination":1.18,"n":22},{"id":"xbench-deepsearch","name":"xBench-DeepSearch","topic":"Agentic research","difficulty":-2.938,"discrimination":0.2,"n":22},{"id":"herobench","name":"HeroBench","topic":"Long-horizon planning","difficulty":-0.017,"discrimination":1.735,"n":21},{"id":"osworld","name":"OSWorld","topic":"GUI agents","difficulty":0.43,"discrimination":0.777,"n":20},{"id":"astabench","name":"AstaBench","topic":"Agent evaluation","difficulty":1.299,"discrimination":0.624,"n":16},{"id":"livemcp-101","name":"LiveMCP-101","topic":"Agent real-time eval","difficulty":0.344,"discrimination":0.905,"n":15},{"id":"tau1-airline","name":"TAU1-Airline","topic":"Agent tasks (airline)","difficulty":-0.807,"discrimination":1.014,"n":13},{"id":"tau1-retail","name":"TAU1-Retail","topic":"Agent tasks (retail)","difficulty":-1.724,"discrimination":0.912,"n":13}]},"faix-code":{"sd":0.354,"ext":{"claude-fable-5":[2.223,0.096,80.13],"kimi-k3":[1.99,0.124,81.01],"claude-mythos-preview":[1.972,0.104,87.73],"claude-opus-4.8":[1.944,0.071,79.04],"gpt-5.5":[1.926,0.071,75.56],"claude-opus-4.7":[1.795,0.071,69.57],"fugu-ultra":[1.767,0.14,75.2],"gpt-5.6-luna":[1.743,0.138,69.4],"glm-5.2":[1.719,0.086,77.93],"gpt-5.6-sol":[1.697,0.127,67.82],"claude-sonnet-5":[1.688,0.087,63.51],"claude-opus-4.6":[1.676,0.058,67.29],"gemini-3.1-pro":[1.659,0.066,65.59],"qwen3.8-max":[1.658,0.141,68.13],"qwen3.8-omni-flash":[1.637,0.121,78.8],"qwen3.8-flash-next":[1.635,0.098,74.2],"fugu":[1.609,0.14,70.67],"deepseek-v4-pro":[1.609,0.081,76.2],"gpt-5.3-codex":[1.602,0.113,70],"gemini-3-pro-preview":[1.593,0.057,79.03],"gpt-5.4":[1.588,0.068,61.67],"qwen3.7-max":[1.566,0.084,72.35],"deepseek-v4-pro-thinking-max":[1.56,0.084,71.2],"deepseek-v4-flash-0731":[1.557,0.101,72.26],"claude-opus-4.5":[1.552,0.049,74.32],"kimi-k2.6-thinking":[1.528,0.078,69.69],"ornith-1.0-397b":[1.522,0.116,74.5],"beam":[1.512,0.098,72.8],"deepseek-v4-flash":[1.506,0.082,70.87],"ornith-1.5-122b":[1.499,0.124,71.57],"qwen3.7-plus":[1.497,0.084,70.38],"glm-5.1":[1.466,0.084,69.48],"hy3":[1.46,0.101,75.67],"dots3-note-preview":[1.456,0.11,81.87],"claude-sonnet-4.6":[1.453,0.075,64.08],"deepseek-v4-pro-thinking":[1.448,0.086,72.2],"gemini-3-pro":[1.445,0.057,64.87],"gpt-5.2-high":[1.436,0.099,62.32],"qwen3.6-max-preview":[1.429,0.127,56.57],"deepseek-v4-flash-thinking-max":[1.42,0.083,66.14],"claude-sonnet-4.5":[1.42,0.053,71.25],"gpt-5.2":[1.407,0.071,66.46],"inkling-small":[1.4,0.098,69.03],"glm-5.3-flash":[1.399,0.108,71.89],"qwen3.6-plus":[1.395,0.084,66.55],"claude-opus-4.5-thinking":[1.394,0.082,67.43],"gpt-5.2-thinking":[1.394,0.124,73.67],"qwen3.8-27b":[1.393,0.092,76],"glm-5":[1.381,0.08,67.72],"seed2.1-pro":[1.377,0.124,70.3],"mimo-v2.5":[1.375,0.09,64.4],"minimax-m2.7":[1.374,0.08,62.79],"minimax-m3":[1.372,0.132,61.63],"deepseek-v4-flash-thinking":[1.362,0.086,69.22],"gpt-5-medium":[1.351,0.086,82.65],"iquest-coder-v1-40b-loop-thinking":[1.348,0.131,91.3],"gpt-5.2-thinking-xhigh":[1.345,0.085,62.42],"seed2.0-pro":[1.339,0.107,71.77],"gpt-5.4-mini":[1.337,0.095,67.12],"mimo-v2-pro":[1.335,0.104,68.93],"kimi-k2.5-thinking":[1.325,0.071,62.04],"qwen3.6-27b":[1.319,0.084,64.17],"minimax-m2.5":[1.314,0.101,57.4],"gemini-3-flash":[1.299,0.064,56.93],"nemotron-3-ultra":[1.297,0.098,65.23],"inkling":[1.291,0.132,59.63],"kimi-k2.5":[1.291,0.084,63.17],"ling-3.0-flash":[1.288,0.133,77.4],"qwen3.5-397b-a17b":[1.287,0.084,63.83],"iquest-coder-v1-40b-thinking":[1.286,0.131,90.28],"gpt-5-codex":[1.284,0.078,66.38],"ornith-1.5-35b-a3b":[1.281,0.124,63.3],"nemotron-3.5-super-vl-120b-a12b":[1.28,0.098,65.38],"gpt-5.1-high":[1.275,0.083,56.16],"gpt-5.1":[1.267,0.071,72.67],"gpt-5":[1.264,0.054,61.34],"step-3.5-flash-20260204":[1.256,0.09,65.07],"hy3-preview":[1.256,0.104,65.7],"mai-thinking-1":[1.243,0.095,65],"comet-60b-a12b-fp8":[1.221,0.111,59.54],"qwen3.8-27b-ud-q4-k-xl":[1.221,0.136,85.65],"gpt-5-mini":[1.221,0.067,59.37],"gemini-3.5-flash-lite":[1.217,0.132,56.7],"ornith-1.0-35b":[1.215,0.113,56.41],"claude-opus-4.1":[1.211,0.073,58.31],"kimi-k2-thinking":[1.21,0.062,68.34],"qwen3.6-35b-a3b":[1.209,0.07,62.82],"agents-a1":[1.209,0.111,62.25],"nemotron-3.5-super-vl-120b-a12b-nvfp4":[1.208,0.111,59.12],"step-3.7-flash":[1.208,0.106,71.55],"mai-code-1-flash":[1.206,0.094,55.9],"laguna-m.1":[1.203,0.096,59.22],"solar-open-2-250b":[1.202,0.137,72.9],"ternary-bonsai-2-27b":[1.201,0.143,85.8],"mistral-medium-3.5":[1.196,0.124,70.77],"glm-4.7-thinking":[1.187,0.111,67.73],"claude-4.5-sonnet-thinking":[1.186,0.063,57.78],"comet-60b-a12b":[1.185,0.111,58.38],"deepseek-v3.2-thinking":[1.184,0.071,65.03],"mimo-v2-flash":[1.183,0.092,67.35],"minimax-m2.1":[1.18,0.076,61.09],"comet-60b-a12b-nvfp4":[1.17,0.111,57.89],"ring-2.6-1t-xhigh":[1.16,0.131,69.6],"muse-glimmer-30b":[1.159,0.106,73.79],"qwen3-max-thinking":[1.156,0.102,62.6],"seed1.8":[1.145,0.095,59.9],"o3":[1.134,0.071,58.86],"grok-4-fast":[1.131,0.094,63.92],"gpt-5-high":[1.13,0.057,58.01],"qwen3.5-122b-a10b":[1.122,0.072,58.91],"gpt-5-thinking":[1.121,0.1,56.45],"seed2.0-lite":[1.118,0.107,63.7],"gemini-2.5-pro-preview-06-05":[1.113,0.099,58.61],"longcat-flash-thinking-2601":[1.107,0.111,65],"qwen3.5-27b":[1.093,0.072,63.37],"kat-coder-v2.5-dev":[1.093,0.124,58.87],"deepseek-v3.2":[1.081,0.055,66.09],"raon-1-mini-preview":[1.074,0.124,63.7],"qwen3.5-35b-a3b":[1.065,0.077,61.48],"gemini-3-flash-preview":[1.061,0.086,73.82],"laguna-xs.2":[1.061,0.096,53.58],"kimi-k2-0905-preview":[1.057,0.092,51.46],"claude-4.5-haiku":[1.055,0.062,56.21],"kolibri-1":[1.038,0.115,81.67],"laguna-xs-2.1":[1.033,0.092,53.72],"nanbeige4.2-3b":[1.023,0.094,62.92],"gpt-5-mini-high":[1.02,0.073,51.02],"devstral-2":[1.02,0.104,55.37],"o3-high":[1.017,0.068,44.9],"gpt-5.4-none":[1.013,0.103,62.01],"qwen3-coder-next":[1.002,0.078,58.95],"grok-4":[1.002,0.066,56.57],"ornith-1.0-9b":[1.001,0.116,54.77],"spark-x2.6-4b":[0.999,0.124,54.77],"deepseek-v3.1-terminus":[0.998,0.065,62.4],"telechat3-coder-36b-thinking":[0.998,0.097,69.25],"claude-sonnet-4":[0.997,0.056,54.27],"gpt-5.4-nano":[0.991,0.115,44.15],"nemotron-3-super-120b-a12b":[0.989,0.076,62.07],"longcat-flash-lite-sparse":[0.984,0.104,53.74],"ling-2.6-1t":[0.98,0.107,59.41],"nova-2-pro":[0.975,0.102,59.13],"gemini-2.5-pro":[0.973,0.043,55.1],"claude-opus-4":[0.972,0.055,59.63],"o4-mini":[0.965,0.08,58.44],"minimax-m2":[0.963,0.065,62.42],"claude-opus-4-thinking":[0.961,0.092,64.78],"deepseek-r1-0528":[0.95,0.068,59.22],"nex-n2-mini":[0.944,0.095,47.66],"claude-sonnet-4-thinking":[0.939,0.113,55.12],"gemma-4-31b-it":[0.937,0.081,60.24],"north-mini-code-1.0":[0.935,0.093,50.46],"glm-4.6":[0.933,0.068,63.08],"gemma-4-26b-a4b-it":[0.93,0.081,55.78],"qwen3-coder-480b-a35b":[0.925,0.071,37.47],"iquest-coder-v1-40b-instruct":[0.909,0.067,68.32],"ernie-5.0":[0.908,0.14,84.41],"deepseek-v3.1":[0.905,0.068,62.92],"qwen3-235b-a22b-thinking-2507":[0.894,0.067,56.42],"qwen3-coder-plus":[0.891,0.104,49.9],"qwen3-coder-480b-a35b-instruct":[0.891,0.052,64.85],"k2-horizon-7b":[0.883,0.111,52.02],"o4-mini-high":[0.878,0.072,61.9],"deepseek-v3.2-exp":[0.878,0.066,56.22],"claude-3.7-sonnet":[0.874,0.061,47.73],"keye-vl-2.0-30b-a3b":[0.873,0.125,65.9],"gemini-3.1-flash-lite":[0.869,0.111,52.75],"claude-3.7-sonnet-20250219":[0.869,0.108,50.67],"iquest-coder-v1-40b-loop-instruct":[0.868,0.063,67.87],"kimi-k2-instruct-0711":[0.864,0.083,52.12],"glm-4.5":[0.86,0.067,52.85],"o1-2024-12-17-high":[0.855,0.098,56.7],"qwen3-next-80b-a3b-thinking":[0.849,0.099,65.96],"deepseek-v3.1-thinking":[0.849,0.068,41.36],"glm-4.7":[0.843,0.067,67.67],"kimi-k2-0905":[0.835,0.073,52.55],"longcat-flash-lite":[0.832,0.106,42.08],"kimi-k2":[0.831,0.084,49.7],"kimi-k2-instruct-0905":[0.828,0.053,66.16],"nova-2-lite":[0.823,0.102,52.37],"mistral-small-4-thinking":[0.822,0.114,74.93],"kimi-k2-instruct":[0.817,0.055,44.1],"grok-4.1-fast":[0.815,0.091,50.52],"k-exaone":[0.81,0.101,48.68],"grok-code-fast-1":[0.81,0.095,62.2],"granite-4.2-30b":[0.802,0.098,49.34],"o1-2024-12-17":[0.792,0.096,57.23],"o3-mini-2025-01-31-high":[0.784,0.129,58.87],"gemma-4-26b-a4b":[0.782,0.127,61.04],"nemotron-cascade-14b-thinking":[0.782,0.108,65.67],"claude-sonnet-4-20250514":[0.778,0.11,40.29],"qwen3-max":[0.775,0.105,47.1],"o1":[0.769,0.1,64.47],"iquest-coder-v1-14b-thinking":[0.761,0.095,57.42],"grok-3-beta-think":[0.76,0.09,64.83],"gpt-oss-120b-high":[0.759,0.082,50.86],"ministral-3-r-8b":[0.757,0.107,79.64],"qwen3-30b-a3b-2507":[0.756,0.097,60.3],"devstral-small-2":[0.755,0.093,41.87],"gpt-4.1":[0.75,0.055,55.19],"qwen-3-235b-a22b-thinking":[0.746,0.104,73.54],"gpt-oss-120b":[0.745,0.056,49.4],"quasar-alpha":[0.74,0.111,48.2],"mellum2.1-12b-a2.5b-thinking":[0.74,0.117,74.97],"o3-mini":[0.737,0.089,64.05],"minimax-m1-80k":[0.724,0.127,63.1],"nemotron-cascade-2-30b-a3b":[0.724,0.134,48.23],"ornith-1.5-9b":[0.724,0.112,66.58],"qwen3-max-instruct-preview":[0.721,0.095,63.07],"nemotron-3-nano-30b-a3b":[0.715,0.09,71.8],"deepseek-r1":[0.712,0.062,47.3],"gemini-2.5-flash":[0.71,0.051,46.71],"minicpm5-2b":[0.704,0.111,49.33],"gemini-2.5-flash-thinking":[0.702,0.078,52.9],"nemotron-cascade-8b-thinking":[0.697,0.109,62.85],"o1-preview-2024-09-12":[0.693,0.087,76.56],"gpt-oss-20b":[0.692,0.069,56.05],"minimax-m1-40k":[0.69,0.127,61.83],"telechat3-36b-thinking":[0.685,0.127,62.67],"k2-think":[0.682,0.11,38.39],"qwen3-235b-a22b-instruct-2507":[0.681,0.057,57.99],"seed-thinking-v1.5":[0.678,0.107,62.33],"qwen3-235b-a22b":[0.676,0.057,51.63],"olmo-3-think-32b-dpo":[0.67,0.09,82.7],"nemotron-cascade-8b":[0.669,0.11,61.75],"nvidia-nemotron-nano-9b-v2":[0.668,0.092,74.23],"intern-s1-pro":[0.664,0.124,51.81],"o1-preview":[0.662,0.082,76.05],"gemma-4-12b-it":[0.661,0.081,48.3],"glm-4.5-air":[0.654,0.072,56.83],"gpt-5-minimal":[0.651,0.108,61.53],"o3-mini-2025-01-31-med":[0.646,0.129,54.93],"olmo-3.1-think-32b":[0.64,0.093,78.32],"o1-mini":[0.634,0.089,76.12],"k2-horizon-3.7b":[0.634,0.115,44.38],"qwen3.5-9b":[0.633,0.067,58.17],"nemotron-nano-v2-9b":[0.633,0.107,78.89],"granite-4.2-8b":[0.63,0.089,50.54],"falcon-h1r-7b":[0.625,0.093,59.31],"claude-3.5-sonnet-20241022":[0.623,0.058,61.33],"ling-2.6-flash":[0.618,0.116,52.4],"gka-primed-hqwen3-32b-reasoner":[0.616,0.17,49.64],"qwen3-vl-32b-thinking":[0.615,0.123,80.53],"nemotron-32b":[0.614,0.11,35.43],"deepseek-v3-0324":[0.612,0.068,43.68],"joyai-llm-flash":[0.612,0.1,49.71],"qwen3-32b-thinking":[0.598,0.075,54.28],"glm-4.7-flash":[0.586,0.089,59.78],"openthinkeragent-32b":[0.584,0.085,37.53],"qwen3-next-80b-a3b-instruct":[0.576,0.072,49.8],"qwen3-30b-a3b-thinking-2507":[0.572,0.084,58.42],"openreasoning-nemotron-7b":[0.56,0.092,57.38],"gpt-4.1-2025-04-14":[0.559,0.156,37.21],"olmo-3-think-32b-sft":[0.556,0.09,80.72],"telechat3-105b-a4.7b-thinking":[0.555,0.127,58.13],"gemini-2.5-flash-preview-09-2025":[0.547,0.086,44.99],"gemini-exp-1206":[0.536,0.111,42.33],"o3-mini-2025-01-31-low":[0.534,0.129,51.17],"deepseek-r1-distill-qwen-32b":[0.534,0.115,63.54],"hypernova-60b-2605":[0.531,0.084,38.7],"qwen3.8-27b-iq2-xxs":[0.525,0.136,74.26],"qwq-32b":[0.522,0.086,41.95],"apriel-1.6-15b-thinker":[0.518,0.095,48.44],"o1-mini-2024-09-12":[0.517,0.068,70.86],"spark-x2.5-4b":[0.515,0.098,55.31],"gemini-2.5-flash-lite":[0.515,0.114,31.87],"motif-2-12.7b-reasoning":[0.513,0.123,76.83],"granite-4.2-3b":[0.512,0.106,38.3],"sarvam-30b":[0.51,0.104,72.2],"mellum2-12b-a2.5b-thinking":[0.505,0.131,61.52],"minicpm-sala":[0.5,0.107,74.18],"ling-1t":[0.491,0.105,58.11],"ernie-4.5":[0.491,0.153,69.75],"deepseek-v3":[0.49,0.058,64.83],"motif-2-12.7b-instruct":[0.487,0.127,75.3],"command-a-plus-05-2026":[0.479,0.17,45.32],"ax-k1":[0.478,0.156,66.15],"nemotron-3.5-lightning-30b-a3b":[0.448,0.123,51.09],"qwen3-14b-thinking":[0.44,0.142,53.05],"gka-primed-hqwen3-8b-reasoner":[0.44,0.172,43.9],"qwen3-vl-8b-thinking":[0.439,0.115,72.55],"olmo-3-think-32b":[0.436,0.105,66.47],"agents-a1-4b":[0.435,0.131,60.63],"qwen3-32b":[0.433,0.055,51.39],"rnj-1.5":[0.427,0.127,63.84],"mimo-7b-rl":[0.426,0.114,43.4],"qwen3-coder-30b-a3b-instruct":[0.424,0.059,53.53],"qwen3-32b-nothinking":[0.422,0.101,54.88],"llada2.0-flash":[0.422,0.097,74.4],"o3-mini-high":[0.422,0.076,46.04],"qwen3-4b-2507":[0.419,0.162,45.6],"gpt-4.1-mini":[0.418,0.077,49.3],"apriel-1.5-15b-thinker":[0.413,0.08,35.07],"olmo-3-think-7b":[0.41,0.094,61.07],"gdn-primed-hqwen3-8b-reasoner":[0.405,0.173,40.96],"phi-4-reasoning-plus":[0.405,0.097,27.05],"k2-high-70b":[0.403,0.128,81.1],"gpt-5-nano":[0.402,0.081,34.38],"minicpm4.1-8b":[0.398,0.107,72.71],"deepcoder-14b-preview":[0.391,0.163,41.47],"seed1.6":[0.391,0.168,59.23],"ministral-3-14b-reasoning":[0.387,0.137,44.43],"grok-3-beta":[0.382,0.087,60.63],"llada2.1-flash-q":[0.376,0.116,69.7],"qwen3.5-4b":[0.373,0.074,52.18],"olmo-3-think-7b-dpo":[0.372,0.105,69.22],"kimi-linear-instruct":[0.37,0.082,41.89],"nvidia-nemotron-3-nano-30b-a3b-bf16":[0.356,0.096,38.33],"hypernova-60b-2602":[0.348,0.084,30.82],"qwen3-vl-32b-instruct":[0.344,0.122,76.17],"llama-3.1-405b":[0.343,0.181,69.14],"deepseek-r1-distill-llama-70b":[0.341,0.163,40.13],"qwen3-30b-a3b":[0.338,0.063,58.88],"llada2.1-flash-s":[0.334,0.114,68.36],"kat-dev-32b":[0.326,0.065,54.4],"gpt-4o-2024-08-06":[0.314,0.065,62.55],"mistral-large-instruct-2407":[0.305,0.103,67.52],"claude-3.5-sonnet-20240620":[0.302,0.072,70.39],"qwen3-8b-thinking":[0.302,0.092,53.87],"instella-moe-16b-a3b-think":[0.3,0.141,68.07],"iquest-coder-v1-14b-instruct":[0.292,0.114,47.64],"qwen3-4b":[0.289,0.096,66.96],"gemma-4-e4b-it":[0.288,0.078,49.9],"qwen3-30b-a3b-instruct-2507":[0.288,0.069,59.69],"qwen3-4b-thinking-2507":[0.279,0.094,36.2],"mistral-medium-3":[0.274,0.086,52.36],"openthinker3-7b":[0.26,0.123,72.27],"claude-3.5-haiku-20241022":[0.259,0.095,30.9],"instella-moe-16b-a3b-dpo":[0.255,0.141,67.3],"amazon-nova-premier":[0.255,0.108,28.47],"nemotron-h-47b-reasoning":[0.254,0.11,26.03],"gpt-4o-2024-05-13":[0.254,0.063,55.91],"gpt-4o-2024-11-20":[0.248,0.089,38.85],"qwen2.5-coder-32b-instruct":[0.247,0.057,55.68],"kimi-dev-72b":[0.238,0.067,52.09],"ling-flash-2.0":[0.231,0.095,72.1],"olmo-3-think-7b-sft":[0.225,0.105,65.61],"ling-2.6-1t-base":[0.224,0.14,69.34],"gpt-4o":[0.214,0.053,44.24],"olmo-hybrid-think-7b-sft":[0.21,0.122,71.83],"k2-medium-70b":[0.206,0.131,72.87],"qwen2.5-plus-1127":[0.205,0.117,75.42],"nemotron-3-nano-4b":[0.204,0.129,33.7],"instella-moe-16b-a3b-sft":[0.203,0.141,65.72],"gemini-2.0-flash-exp":[0.2,0.097,34.15],"solar-open-100b":[0.199,0.162,44.33],"deepseek-coder-v2-instruct":[0.199,0.072,61.21],"deepseek-v2.5":[0.198,0.064,61.9],"gpt-4-turbo-2024-04-09":[0.198,0.071,64.29],"youtu-llm-2b":[0.193,0.101,65.86],"kimi-k2-base":[0.187,0.08,68.15],"qwen2.5-72b-instruct":[0.182,0.064,57.38],"claude-3.5-sonnet":[0.18,0.092,77.23],"gpt-4-turbo":[0.162,0.116,71.8],"qwen3-8b":[0.16,0.065,47.19],"deepseek-r1-0528-qwen3-8b":[0.149,0.112,27.33],"exaone-4.0-1.2b":[0.148,0.133,47.6],"llama-4-maverick":[0.143,0.074,40.89],"qwen3-4b-instruct-2507":[0.142,0.083,51.33],"tri-21b-think":[0.14,0.121,61.74],"gpt-4o-mini":[0.13,0.105,74.66],"llama-3.1-405b-instruct":[0.129,0.079,56.52],"spark-x2.5-1.7b":[0.127,0.124,23.27],"rnj-1":[0.124,0.127,59.86],"gpt-4-1106-preview":[0.118,0.076,68.8],"mimo-v2.5-pro-base":[0.106,0.125,56.25],"ling-1t-base":[0.103,0.14,65.81],"qwq-32b-preview":[0.102,0.1,44.46],"qwen2.5-32b-instruct":[0.102,0.074,63.96],"deepseek-coder-v2-instruct-0724":[0.096,0.094,49.64],"kat-dev-72b-exp":[0.094,0.067,52.33],"alodlm-8b":[0.087,0.129,81.5],"deepseek-v2-chat-0628":[0.086,0.109,54.84],"ling-3.0-flash-base":[0.069,0.127,59.07],"qwen2.5-coder-14b-instruct":[0.067,0.067,53.15],"llama-3.1-70b-instruct":[0.065,0.103,59.07],"qwen3-vl-8b-instruct":[0.062,0.103,62.14],"granite-4.1-30b":[0.062,0.111,70.41],"gpt-4":[0.057,0.11,81.8],"stable-diffcoder-8b-instruct":[0.052,0.108,62.5],"qwen-turbo-0919":[0.041,0.117,70.72],"gemini-1.5-pro-002":[0.032,0.085,57.5],"claude-3-opus-20240229":[0.03,0.075,62.44],"olmo-3.1-instruct-32b":[0.028,0.103,72.44],"llama-4-scout-17b":[0.027,0.122,48.6],"falcon-h1-34b-instruct":[0.025,0.135,50.81],"qwen2.5-turbo":[0.024,0.117,70.22],"olmo-3.1-instruct-32b-dpo":[0.017,0.122,66.3],"qwen3-14b":[0.013,0.082,53.21],"lfm2.5-2.6b":[0.012,0.142,25.54],"deepseek-v2.5-1210":[0.011,0.165,37.23],"deepseek-r1-distill-qwen-7b":[0.005,0.12,46.26],"iquest-coder-v1-7b-thinking":[0.002,0.103,33.38],"gpt-4o-mini-2024-07-18":[-0.001,0.067,59.43],"gpt-4-0613":[-0.005,0.176,53],"qwen3-4b-thinking":[-0.012,0.142,31.97],"mellum2-12b-a2.5b-instruct":[-0.016,0.129,62.25],"grok-beta":[-0.016,0.099,65.86],"ling-2.6-flash-base":[-0.023,0.14,62.62],"mimo-v2.5-base":[-0.024,0.114,52.51],"k2-horizon-0.9b":[-0.024,0.14,61.77],"granite-4.0-h-small":[-0.024,0.111,68.07],"gemini-1.5-pro":[-0.027,0.079,64.38],"ministral-3-14b-instruct":[-0.027,0.129,60.17],"ling-mini-2.0":[-0.036,0.099,60.14],"hy3-preview-base":[-0.039,0.111,60.77],"ling-2.5-flash-base":[-0.044,0.127,56.08],"llama-3.3-70b-instruct":[-0.045,0.148,60.25],"nemotron-3.5-super-vl-120b-a12b-base":[-0.047,0.128,69.33],"claude-3-opus":[-0.047,0.113,75.83],"granite-3.3-8b-instruct":[-0.049,0.136,60.33],"nemotron-3-super-120b-a12b-base":[-0.051,0.105,64.15],"granite-4.1-8b":[-0.056,0.111,67.19],"qwen2.5-7b-instruct":[-0.063,0.085,58.44],"qwen3-30b-a3b-base":[-0.066,0.129,65.91],"qwen2-72b-instruct":[-0.067,0.093,67.62],"step-3.5-flash-base":[-0.075,0.093,63.43],"mimo-v2-flash-base":[-0.086,0.087,63.18],"qwen2.5-14b-instruct":[-0.101,0.097,54.89],"llada2.1-mini-q":[-0.105,0.1,60.18],"llada2.0-mini":[-0.109,0.104,59.29],"deepseek-r1-distill-llama-8b":[-0.116,0.108,51.14],"qwen3-8b-non-thinking":[-0.121,0.099,59.56],"gemma-3-27b-it":[-0.133,0.073,54.05],"mistral-small-3.2-24b-instruct":[-0.143,0.142,65.73],"gemini-1.5-flash":[-0.144,0.109,68.16],"seed-coder-8b-instruct":[-0.15,0.058,49.92],"k2-low-70b":[-0.156,0.129,64.4],"llada2.1-mini":[-0.157,0.156,55.01],"gpt-oss-20b-moe":[-0.158,0.166,52],"llada2.2-mini":[-0.158,0.155,54.14],"glm-4.5-base":[-0.158,0.098,68.84],"iquest-coder-v1-7b-instruct":[-0.165,0.106,30.08],"lfm2.5-8b-a1b":[-0.167,0.13,28.3],"llama-3.3-70b":[-0.17,0.122,64.53],"llada2.1-mini-s":[-0.171,0.1,58.6],"deepseek-v2-chat":[-0.174,0.094,56.65],"falcon-h1-7b":[-0.174,0.134,46.23],"gemini-1.5-flash-002":[-0.175,0.083,59.69],"qwen3-1.7b":[-0.179,0.092,57.76],"gpt-3.5-turbo-nov-2023":[-0.181,0.164,74.3],"deepseek-v4-flash-base":[-0.181,0.149,54.8],"stable-diffcoder-8b-base":[-0.188,0.13,73.53],"dream-coder-7b-instruct":[-0.19,0.159,66.53],"mellum2-12b-a2.5b-instruct-sft":[-0.202,0.129,53.7],"llama-3-70b-instruct":[-0.202,0.078,60.21],"gemma-4-e2b-it":[-0.208,0.119,38.7],"ling-flash-base-2.0":[-0.208,0.116,67.08],"qwen-2.5-72b":[-0.209,0.097,63.34],"glm-4.5-air-base":[-0.213,0.146,60.22],"skywork-o1-open-llama-3.1-8b":[-0.216,0.109,66.02],"llama-3.1-70b":[-0.219,0.175,68.88],"olmo-3.1-instruct-32b-sft":[-0.22,0.122,59.23],"opencodeinterpreter-ds-33b":[-0.225,0.113,75.12],"mistral-large-3-base":[-0.23,0.138,61.73],"nemotron-3-nano-4b-thinking":[-0.234,0.178,32.78],"ling-3.0-tiny-base":[-0.236,0.127,50.05],"qwen2.5-coder-7b-instruct":[-0.237,0.063,45.43],"wizardcoder-33b-v1.1":[-0.245,0.126,75.43],"yi-coder-9b-chat":[-0.253,0.072,52.76],"claude-3-haiku-mar-2024":[-0.256,0.164,72.63],"gemma-2-27b-it":[-0.259,0.086,57.99],"gpt-3.5-turbo":[-0.262,0.129,74.92],"claude-3-sonnet-mar-2024":[-0.267,0.164,72.3],"ouro-2.6b":[-0.273,0.129,74.1],"minicpm5-1b":[-0.275,0.116,41.66],"gpt-3.5-turbo-1106":[-0.278,0.113,74.08],"wedlm-8b-instruct":[-0.278,0.129,73.17],"llada2.0-flash-preview":[-0.284,0.116,55.94],"falcon-h1-3b":[-0.288,0.14,55],"deepseek-coder-33b-instruct":[-0.288,0.068,48.32],"ling-2.5-mini-base":[-0.293,0.127,48.92],"artigenz-coder-ds-6.7b":[-0.293,0.108,61.13],"seed-coder-8b-base":[-0.296,0.13,70.45],"codestral-22b":[-0.296,0.089,51.02],"codestral-22b-v0.1":[-0.297,0.072,56.23],"opencoder-8b-instruct":[-0.305,0.077,49.85],"step-3.5-flash-base-midtrain":[-0.31,0.121,65.72],"codegeex4-all-9b":[-0.312,0.114,49.22],"mistral-small-instruct-2409":[-0.314,0.14,32.9],"magicoder-s-ds-6.7b":[-0.316,0.088,57.97],"qwen2-57b-a14b-instruct":[-0.316,0.105,62.86],"opencodeinterpreter-ds-6.7b":[-0.32,0.108,60.06],"qwen2.5-coder-32b":[-0.324,0.111,61.17],"deepseek-v3-base":[-0.328,0.102,64.25],"speechless-codellama-34b-v2.0":[-0.344,0.113,71.32],"qwen2.5-7b":[-0.347,0.095,56.07],"mixtral-8x22b-instruct-v0.1":[-0.348,0.087,63.28],"granite-4.0-h-tiny":[-0.356,0.087,53.51],"deepseek-coder-7b-instruct-v1.5":[-0.361,0.113,71.12],"falcon-h1-1.5b-deep":[-0.362,0.12,55.79],"granite-4.0-h-micro":[-0.363,0.11,61.31],"deepseek-coder-33b":[-0.366,0.134,58.88],"falcon3-10b":[-0.366,0.14,52.93],"code-millenials-34b":[-0.367,0.113,71.32],"claude-3-sonnet-20240229":[-0.367,0.108,60.47],"xwincoder-34b":[-0.368,0.113,71.28],"smollm3-3b":[-0.369,0.079,48.57],"starchat2-15b-v0.1":[-0.372,0.113,71.18],"granite-4.1-3b":[-0.377,0.111,59.77],"deepseek-coder-v2-base":[-0.388,0.125,55.24],"deepseek-v2-chat-sft":[-0.389,0.11,59.22],"gemma-3-12b-it":[-0.392,0.112,50.7],"whiterabbitneo-33b-v1":[-0.393,0.108,59.51],"claude-3-haiku-20240307":[-0.393,0.086,51.66],"olmo-3-instruct-7b":[-0.395,0.083,54.19],"wavecoder-ultra-6.7b":[-0.402,0.108,58.01],"motif-2-12.7b-base":[-0.403,0.124,70.68],"llama-4-maverick-base":[-0.403,0.133,55.33],"deepseek-coder-v2-lite-instruct":[-0.404,0.06,41.58],"qwen1.5-110b-chat":[-0.408,0.111,47.85],"qwen2.5-coder-14b":[-0.416,0.109,58.84],"qwen3.5-35b-a3b-base":[-0.423,0.144,58.34],"gpt-3.5-turbo-0125":[-0.426,0.115,45.34],"granite-4.0-micro":[-0.43,0.111,59.74],"gemma-3-27b":[-0.432,0.128,56.16],"kimi-linear-base":[-0.433,0.123,53.23],"lfm2-8b-a1b":[-0.434,0.116,39.25],"deepseek-v3.1-base":[-0.437,0.116,63.72],"ouro-1.4b":[-0.445,0.129,69.38],"deepseek-coder-6.7b-instruct":[-0.446,0.07,45.16],"databricks-dbrx-instruct":[-0.454,0.113,67.64],"gpt-3.5-may-2023":[-0.454,0.126,68.73],"qwen2-7b-instruct":[-0.464,0.079,49.99],"deepseek-v3.2-exp-base":[-0.467,0.116,62.85],"qwen-2.5-3b-instruct":[-0.469,0.117,56.8],"speechless-coder-ds-6.7b":[-0.469,0.113,68.68],"wizardcoder-python-34b-v1.0":[-0.479,0.113,68.14],"qwen2.5-coder-3b-instruct":[-0.483,0.095,50.97],"diffucoder-7b-instruct":[-0.491,0.127,61.98],"olmo-hybrid-instruct-7b-dpo":[-0.491,0.124,51.33],"magicoder-s-cl-7b":[-0.496,0.113,67.36],"codestral-mamba":[-0.5,0.148,49.43],"yi-1.5-34b-chat":[-0.502,0.149,49.45],"qwen2.5-coder-7b":[-0.511,0.101,55.62],"minicpm3-4b":[-0.512,0.086,53.41],"alodlm-1.7b":[-0.531,0.129,66.47],"codestral-12b-instruct":[-0.532,0.146,48.1],"openchat-3.5-7b-0106":[-0.535,0.113,65.26],"opencoder-8b-base":[-0.544,0.133,62.83],"phind-codellama-34b-v2":[-0.545,0.104,51.8],"glm-4-9b-chat":[-0.553,0.105,60.46],"olmo-hybrid-instruct-7b-sft":[-0.556,0.122,48.6],"qwen3-8b-base":[-0.557,0.113,49.65],"qwen2-72b":[-0.56,0.106,64.42],"yi-1.5-9b-chat":[-0.564,0.148,48.73],"mistral-large":[-0.565,0.129,66],"speechless-starcoder2-15b":[-0.57,0.113,65.72],"olmo-3-instruct-7b-dpo":[-0.577,0.121,49.3],"claude-2":[-0.579,0.126,64.23],"llama-3-70b":[-0.581,0.129,56.8],"codellama-70b-instruct":[-0.599,0.09,48.86],"qwen1.5-72b-chat":[-0.599,0.084,50.47],"falcon-h1-1.5b":[-0.599,0.14,45.18],"moonlight-instruct":[-0.61,0.14,45.86],"falcon3-7b":[-0.613,0.14,48.15],"gemma-2-9b-it":[-0.614,0.074,44.14],"codeqwen1.5-7b-chat":[-0.618,0.082,46.15],"qwen2.5-32b-base":[-0.619,0.123,64.4],"mistral-large-2402":[-0.623,0.108,52.7],"phi-3.5-mini-instruct":[-0.624,0.083,44.46],"lfm2.5-1.2b-thinking":[-0.626,0.146,26.75],"gemma-3-4b-it":[-0.633,0.103,44.28],"llama-3.1-405b-base":[-0.648,0.11,53.66],"command-r-plus":[-0.651,0.095,48.14],"code-290k-6.7b-instruct":[-0.66,0.126,61.33],"deepseek-llm-67b-chat":[-0.66,0.11,50.7],"qwen1.5-32b-chat":[-0.664,0.101,44.87],"llama-3.1-8b-instruct":[-0.666,0.067,41.45],"starcoder2-15b-instruct-v0.1":[-0.674,0.087,49.51],"gemini-1.0-pro":[-0.687,0.113,62.24],"lfm2-2.6b":[-0.691,0.118,28.92],"internlm2.5-7b-chat":[-0.691,0.153,43.08],"qwen3.5-9b-base":[-0.693,0.127,38],"dolphin-2.6-mixtral-8x7b":[-0.696,0.113,61.64],"olmo-3-7b-sft":[-0.706,0.115,38.1],"phi-3-mini-4k-instruct":[-0.71,0.113,60.58],"qwen2.5-14b":[-0.713,0.119,60.26],"llama-3-8b-instruct":[-0.732,0.091,47.57],"qwen3.5-2b":[-0.735,0.076,30.14],"gemma-2-27b":[-0.741,0.102,50.92],"qwen2.5-3b":[-0.748,0.104,52.12],"qwen1.5-110b":[-0.753,0.123,58.9],"llada-moe-7b-a1b-instruct":[-0.762,0.161,50.67],"deepseek-r1-distill-qwen-1.5b":[-0.765,0.111,41.1],"dream-7b-instruct":[-0.773,0.113,51.92],"yi-1.5-6b-chat":[-0.78,0.153,42.53],"qwen2.5-coder-1.5b-instruct":[-0.808,0.091,42.57],"qwen2.57b-a14b":[-0.812,0.101,48.7],"codegemma-7b-it":[-0.814,0.108,48.23],"deepseek-coder-33b-base":[-0.817,0.098,50.21],"qwen3-0.6b":[-0.818,0.122,18.99],"qwen3.5-4b-base":[-0.825,0.122,37.61],"yi-coder-9b":[-0.829,0.144,58.47],"dream-7b-base":[-0.829,0.113,57.54],"gemma-2-2b-it":[-0.836,0.131,45.03],"codellama-70b":[-0.841,0.103,49.63],"deepseek-v2":[-0.856,0.095,48.04],"code-13b":[-0.856,0.126,53.63],"speechless-starcoder2-7b":[-0.858,0.113,56.54],"mixtral-8x22b":[-0.865,0.096,53.64],"qwen2.5-1.5b-instruct":[-0.871,0.091,34.52],"claude-instant-1-mar-2024":[-0.874,0.126,52.83],"gemma-3-12b":[-0.874,0.146,43.57],"moonlight-base":[-0.875,0.106,42.48],"wizardcoder-15b-v1.0":[-0.884,0.113,55.4],"llama-3-70b-base":[-0.889,0.096,52.99],"codeqwen1.5-7b":[-0.903,0.097,47.12],"qwen2.5-coder-3b":[-0.906,0.106,46.45],"chatglm3-6b":[-0.907,0.162,57.93],"speechless-coding-7b-16k-tora":[-0.913,0.113,54.18],"codellama-34b":[-0.914,0.102,53.44],"code-33b":[-0.914,0.126,51.23],"coda-1.7b-instruct":[-0.92,0.116,53.54],"qwen2-7b":[-0.936,0.106,52.13],"mimo-7b-base":[-0.941,0.14,44.12],"codellama-python-34b":[-0.949,0.132,51.68],"qwen2.5-1.5b":[-0.967,0.102,44.17],"starcoder2-15b":[-0.97,0.088,41.42],"fast-dllm-v2-7b":[-0.971,0.127,50.2],"llama-3.1-8b":[-0.974,0.135,54.86],"phi-2-2.7b":[-0.994,0.129,53.18],"olmo-2-0325-32b-instruct":[-1.002,0.122,34.67],"openhermes-2.5-code-290k-13b":[-1.015,0.113,50.02],"deepseek-coder-6.7b-base":[-1.017,0.093,43.91],"yi-1.5-34b":[-1.02,0.106,49.8],"llama-3.2-3b-instruct":[-1.026,0.121,15.66],"phi-3-medium-4k-instruct":[-1.037,0.115,43.86],"qwen1.5-72b":[-1.046,0.096,47.14],"wizardcoder-python-7b-v1.0":[-1.048,0.113,49.76],"mixtral-8x7b-instruct-v0.1":[-1.049,0.099,42.45],"codegemma-7b":[-1.055,0.099,42.8],"codellama-34b-instruct":[-1.059,0.092,35.25],"phi-2":[-1.061,0.101,48],"qwen1.5-32b":[-1.062,0.106,48.42],"deepseek-coder-v2-lite-base":[-1.068,0.108,43.06],"deepseek-coder-1.3b-instruct":[-1.071,0.093,36.54],"qwen3-0.8b":[-1.081,0.14,31.35],"mistral-codealpaca-7b":[-1.091,0.126,44.13],"yi-coder-1.5b-chat":[-1.093,0.098,36.41],"llama-3.2-3b-base":[-1.094,0.167,34.42],"qwen2.5-coder-1.5b":[-1.105,0.106,41.35],"codellama-13b":[-1.105,0.101,47.43],"olmo-hybrid-7b":[-1.106,0.136,40.66],"deepseek-llm-67b-base":[-1.114,0.132,46.5],"speechless-code-mistral-7b-v1.0":[-1.12,0.113,47.46],"mistralhermes-codepro-7b-v1":[-1.124,0.113,47.12],"olmo-3-7b":[-1.124,0.114,41.41],"codellama-python-13b":[-1.129,0.132,46.12],"falcon3-3b":[-1.133,0.163,34.72],"llama-3.1-8b-base":[-1.138,0.121,32.31],"apertus-70b-instruct":[-1.141,0.09,33.08],"falcon-h1-0.5b-instruct":[-1.148,0.142,28.41],"mixtral-8x7b":[-1.167,0.097,43.12],"deepseek-v2-lite-chat":[-1.168,0.109,39.1],"gemma-2-9b":[-1.18,0.095,36.22],"yi-1.5-9b":[-1.188,0.129,47.55],"codellama-python-7b":[-1.228,0.132,43.03],"codellama-7b":[-1.244,0.101,42.74],"qwen1.5-7b-chat":[-1.252,0.105,34.64],"gemma-1.1-7b-it":[-1.255,0.113,43.12],"qwen2-1.5b-instruct":[-1.265,0.117,35.48],"llama-3-8b":[-1.265,0.131,51.74],"codellama-13b-instruct":[-1.269,0.092,32.22],"apertus-8b-instruct":[-1.287,0.101,33.18],"yi-coder-1.5b":[-1.294,0.144,41.53],"map-neo-7b-instruct":[-1.301,0.129,40.82],"codet5-16b":[-1.304,0.164,43.5],"olmo-2-1124-7b-instruct":[-1.306,0.122,24.57],"llada-8b-instruct":[-1.309,0.112,37.32],"starcoderbase-16b":[-1.312,0.132,40.3],"mistral-7b-instruct-v0.2":[-1.318,0.113,40.01],"solar-10.7b-instruct-v1.0":[-1.32,0.113,39.56],"starcoder2-7b":[-1.331,0.098,35.91],"yi-1.5-6b":[-1.344,0.129,42.23],"gemma-7b":[-1.351,0.106,38.73],"xdan-l1-chat-rl-v1-7b":[-1.355,0.113,39.52],"llama-3-8b-base":[-1.355,0.106,39.78],"qwen2.5-coder-0.5b-instruct":[-1.374,0.102,30.55],"qwen1.5-7b":[-1.379,0.106,37.4],"starcoder2-3b":[-1.41,0.098,34.71],"starcoder-15b":[-1.416,0.113,38.78],"codet5-6b":[-1.424,0.164,39.6],"codellama-7b-instruct":[-1.429,0.084,26.1],"python-code-13b":[-1.433,0.126,31.3],"qwen3.5-0.8b-thinking":[-1.445,0.12,19.71],"codegen-16b":[-1.453,0.113,37.72],"map-neo-7b-sft":[-1.456,0.129,37.07],"llama-3.2-3b":[-1.463,0.129,37.73],"codet5plus-16b":[-1.465,0.113,37.8],"qwen2-1.5b":[-1.467,0.119,35.42],"stablecode-3b":[-1.468,0.101,36.87],"qwen2.5-0.5b-instruct":[-1.478,0.115,21.68],"mistral-7b-v0.1":[-1.481,0.106,35.25],"mistral-7b":[-1.5,0.103,36.53],"deepseek-coder-1.3b-base":[-1.506,0.098,31.62],"deepseek-v2-lite":[-1.527,0.129,34.5],"gemma-3-1b-it":[-1.541,0.103,22.06],"codegen-6b":[-1.547,0.113,34.84],"qwen3.5-0.8b":[-1.555,0.168,30.53],"coda-1.7b-base":[-1.559,0.113,33.84],"codet5plus-6b":[-1.562,0.113,34.5],"granite-3.3-8b-base":[-1.601,0.178,20.7],"gemma-7b-it":[-1.601,0.113,32.52],"qwen2.5-coder-0.5b":[-1.609,0.107,28.85],"codegemma-2b":[-1.624,0.113,34.08],"qwen2.5-0.5b":[-1.644,0.102,27.27],"llama-3.2-1b-instruct":[-1.648,0.115,10.53],"starcoderbase-7b":[-1.649,0.112,28.32],"marin-8b-base":[-1.651,0.136,26.56],"zephyr-7b-beta":[-1.653,0.113,30.64],"llama-3.2-1b":[-1.667,0.132,30.97],"codet5-2b":[-1.677,0.113,31.1],"llama-3.2-1.24b-base":[-1.683,0.14,20.53],"codegen-2b":[-1.689,0.113,30.38],"smollm2-1.7b-instruct":[-1.7,0.155,13.4],"olmoe-1b-7b":[-1.712,0.111,24.93],"gemma-2b":[-1.748,0.113,28.46],"qwen2-0.5b-instruct":[-1.756,0.122,23.3],"gemma-3-1b":[-1.771,0.138,23.8],"map-neo-7b":[-1.802,0.129,27.18],"apertus-8b":[-1.806,0.136,24.14],"codegen2-7b":[-1.889,0.126,17.9],"olmo-2-0425-1b-instruct":[-1.89,0.155,14.7],"qwen2-0.5b":[-1.904,0.119,23.7],"codegen2-16b":[-1.905,0.126,17.5],"gemma-1.1-2b-it":[-1.932,0.114,22.22],"starcoderbase-3b":[-1.949,0.126,16.5],"gemma-2b-it":[-1.97,0.126,16.03],"gemma-2-2b":[-2.007,0.102,21.65],"olmo-1.7-7b":[-2.009,0.129,22.58],"vicuna-13b":[-2.032,0.121,15.97],"falcon3-1b":[-2.048,0.15,12.9],"santacoder-1.1b":[-2.059,0.126,14.2],"amberchat":[-2.064,0.129,20.8],"codegen2-3b":[-2.077,0.126,13.83],"incoder-6.7b":[-2.099,0.126,13.43],"starcoderbase-1b":[-2.121,0.126,13],"llama-2-7b-chat":[-2.125,0.129,20.15],"llama-2-7b":[-2.158,0.129,19.52],"vicuna-7b":[-2.203,0.126,11.6],"gpt-j-6b":[-2.214,0.126,11.4],"incoder-1.3b":[-2.214,0.126,11.4],"olmo-7b-instruct":[-2.218,0.131,16.06],"amber-7b":[-2.23,0.13,16.73],"gemma-3-270m-it":[-2.285,0.134,7.53],"olmo-7b":[-2.285,0.129,17.4],"olmo-2-1124-7b":[-2.304,0.148,12.54],"codegen2-1b":[-2.323,0.126,9.73],"smollm2-360m-instruct":[-2.415,0.152,7.83],"pythia-6.9b":[-2.504,0.131,11.72],"gpt-neo-2.7b":[-2.536,0.126,7.1],"pythia-12b":[-2.565,0.132,10.62],"polycoder-2.7b":[-2.637,0.126,6.1],"stablelm-7b":[-3.237,0.126,2.4],"zyte-1b":[-3.416,0.114,4.66]},"benchmarks":[{"id":"livecodebench","name":"LiveCodeBench","topic":"Code generation","difficulty":0.269,"discrimination":1.748,"n":460},{"id":"humaneval-plus","name":"HumanEval+","topic":"Code generation","difficulty":-0.9,"discrimination":1.504,"n":403},{"id":"humaneval","name":"HumanEval","topic":"Code generation","difficulty":-1.072,"discrimination":1.704,"n":399},{"id":"mbpp","name":"MBPP","topic":"Code generation","difficulty":-1.405,"discrimination":1.143,"n":365},{"id":"mbpp-plus","name":"MBPP+","topic":"Code generation","difficulty":-1.084,"discrimination":0.763,"n":357},{"id":"swe-bench-verified","name":"SWE-Bench Verified","topic":"Code repair","difficulty":0.691,"discrimination":1.951,"n":254},{"id":"bigcodebench","name":"BigCodeBench","topic":"Code Generation","difficulty":0.398,"discrimination":0.519,"n":186},{"id":"evalplus","name":"EvalPlus","topic":"Code generation","difficulty":-0.895,"discrimination":1.504,"n":172},{"id":"scicode","name":"SciCode (sub)","topic":"Code","difficulty":1.416,"discrimination":0.922,"n":162},{"id":"bigcodebench-hard","name":"BigCodeBench Hard","topic":"Code generation (hard)","difficulty":1.528,"discrimination":0.873,"n":142},{"id":"crux-o","name":"CRUX-O","topic":"Code reasoning","difficulty":-0.837,"discrimination":1.148,"n":141},{"id":"swe-bench-multilingual","name":"SWE-Bench Multilingual","topic":"Code repair (multilingual)","difficulty":0.837,"discrimination":1.721,"n":139},{"id":"multipl-e","name":"MultiPL-E","topic":"Code generation (multilingual)","difficulty":-0.661,"discrimination":1.157,"n":123},{"id":"terminal-bench-2.0","name":"Terminal-Bench 2.0","topic":"Agent terminal tasks","difficulty":1.209,"discrimination":2.105,"n":116},{"id":"livecodebench-v5","name":"LiveCodeBench v5 (2024.10-2025.02)","topic":"Code generation","difficulty":0.354,"discrimination":1.779,"n":112},{"id":"crux-i","name":"CRUX-I","topic":"Code reasoning","difficulty":-0.747,"discrimination":1.1,"n":108},{"id":"bfcl-v3","name":"BFCL v3","topic":"Code reasoning","difficulty":-0.595,"discrimination":0.612,"n":103},{"id":"aider-polyglot","name":"Aider-Polyglot","topic":"Code assistant eval","difficulty":0.689,"discrimination":2.954,"n":91},{"id":"swe-bench-pro-public","name":"SWE-Bench Pro (Public)","topic":"Software engineering","difficulty":1.283,"discrimination":1.419,"n":90},{"id":"terminal-bench","name":"Terminal-Bench","topic":"Agent terminal tasks","difficulty":1.216,"discrimination":2.164,"n":85},{"id":"ojbench","name":"OJBench","topic":"Code generation (online judge)","difficulty":1.278,"discrimination":1.704,"n":66},{"id":"fullstackbench","name":"FullStackBench","topic":"Full-stack development","difficulty":-0.032,"discrimination":0.619,"n":54},{"id":"artifactsbench","name":"ArtifactsBench","topic":"Agentic coding","difficulty":0.732,"discrimination":0.905,"n":51},{"id":"aider-code-editing","name":"Aider Code Editing","topic":"Code editing","difficulty":-0.247,"discrimination":1.751,"n":51},{"id":"livecodebench-v3","name":"LiveCodeBench v3","topic":"Code generation","difficulty":-0.04,"discrimination":2.251,"n":45},{"id":"swe-bench","name":"SWE-Bench","topic":"Code repair","difficulty":0.923,"discrimination":1.767,"n":41},{"id":"autocodebench-lite","name":"AutoCodeBench-Lite","topic":"Autonomous coding","difficulty":0.616,"discrimination":1.318,"n":39},{"id":"autocodebench","name":"AutoCodeBench","topic":"Autonomous coding","difficulty":0.946,"discrimination":0.951,"n":36},{"id":"roo-code-evals","name":"Roo Code Evals","topic":"Code assistant eval","difficulty":-0.115,"discrimination":2.511,"n":33},{"id":"multi-swe-bench","name":"Multi-SWE-Bench","topic":"Code repair (multi-repo)","difficulty":1.507,"discrimination":1.481,"n":32},{"id":"scicode-main","name":"SciCode (main)","topic":"Code","difficulty":1.532,"discrimination":2.444,"n":30},{"id":"gso-benchmark","name":"GSO Benchmark","topic":"Code generation","difficulty":2.009,"discrimination":2.558,"n":29},{"id":"evalperf","name":"EvalPerf","topic":"Code evaluation performance","difficulty":-0.159,"discrimination":2.203,"n":28},{"id":"multipl-e-mbpp","name":"MultiPL-E MBPP","topic":"Code generation (multilingual)","difficulty":-0.342,"discrimination":0.665,"n":22},{"id":"multipl-e-humaneval","name":"MultiPL-E HumanEval","topic":"Code generation (multilingual)","difficulty":-0.35,"discrimination":1.149,"n":22},{"id":"bfcl","name":"BFCL","topic":"Code reasoning","difficulty":-4.261,"discrimination":0.24,"n":21},{"id":"astabench","name":"AstaBench","topic":"Agent evaluation","difficulty":1.652,"discrimination":1.408,"n":20},{"id":"repobench","name":"RepoBench","topic":"Code understanding","difficulty":0.62,"discrimination":1.12,"n":12}]},"faix-math":{"sd":0.384,"ext":{"gpt-5.2-thinking-xhigh":[2.333,0.096,91.35],"gemini-3.1-pro":[2.33,0.144,80.78],"seed2.1-pro":[2.318,0.139,81.23],"claude-opus-4.5-thinking":[2.265,0.097,88.97],"gpt-5.5":[2.247,0.111,87.98],"gemini-3-pro":[2.226,0.081,81.47],"gpt-5.2-high":[2.204,0.111,73.57],"claude-opus-4.6":[2.156,0.129,83.73],"seed2.0-pro":[2.081,0.118,91.2],"seed2.1-turbo":[2.069,0.169,85.18],"qwen3.8-27b":[1.859,0.108,93.04],"gpt-5.2":[1.835,0.141,82.4],"gemini-3-flash":[1.765,0.119,89.27],"qwen3.6-plus":[1.755,0.122,87.14],"kimi-k2.5":[1.719,0.117,80.43],"gpt-5-thinking":[1.695,0.099,79.7],"kimi-k2.5-thinking":[1.669,0.119,82.72],"qwen3.5-397b-a17b":[1.657,0.128,83.11],"gpt-5-high":[1.649,0.073,80.94],"step3-vl-10b-pacore":[1.632,0.095,87],"gpt-5":[1.632,0.077,78.11],"qwen3.5-122b-a10b":[1.601,0.12,84.28],"grok-4-fast":[1.586,0.097,92.07],"seed2.0-lite":[1.583,0.118,85.13],"seed1.8":[1.563,0.087,79.13],"ternary-bonsai-2-27b":[1.55,0.113,96.82],"grok-4":[1.531,0.09,73.06],"claude-opus-4.5":[1.523,0.097,71.43],"qwen3.5-35b-a3b":[1.508,0.12,82.28],"nemotron-3-nano-30b-a3b":[1.491,0.139,87.07],"claude-opus-4.7":[1.49,0.169,77.4],"qwen3.8-27b-ud-q4-k-xl":[1.488,0.113,96.32],"qwen3.6-27b":[1.458,0.119,86.13],"exaone-4.5-33b-thinking":[1.444,0.123,83.05],"qwen3.5-27b":[1.435,0.105,85.67],"claude-sonnet-4.5":[1.428,0.102,80.01],"qwen3-235b-a22b-thinking-2507":[1.416,0.087,72.24],"gemini-2.5-pro":[1.411,0.063,72.56],"deepseek-v3.1-terminus":[1.407,0.097,80.19],"gpt-oss-120b":[1.406,0.073,77.99],"sarvam-105b":[1.375,0.108,85.33],"qwen-3-235b-a22b-thinking":[1.371,0.091,83.84],"qwen3-vl-235b-a22b-thinking":[1.366,0.118,82.83],"o3":[1.354,0.083,73.61],"gpt-5-mini-high":[1.348,0.111,76.88],"o3-high":[1.344,0.079,80.34],"deepseek-v3.2":[1.333,0.077,90.4],"ernie-5.0":[1.31,0.095,81.94],"qwen3-30b-a3b-thinking-2507":[1.294,0.08,78.78],"qwen3-next-80b-a3b-thinking":[1.294,0.081,75.37],"intellect-3":[1.291,0.092,92.3],"minicpm-v-4.7-35b-a3b":[1.291,0.243,82.9],"deepseek-r1-0528":[1.29,0.092,92.3],"deepseek-v3.1-thinking":[1.274,0.09,71.59],"deepseek-v3.2-exp":[1.262,0.096,81.62],"step3-vl-10b-sere":[1.259,0.095,80.16],"gpt-5-mini":[1.258,0.097,80.52],"glm-4.7-flash":[1.241,0.106,82.62],"o4-mini":[1.22,0.096,81.83],"zdtaichu5.0-9b":[1.215,0.126,80.88],"glm-4.5-air":[1.214,0.069,85.09],"superapriel-15b-instruct":[1.208,0.096,91.03],"step3-vl-10b":[1.205,0.118,79.01],"sarvam-30b":[1.204,0.108,81.2],"qwen3.6-35b-a3b":[1.2,0.102,85.9],"openreasoning-nemotron-32b":[1.19,0.082,82.33],"qwen3.5-omni-plus":[1.183,0.247,80.97],"qwen3-vl-235b-a22b":[1.164,0.09,79.2],"gemma-4-26b-a4b-it":[1.163,0.112,86.19],"dots-vlm1":[1.158,0.13,80.16],"ministral-3-14b-reasoning":[1.152,0.097,87.1],"apriel-1.6-15b-thinker":[1.149,0.131,76.25],"openreasoning-nemotron-14b":[1.138,0.082,80.33],"nemotron-32b":[1.129,0.079,73.99],"falcon-h1r-7b":[1.124,0.077,83.38],"k2-high-70b":[1.121,0.091,85.22],"qwen3-vl-32b-thinking":[1.106,0.082,77.31],"motif-2-12.7b-reasoning":[1.102,0.085,91.64],"k2-think-v2":[1.101,0.088,85.83],"qwen3.5-9b":[1.096,0.089,82.06],"qwen3-235b-a22b":[1.095,0.07,75.52],"apriel-1.5-15b-thinker":[1.095,0.075,76.48],"qwen3-vl-30b-a3b-thinking":[1.093,0.096,67.47],"gpt-oss-20b":[1.092,0.086,70.79],"glm-4.5":[1.085,0.09,76.78],"k2-think":[1.084,0.079,72.79],"gemma-4-31b-it":[1.079,0.098,84.06],"claude-4.5-haiku":[1.055,0.119,80.7],"qwen3-30b-a3b":[1.05,0.07,75.34],"minimax-m1-80k":[1.038,0.092,86.57],"seed-thinking-v1.5":[1.019,0.092,85.8],"qwen3-4b-thinking-2507":[1.014,0.098,70.03],"openreasoning-nemotron-7b":[1.009,0.075,72.84],"olmo-3.1-think-32b":[1.003,0.076,78.63],"qwen3-vl-8b-thinking":[0.999,0.083,74.11],"qwen3-14b-thinking":[0.998,0.092,84.87],"o3-mini":[0.992,0.093,86.07],"minimax-m2":[0.982,0.087,80.62],"qwen3-32b-thinking":[0.977,0.069,71.2],"nvidia-nemotron-nano-9b-v2":[0.968,0.082,77.72],"gemini-2.5-flash-thinking":[0.968,0.08,69.54],"deepseek-r1-0528-qwen3-8b":[0.967,0.077,77.56],"minimax-m1-40k":[0.961,0.092,84.63],"zgcm-1-7b":[0.959,0.092,83.69],"gpt-oss-120b-medium":[0.959,0.09,76.27],"claude-opus-4.1":[0.958,0.125,72.67],"qwen3.5-4b":[0.954,0.088,77.4],"minicpm4.1-8b":[0.941,0.092,84.09],"qwen3-next-80b-a3b-instruct":[0.932,0.076,69.77],"gemma-4-12b-it":[0.928,0.113,82.77],"olmo-3-think-32b-dpo":[0.915,0.072,76.32],"o1":[0.912,0.091,80.3],"olmo-3-think-32b":[0.908,0.081,78.82],"o3-mini-medium":[0.906,0.082,69.13],"o1-2024-12-17":[0.906,0.096,80.4],"qwen3-32b":[0.904,0.067,77.76],"vibethinker-1.5b":[0.895,0.082,68.37],"instella-moe-16b-a3b-dpo":[0.893,0.092,81.85],"glm-4.6v":[0.889,0.089,67.85],"instella-moe-16b-a3b-think":[0.887,0.092,81.7],"qwen3.5-omni-flash":[0.883,0.246,75.87],"deepseek-r1":[0.879,0.071,63.09],"gpt-oss-20b-medium":[0.879,0.092,82.58],"qwq-32b":[0.875,0.075,72.73],"instella-moe-16b-a3b-sft":[0.874,0.092,81.17],"claude-3.7-sonnet":[0.871,0.125,77],"qwen3-omni-30b-a3b-thinking":[0.869,0.131,66.93],"qwen3-8b-thinking":[0.868,0.082,76.52],"motif-2-12.7b-instruct":[0.857,0.083,85.17],"gemini-2.5-flash":[0.855,0.075,67.05],"ovis2.6-30b-a3b":[0.853,0.214,71.12],"ernie-4.5-vl-28b-a3b-thinking":[0.845,0.24,75.13],"joyai-llm-flash":[0.844,0.111,86.25],"olmo-3-think-32b-sft":[0.843,0.072,73.83],"qwen3-vl-32b-instruct":[0.842,0.084,71.81],"phi-4-reasoning-plus":[0.841,0.077,72.88],"claude-opus-4":[0.84,0.083,58.87],"qwen3-vl-30b-a3b-instruct":[0.836,0.086,67.09],"olmo-3-think-7b-dpo":[0.835,0.088,69.44],"telechat3-36b-thinking":[0.832,0.092,80.53],"qwen3-30b-a3b-instruct-2507":[0.826,0.063,77.91],"deepseek-r1-0120":[0.818,0.082,63.83],"olmo-3-think-7b-sft":[0.815,0.088,69.79],"qwen3-vl-4b-thinking":[0.813,0.099,74.12],"olmo-3-think-7b":[0.802,0.077,78.9],"longcat-flash-lite":[0.801,0.092,77.41],"lg-exaone-32b":[0.8,0.087,81.82],"seed-1.5-vl":[0.775,0.091,67.53],"glm-4.5v":[0.774,0.177,69.52],"kimi-k2-instruct":[0.757,0.072,64.46],"phi-4-reasoning":[0.754,0.082,60.5],"acereason-nemotron-1.1":[0.745,0.082,60.1],"k2-medium-70b":[0.744,0.092,72.55],"apriel-nemotron-15b-thinker":[0.739,0.087,79.97],"llada2.0-flash":[0.734,0.083,80.36],"magistral-small-2506":[0.726,0.082,59],"mimo-7b-rl":[0.724,0.082,58.9],"ovis2.6-80b-a3b":[0.724,0.217,67.35],"telechat3-105b-a4.7b-thinking":[0.721,0.092,77.27],"kimi-linear-instruct":[0.72,0.077,67.3],"llada2.1-flash-q":[0.717,0.094,76.07],"ling-flash-2.0":[0.713,0.084,80.41],"qwen3-8b":[0.711,0.072,69.36],"llada2.1-flash-s":[0.701,0.094,75.45],"openthinker3-7b":[0.698,0.088,64.45],"qwen3-14b":[0.692,0.086,83.84],"questa-nemotron-1.5b":[0.689,0.074,61.7],"nemotron-research-goosereason-4b-instruct":[0.685,0.074,73.83],"deepseek-r1-distill-qwen-32b":[0.68,0.088,64.52],"seed1.5-vl-thinking":[0.669,0.25,70.66],"kimi-k2-0905":[0.667,0.097,52.84],"qwen3-4b":[0.658,0.074,77.43],"llama-3.1-nemotron-nano-8b-v1":[0.656,0.086,74.9],"olmo-hybrid-think-7b-sft":[0.654,0.088,62.57],"skywork-or1-7b":[0.617,0.082,52.27],"olmo-3.1-instruct-32b":[0.616,0.083,72.3],"o1-mini":[0.615,0.085,75.22],"qwen3-omni-30b-a3b-instruct":[0.607,0.118,60.1],"granite-4.1-30b":[0.605,0.14,82.13],"gemini-2.5-flash-lite":[0.596,0.085,64.58],"youtu-llm-2b":[0.591,0.092,69.63],"deepseek-r1-distill-32b":[0.585,0.074,55.6],"gpt-5-nano":[0.574,0.187,67.4],"nemotron-h-47b-reasoning":[0.569,0.077,60.4],"ling-mini-2.0":[0.567,0.078,64.69],"deepseek-v3-0324":[0.553,0.074,63.13],"ernie-4.5":[0.532,0.09,75.92],"claude-sonnet-4":[0.524,0.079,56.92],"marco-mini-instruct":[0.519,0.145,79.25],"granite-4.1-8b":[0.518,0.135,83.75],"grok-3":[0.517,0.099,65.61],"nemotron-1.5b":[0.517,0.074,51.86],"qwen3-vl-8b-instruct":[0.51,0.071,56.12],"qwen3-4b-instruct-2507":[0.468,0.062,61.62],"k2-v2":[0.464,0.111,76.93],"step-3":[0.464,0.191,63.32],"gemini-2.0-pro":[0.462,0.111,73.64],"deepseek-v3":[0.462,0.081,67.3],"glm-4.1v":[0.456,0.194,61.96],"gemma-4-e4b-it":[0.453,0.076,65.28],"claude-3.7-sonnet-thinking":[0.437,0.242,72.64],"qwen3-vl-4b-instruct":[0.433,0.083,55.24],"llada2.1-mini-q":[0.433,0.094,67.03],"openreasoning-nemotron-1.5b":[0.419,0.077,58.54],"gemma-3-27b":[0.406,0.107,84.44],"llada2.0-mini":[0.404,0.094,65.66],"gemini-2.0-flash":[0.385,0.132,65.23],"gpt-4.1":[0.383,0.07,65.96],"llada2.1-mini-s":[0.377,0.094,64.84],"deepseek-r1-distill-qwen-7b":[0.373,0.087,57.99],"smollm3-3b":[0.351,0.069,64.65],"glm-4.6v-flash":[0.329,0.216,60.15],"deepseek-r1-distill-llama-8b":[0.329,0.091,62.47],"openpangu-vl-7b":[0.307,0.117,66.97],"qwen3.8-27b-iq2-xxs":[0.302,0.136,80.39],"k2-low-70b":[0.266,0.091,55.92],"o1-preview":[0.26,0.103,71.87],"gpt-4.5":[0.251,0.125,60.33],"olmo-3-instruct-7b":[0.241,0.079,62.79],"mistral-3.2-24b":[0.24,0.156,88.86],"nemotron-3-super-120b-a12b-base":[0.239,0.095,75.1],"nemotron-3.5-super-vl-120b-a12b-base":[0.225,0.145,87.12],"nemotron-3-nano-30b-a3b-base":[0.224,0.118,85.08],"gemma-4-e2b-it":[0.213,0.078,55.18],"gemma-3-27b-it":[0.205,0.073,59.47],"minicpm-v-4.6-thinking":[0.205,0.226,62.33],"lfm2.5-1.2b-thinking":[0.184,0.113,68.83],"mobilellm-r1.5-950m":[0.18,0.09,60.05],"olmo-3.1-instruct-32b-dpo":[0.178,0.088,44.6],"qwen2.5-14b-instruct":[0.161,0.157,85.69],"qwen3-1.7b":[0.134,0.062,50.76],"qwen3-8b-non-thinking":[0.126,0.077,46.03],"gpt-5-minimal":[0.125,0.129,47.4],"qwen2.5-math-72b-instruct":[0.122,0.077,67.03],"ling-2.6-1t-base":[0.107,0.124,66.8],"qwen3-1.7b-thinking":[0.105,0.107,57.25],"gemma-3-12b":[0.103,0.138,69.77],"kimi-vl-a3b-thinking-2506":[0.083,0.196,52.34],"nemotron-3-ultra-base":[0.08,0.157,85.94],"deepseek-v3.1":[0.076,0.118,61.89],"mistral-medium-3":[0.076,0.094,46.33],"kimi-vl-a3b-thinking":[0.072,0.236,59.3],"ministral-3-8b-instruct":[0.065,0.152,68.05],"deepseek-r1-distill-qwen-1.5b":[0.06,0.083,59.78],"qwen3.5-35b-a3b-base":[0.057,0.134,77.21],"minicpm-o-4.5":[0.056,0.164,83.87],"mistral-large-instruct-2407":[0.056,0.157,85],"ling-3.0-flash-base":[0.052,0.125,58.18],"qwen3-32b-nothinking":[0.047,0.075,34.42],"gemma-3-12b-it":[0.043,0.072,58.21],"granite-4.1-3b":[0.04,0.144,72.36],"keye-vl-8b":[0.035,0.234,47.67],"llama-4-maverick":[0.028,0.136,61.8],"claude-3.5-sonnet-20240620":[0.027,0.176,79.37],"qwen2.5-72b-instruct":[0.015,0.075,65.22],"mistral-small-3.1-24b-instruct":[0.007,0.135,77.68],"llada2.0-flash-preview":[0.002,0.093,58.4],"lfm2-350m-math":[-0.007,0.084,48.75],"ling-2.6-flash-base":[-0.01,0.124,63.66],"gemini-1.5-flash":[-0.011,0.128,68.71],"olmo-3-instruct-7b-dpo":[-0.013,0.088,36.58],"qwen3-8b-instruct":[-0.018,0.132,82.33],"qwen2.5-vl-72b-instruct":[-0.018,0.236,56.83],"lfm2-24b-a2b":[-0.028,0.148,67.05],"ling-1t-base":[-0.028,0.124,64.02],"kimi-k2-base":[-0.028,0.137,85.17],"llama-4-scout-17b":[-0.029,0.085,62.97],"qwen2-math-72b-instruct":[-0.037,0.077,62.37],"gpt-5-nano-minimal":[-0.039,0.129,32.02],"qwen2.5-32b-instruct":[-0.048,0.073,58.45],"gpt-4o-mini":[-0.05,0.154,75.79],"falcon-h1-34b-instruct":[-0.063,0.081,55.44],"deepseek-v4-flash-base":[-0.069,0.122,81.64],"nemotron-3.5-lightning-30b-a3b":[-0.069,0.185,79.17],"gpt-4o-2024-08-06":[-0.069,0.092,63.78],"nemotron-labs-twotower-30b-a3b-base":[-0.069,0.156,83.71],"qwen2.5-math-7b-instruct":[-0.079,0.077,61.21],"hunyuan-large":[-0.083,0.144,84.63],"llama-3.1-405b-instruct":[-0.084,0.101,66.92],"minicpm-v-4.6":[-0.085,0.191,54.23],"hy3-preview-base":[-0.086,0.103,66.34],"internvl3.5-8b":[-0.086,0.189,67.89],"marco-nano-instruct":[-0.088,0.145,68.1],"qwen2.5-coder-32b-instruct":[-0.09,0.084,57.38],"gemini-1.5-pro":[-0.105,0.087,53.58],"joyai-llm-flash-base":[-0.106,0.132,81.31],"claude-3.5-sonnet":[-0.106,0.103,64.7],"apertus-v1.5-70b-thinking":[-0.11,0.083,53.72],"qwen-2.5-72b":[-0.122,0.08,60.2],"deepseek-v4-pro-base":[-0.128,0.137,83.1],"lfm2-8b-a1b":[-0.131,0.089,60.81],"minicpm-v-4.7-1b":[-0.134,0.239,55.45],"ling-2.5-flash-base":[-0.135,0.125,49.84],"ling-flash-base-2.0":[-0.151,0.104,65.77],"gemma-3-4b":[-0.152,0.14,52.33],"deepseek-v2.5":[-0.153,0.1,65.33],"skywork-o1-open-llama-3.1-8b":[-0.155,0.084,56.22],"apertus-v1.5-8b-thinking":[-0.158,0.085,52.22],"qwen2-72b-instruct":[-0.166,0.097,67.63],"wedlm-8b-instruct":[-0.167,0.134,78.63],"claude-3.5-sonnet-20241022":[-0.176,0.094,60.73],"granite-4.0-h-small":[-0.18,0.105,57.99],"deepseek-v3.2-base":[-0.183,0.137,81.38],"deepseek-coder-v2-instruct":[-0.192,0.086,54.84],"qwen2-math-7b-instruct":[-0.203,0.076,57.66],"qwen2.5-math-72b":[-0.204,0.144,82.43],"qwen3-30b-a3b-base":[-0.214,0.132,77.52],"deepseek-v3.2-exp-base":[-0.231,0.157,78.64],"gpt-4o":[-0.233,0.091,60.28],"deepseek-v4.1-flash-base":[-0.237,0.16,78.1],"granite-4.0-h-micro":[-0.237,0.157,56.55],"deepseek-v3-base":[-0.253,0.137,80.61],"qwen3-6b":[-0.256,0.084,38.92],"glm-4.5-base":[-0.257,0.137,80.81],"gpt-4":[-0.258,0.106,61.48],"falcon-h1-7b":[-0.258,0.081,48.35],"gpt-4-turbo-2024-04-09":[-0.262,0.11,65.52],"llama-3.3-70b-instruct":[-0.264,0.138,76.6],"mistral-large-3-base":[-0.265,0.124,72.25],"internvl3.5-4b":[-0.266,0.191,52.75],"gemma-3-4b-it":[-0.271,0.076,58.17],"mobilellm-r1-950m":[-0.273,0.078,47.92],"qwen2.5-coder-14b-instruct":[-0.279,0.086,52.22],"falcon-h1-1.5b-deep":[-0.284,0.081,48.42],"qwen2.5-math-1.5b-instruct":[-0.285,0.076,55.4],"gpt-4o-2024-05-13":[-0.292,0.082,57.36],"falcon-h1-3b":[-0.295,0.081,47.96],"internlm2-math-plus-mixtral8x22b":[-0.302,0.168,62.4],"mimo-v2.5-base":[-0.305,0.102,56.62],"gpt-5-mini-minimal":[-0.305,0.236,47.57],"llama-3.1-70b-instruct":[-0.316,0.099,64.17],"step-3.5-flash-base":[-0.318,0.102,56.12],"mistral-small-3.2-24b-instruct":[-0.325,0.143,68.64],"olmo-hybrid-instruct-7b-dpo":[-0.325,0.088,28.18],"olmo-3.1-instruct-32b-sft":[-0.333,0.088,27.7],"kanana-1.5-o-9.8b-instruct-2602":[-0.333,0.244,50.79],"qwen2.5-7b-instruct":[-0.337,0.071,43.81],"gpt-4o-mini-2024-07-18":[-0.354,0.133,51.66],"lfm2.5-1.2b-instruct":[-0.363,0.115,47.24],"qwen3-0.6b":[-0.368,0.077,33.06],"qwen2-math-72b":[-0.373,0.144,78.67],"qwen3-8b-base":[-0.375,0.127,60.17],"qwen3-vl-2b-instruct":[-0.375,0.131,57.21],"qwen3.5-2b":[-0.38,0.085,52.54],"ling-3.0-tiny-base":[-0.392,0.125,40.4],"ling-2.5-mini-base":[-0.394,0.125,40.51],"llama-3.3-70b":[-0.404,0.093,52.69],"numinamath-72b-cot":[-0.409,0.083,51.17],"qwen2.5-7b":[-0.413,0.073,45.65],"falcon-h1-1.5b":[-0.415,0.081,42.68],"qvq-72b":[-0.418,0.147,42.57],"qwen2.5-math-7b":[-0.422,0.147,77.33],"lfm2-2.6b":[-0.442,0.1,58.18],"qwen2.5-omni-7b":[-0.447,0.193,55.7],"kimi-linear-base":[-0.456,0.144,76.77],"claude-3-opus-20240229":[-0.458,0.113,63.35],"olmo-hybrid-instruct-7b-sft":[-0.459,0.088,24.55],"qwen2.5-coder-7b-instruct":[-0.461,0.081,39.3],"deepseek-coder-v2-lite-instruct":[-0.478,0.076,48.87],"qwen2-math-1.5b-instruct":[-0.482,0.083,49.54],"qwen2-72b":[-0.483,0.144,75.33],"gemini-1.0-ultra":[-0.489,0.178,66.87],"falcon3-10b":[-0.496,0.081,42.93],"glm-4.5-air-base":[-0.5,0.113,64.04],"ministral-3-3b-instruct":[-0.501,0.177,56.33],"gemma-3-27b-vl":[-0.504,0.194,40.9],"olmo-3-7b-sft":[-0.505,0.088,23.35],"claude-3-opus":[-0.508,0.106,55.02],"granite-3.3-8b-instruct":[-0.508,0.079,40.39],"deepseek-v2-chat-sft":[-0.514,0.148,75.17],"gemma-2-9b-it":[-0.518,0.157,71.39],"falcon3-7b":[-0.527,0.081,41.01],"granite-4.0-h-tiny":[-0.543,0.081,51.45],"internlm2-math-plus-20b":[-0.549,0.099,51.93],"apertus-v1.5-70b":[-0.551,0.132,67.3],"deepseek-math-7b-rl":[-0.554,0.099,53.8],"qwen3.5-9b-base":[-0.568,0.125,33.34],"moonlight-base":[-0.571,0.126,63.38],"kanana-2-3b-instruct":[-0.58,0.131,48.94],"gpt-4-1106-preview":[-0.593,0.129,54.43],"qwen3.5-4b-base":[-0.595,0.108,44.04],"qwen2-57b-a14b-instruct":[-0.596,0.157,69.47],"llama-3.1-405b-base":[-0.605,0.138,72.5],"qwen2.5-coder-3b-instruct":[-0.608,0.086,38.82],"internvl2.5-78b":[-0.62,0.14,41.95],"internvl2.5-38b":[-0.62,0.14,41.3],"kanana-2-1.3b-instruct":[-0.622,0.131,47.37],"mathstral-7b":[-0.624,0.09,49.72],"internlm2-math-plus-7b":[-0.627,0.099,50.4],"qwen2-7b-instruct":[-0.632,0.097,53.32],"glm-4-9b-chat":[-0.636,0.157,67.23],"qwen2.5-vl-7b":[-0.639,0.194,37.58],"deepseek-math-7b-instruct":[-0.641,0.144,71.43],"granite-4.0-micro":[-0.645,0.139,44.33],"glm4-9b":[-0.648,0.13,56.73],"kimi-vl-a3b-instruct":[-0.651,0.236,43.4],"qwen2-math-7b":[-0.653,0.144,71.33],"ouro-1.4b":[-0.653,0.18,61.24],"mobilellm-r1.5-360m":[-0.655,0.099,32.73],"qwen1.5-72b-chat":[-0.657,0.137,71.23],"mixtral-8x22b-instruct-v0.1":[-0.659,0.147,71.33],"gpt-4v":[-0.662,0.14,33.23],"llava-onevision-72b":[-0.663,0.225,47.28],"deepseek-v2-chat":[-0.672,0.094,57.78],"llama-3.1-8b":[-0.678,0.156,68.77],"moonlight-instruct":[-0.681,0.084,32.5],"qwen2-7b":[-0.689,0.118,62.23],"numinamath-7b-cot":[-0.693,0.099,49.56],"gemma-2-27b":[-0.693,0.13,50.5],"qwen2.5-3b":[-0.694,0.074,44.14],"qwen2-vl-72b":[-0.696,0.142,40.67],"qwen2.5-math-1.5b":[-0.701,0.144,69.87],"hyperclovax-seed-omni-8b":[-0.713,0.204,47.13],"qwen2-vl-72b-instruct":[-0.735,0.147,35.87],"eurollm-22b":[-0.738,0.126,63.52],"qwen2.5-vl-3b":[-0.741,0.258,48.67],"olmo-2-32b-base":[-0.744,0.156,58.7],"qwen1.5-32b-chat":[-0.758,0.157,64.07],"internvl3-8b":[-0.762,0.234,28.43],"gpt-4-turbo":[-0.763,0.128,40.69],"minicpm-o-2.6":[-0.763,0.203,38.99],"internvl2.5-26b":[-0.77,0.11,46.05],"llama-3-70b-instruct":[-0.77,0.106,56.52],"llama-3.1-8b-instruct":[-0.771,0.067,39.51],"llama-3.1-70b-base":[-0.778,0.144,67.53],"falcon-h1-0.5b-instruct":[-0.781,0.081,33.61],"gemma-2-27b-it":[-0.792,0.097,31.9],"mixtral-8x22b":[-0.793,0.149,67.73],"qwen1.5-72b":[-0.803,0.144,67],"deepseek-v2":[-0.808,0.137,66.88],"llama-3-70b-base":[-0.819,0.144,66.47],"apertus-v1.5-8b":[-0.838,0.132,56.97],"olmo-3-7b":[-0.842,0.129,44.85],"deepseek-llm-67b-chat":[-0.843,0.144,65.67],"granite-3.3-2b-instruct":[-0.846,0.11,44.62],"qwen2-math-1.5b":[-0.854,0.144,65.1],"llama-3-8b":[-0.862,0.135,47.8],"granite-4.0-1b":[-0.864,0.111,40.52],"falcon3-3b":[-0.868,0.081,32.96],"deepseek-math-7b":[-0.872,0.117,50.6],"olmo-2-0325-32b-instruct":[-0.874,0.097,16.12],"apertus-70b":[-0.892,0.128,52.99],"granite-3.2-8b-instruct":[-0.894,0.11,45.63],"minicpm-v-2_6":[-0.896,0.237,36.57],"dream-7b-instruct":[-0.906,0.132,54.4],"mobilemoe-l":[-0.927,0.145,55.3],"gemma-2-9b":[-0.931,0.101,36.94],"gpt-3.5":[-0.94,0.144,62.9],"llama-3.1-70b":[-0.942,0.13,55.95],"internvl2-llama-3-76b":[-0.951,0.136,38.28],"internvl2.5-8b":[-0.957,0.112,42.7],"deepseek-coder-v2-lite-base":[-0.959,0.144,61.7],"granite-3.1-8b-instruct":[-0.984,0.11,43.28],"qwen2.5-1.5b-instruct":[-0.993,0.087,37.16],"llama-3.2-3b":[-0.997,0.117,43.8],"qwen2-vl-7b":[-0.998,0.217,37.12],"gemini-pro":[-1.001,0.155,45.64],"internlm2-20b":[-1.003,0.167,44.72],"qwen3-0.8b":[-1.017,0.083,22.97],"marin-8b-instruct":[-1.025,0.132,50.23],"llama-3.2-3b-base":[-1.026,0.094,30.6],"aquila-vl-2b":[-1.034,0.236,34.53],"metamath-70b":[-1.051,0.145,59.93],"internlm2-math-plus-1.8b":[-1.06,0.172,44.9],"mixtral-8x7b":[-1.061,0.167,42.87],"qwen2.5-1.5b":[-1.064,0.074,26.95],"claude-3.5-haiku-20241022":[-1.066,0.135,59.69],"llama-3-8b-instruct":[-1.07,0.157,54.53],"llama3.0-70b":[-1.071,0.112,41.73],"internvl2-8b":[-1.116,0.122,38.63],"llama-3.1-8b-base":[-1.121,0.078,31.61],"qwen3.5-0.8b-thinking":[-1.13,0.109,38.16],"skywork-13b-math":[-1.143,0.158,55.53],"granite-4.0-h-1b":[-1.144,0.111,39.27],"llama-3.2-3b-instruct":[-1.146,0.1,43.99],"internvl2-26b":[-1.161,0.108,38.21],"internlm2-math-base-20b":[-1.177,0.143,48.5],"wizardmath-70b-v1.0":[-1.185,0.148,56.57],"internvl2-40b":[-1.188,0.136,32.52],"eurollm-9b-instruct-2512":[-1.195,0.132,43.07],"gemma-3-1b-it":[-1.209,0.076,31.24],"mobilemoe-m":[-1.218,0.145,45.67],"apertus-70b-instruct":[-1.249,0.079,25.37],"internvl2.5-4b":[-1.255,0.14,30.38],"olmo-2-1124-7b-instruct":[-1.261,0.088,9.25],"deepseek-v2-lite-chat":[-1.272,0.084,34.42],"granite-3.2-2b-instruct":[-1.286,0.11,34.48],"granite-3.1-2b-instruct":[-1.287,0.11,34.5],"deepseek-coder-7b-base-v1.5":[-1.287,0.167,38.6],"phi-3.5-vision-instruct":[-1.291,0.236,27.83],"internlm2-7b":[-1.308,0.167,37.7],"qwen2.5-0.5b-instruct":[-1.312,0.082,23.12],"qwen3.5-0.8b":[-1.345,0.117,37.33],"llama-3.2-1b-instruct":[-1.366,0.09,16.32],"mobilellm-r1-360m":[-1.369,0.141,26.5],"lfm2.5-vl-1.6b":[-1.373,0.191,28.75],"qwen2-1.5b-instruct":[-1.397,0.099,32.9],"apertus-8b-instruct":[-1.403,0.079,18.32],"llama-3.2-1.24b":[-1.411,0.112,22.68],"deepseek-llm-67b-base":[-1.412,0.144,48.37],"qwen1.5-7b-chat":[-1.413,0.161,41.03],"olmo-2-0425-1b-instruct":[-1.415,0.078,22.32],"qwen2.5-0.5b":[-1.418,0.074,15.17],"codellama-34b":[-1.419,0.167,33.83],"deepseek-llm-7b-chat":[-1.42,0.144,49.07],"qwen2-1.5b":[-1.422,0.144,46.16],"qwen2-vl-2b":[-1.423,0.236,27.07],"llemma-34b":[-1.439,0.143,40.3],"deepseek-moe-16b-chat":[-1.443,0.144,48.43],"smollm2-1.7b-instruct":[-1.458,0.08,18.93],"deepseek-v2-lite":[-1.462,0.133,33.05],"internvl2.5-2b":[-1.463,0.114,31.2],"olmoe-1b-7b":[-1.467,0.083,17.58],"internlm2-math-base-7b":[-1.473,0.168,33.67],"falcon3-1b":[-1.497,0.085,14.27],"internvl2-4b":[-1.507,0.164,27.05],"llama-2-70b":[-1.534,0.144,45.77],"mobilemoe-s":[-1.574,0.145,33.37],"internvl2.5-1b":[-1.6,0.14,21.82],"wizardmath-13b-v1.0":[-1.6,0.144,42.91],"t5gemma-2-4b-4b":[-1.613,0.158,35.77],"llama-3.2-1.24b-base":[-1.656,0.101,5.04],"deepseek-vl-7b":[-1.659,0.231,37.77],"mistral-7b-v0.1":[-1.705,0.143,33.73],"internvl-chat-v1.5":[-1.722,0.14,24.38],"llemma-7b":[-1.735,0.147,31.28],"gemma-2-2b":[-1.81,0.15,19.77],"codellama-7b":[-1.845,0.177,21.27],"llava-1.5-7b":[-1.857,0.258,16.91],"internvl2-1b":[-1.887,0.14,16.88],"smollm2-1.7b-base":[-1.891,0.154,15.35],"internvl2-2b":[-1.971,0.11,21.97],"mobilellm-p1":[-2.096,0.145,19.2],"baichuan-13b-base":[-2.177,0.152,27.64],"deepseek-llm-7b-base":[-2.242,0.153,19.3],"mobilellm-r1-140m":[-2.254,0.143,5.9],"deepseek-moe-16b-base":[-2.296,0.152,21.17],"llama-2-7b":[-2.351,0.152,15.98],"gemma-3-270m-it":[-2.353,0.133,6.67],"t5gemma-2-1b-1b":[-2.492,0.182,7.5],"smollm2-135m-instruct":[-2.713,0.143,2.8],"smollm2-360m-instruct":[-2.726,0.125,5.7],"smollm2-360m-base":[-2.781,0.162,2.67],"t5gemma-2-270m-270m":[-3.052,0.189,1.67]},"benchmarks":[{"id":"gsm8k","name":"GSM8K","topic":"Math (grade-school)","difficulty":-1.871,"discrimination":1.213,"n":310},{"id":"aime-2025","name":"AIME 2025","topic":"Math (competition)","difficulty":0.516,"discrimination":2.608,"n":282},{"id":"math","name":"MATH","topic":"Math (competition)","difficulty":-0.707,"discrimination":1.795,"n":267},{"id":"math500","name":"MATH500","topic":"Math reasoning","difficulty":-0.843,"discrimination":1.806,"n":217},{"id":"aime-2024","name":"AIME 2024","topic":"Math (competition)","difficulty":0.402,"discrimination":2.645,"n":214},{"id":"mathvision","name":"MathVision","topic":"Math reasoning (multimodal)","difficulty":0.248,"discrimination":1.072,"n":135},{"id":"mgsm","name":"MGSM","topic":"Math (multilingual)","difficulty":-1.703,"discrimination":0.905,"n":112},{"id":"mathvista-mini","name":"MathVista-Mini","topic":"Math reasoning (multimodal)","difficulty":-1.548,"discrimination":0.562,"n":101},{"id":"cmath","name":"CMath","topic":"Math (Chinese)","difficulty":-1.749,"discrimination":1.381,"n":93},{"id":"hmmt-2025","name":"HMMT 2025","topic":"Math (competition)","difficulty":0.811,"discrimination":2.772,"n":87},{"id":"olympiadbench","name":"OlympiadBench","topic":"Math (olympiad)","difficulty":0.125,"discrimination":2.215,"n":77},{"id":"mathvista","name":"MathVista","topic":"Multimodal math reasoning","difficulty":-1.968,"discrimination":0.497,"n":76},{"id":"mathverse-mini","name":"MathVerse-mini","topic":"Math reasoning (multimodal)","difficulty":-0.244,"discrimination":0.833,"n":65},{"id":"amc-23","name":"AMC-23","topic":"Math (competition)","difficulty":-0.369,"discrimination":1.896,"n":64},{"id":"dynamath","name":"DynaMath","topic":"Math reasoning (video)","difficulty":-0.417,"discrimination":0.691,"n":63},{"id":"minerva-math","name":"Minerva Math","topic":"University-level math","difficulty":-0.023,"discrimination":1.734,"n":57},{"id":"polymath","name":"PolyMATH","topic":"Math reasoning","difficulty":0.931,"discrimination":1.027,"n":56},{"id":"wemath","name":"WeMath","topic":"Math reasoning","difficulty":0.125,"discrimination":0.985,"n":43},{"id":"gsm-plus","name":"GSM-Plus","topic":"Math (grade-school, enhanced)","difficulty":-0.769,"discrimination":1.352,"n":39},{"id":"omega","name":"OMEGA","topic":"Math (advanced)","difficulty":1.105,"discrimination":1.167,"n":38},{"id":"omni-math","name":"Omni-MATH","topic":"Math reasoning","difficulty":0.666,"discrimination":0.92,"n":31},{"id":"beyondaime","name":"BeyondAIME","topic":"Math (beyond AIME)","difficulty":0.944,"discrimination":1.488,"n":28},{"id":"minif2f-test","name":"MiniF2F (Test)","topic":"Math competition","difficulty":2.183,"discrimination":0.284,"n":22},{"id":"mathverse-vision","name":"MathVerse-Vision","topic":"Math reasoning (multimodal)","difficulty":-0.11,"discrimination":0.891,"n":19},{"id":"omni-math-hard","name":"Omni-MATH-HARD","topic":"Math","difficulty":1.043,"discrimination":1.224,"n":18},{"id":"proofbench-advanced","name":"ProofBench Advanced","topic":"Mathematical proofs (advanced)","difficulty":2.495,"discrimination":1.577,"n":15},{"id":"deepmind-math","name":"DeepMind Mathematics","topic":"Math reasoning","difficulty":-0.291,"discrimination":1.5,"n":12},{"id":"hiddenmath","name":"HiddenMath","topic":"Math reasoning","difficulty":0.106,"discrimination":1.891,"n":10}]},"faix-ocr":{"sd":0.317,"ext":{"claude-fable-5":[2.771,0.15,81.06],"qwen3.8-max":[2.654,0.149,85.16],"gpt-5.6-sol":[2.456,0.149,81.22],"qwen3.8-flash-next":[2.162,0.135,76.25],"gemini-3.1-pro":[2.032,0.115,79.48],"qwen3.8-27b":[1.988,0.146,86.16],"kimi-k3":[1.972,0.155,90.07],"claude-mythos-5":[1.972,0.165,82.13],"claude-opus-4.8":[1.923,0.14,75.61],"seed2.1-pro":[1.832,0.127,86.1],"qwen3.7-plus":[1.791,0.15,78.5],"gpt-5.5":[1.759,0.126,83.63],"gpt-5.4":[1.69,0.13,79.4],"seed2.1-turbo":[1.667,0.127,84.67],"gemini-3-flash":[1.639,0.118,79.47],"seed2.0-lite-0428":[1.626,0.134,88.9],"qwen3.6-plus":[1.614,0.133,77.13],"qwen3.5-397b-a17b":[1.605,0.125,81.22],"qwen3.5-122b-a10b":[1.573,0.12,77.83],"seed2.0-pro":[1.523,0.134,87.6],"gemini-3-pro":[1.485,0.107,82.06],"seed2.0-lite":[1.437,0.134,86.53],"qwen3.5-27b":[1.427,0.125,79.4],"kimi-k2.5-thinking":[1.421,0.136,87.08],"glm-5.3-flash":[1.409,0.132,68.9],"claude-opus-4.7":[1.404,0.126,83.04],"qwen3.5-35b-a3b":[1.352,0.132,80.87],"kimi-k2.5":[1.345,0.128,75.58],"qwen3.6-27b":[1.332,0.141,83.31],"nemotron-3.5-super-vl-120b-a12b":[1.33,0.132,69.05],"o3-high":[1.287,0.15,78.17],"gemma-4-31b-it":[1.277,0.122,81.09],"qwen3.6-35b-a3b":[1.266,0.128,81.73],"gpt-5.2-thinking-xhigh":[1.207,0.141,83.1],"o4-mini-high":[1.156,0.15,75.93],"gpt-5-high":[1.141,0.113,83.05],"inkling-small":[1.135,0.132,61.66],"gemini-2.5-pro":[1.122,0.091,77.67],"nemotron-3.5-super-vl-120b-a12b-nvfp4":[1.118,0.132,66.24],"gemma-4-26b-a4b-it":[1.113,0.123,71.51],"seed1.8":[1.111,0.149,80.6],"gpt-5.4-mini":[1.103,0.228,71.03],"ovis2.6-80b-a3b":[1.1,0.114,78],"minicpm-v-4.7-35b-a3b":[1.096,0.141,81.43],"qwen3.5-omni-plus":[1.085,0.132,78.15],"qwen3-vl-235b-a22b-thinking":[1.079,0.099,78.58],"ovis2.6-30b-a3b":[1.07,0.109,78.69],"comet-60b-a12b":[1.023,0.132,64.06],"qwen3.5-9b":[1.019,0.109,80.39],"gemini-3.1-flash-lite":[1.018,0.145,70.47],"comet-60b-a12b-fp8":[1.007,0.132,63.59],"claude-opus-4.5":[0.997,0.119,74.09],"intern-s1-pro":[0.988,0.158,64.45],"comet-60b-a12b-nvfp4":[0.984,0.132,63.19],"claude-opus-4.6":[0.983,0.15,64.45],"qwen3-vl-235b-a22b":[0.95,0.132,77.75],"exaone-4.5-33b-thinking":[0.948,0.137,72.26],"gpt-5-mini-high":[0.912,0.123,68.12],"seed1.5-vl-thinking":[0.907,0.1,78.86],"glm-4.6v":[0.903,0.101,74.41],"ernie-5.0":[0.889,0.118,85.11],"dots-vlm1":[0.888,0.108,80.91],"claude-3.7-sonnet-thinking":[0.877,0.129,72.08],"qianfan-ocr":[0.875,0.148,77.22],"claude-opus-4.5-thinking":[0.867,0.14,79.08],"qwen3-vl-32b-instruct":[0.856,0.102,77.16],"nemotron-3-nano-omni-30b-a3b-reasoning":[0.84,0.178,60.57],"ovisocr3":[0.824,0.275,72],"qwen3.5-4b":[0.824,0.109,76.41],"gpt-5.2":[0.815,0.137,77.6],"glm-4.5v":[0.808,0.106,69.75],"gpt-5-mini":[0.801,0.102,72.41],"qwen3.5-omni-flash":[0.792,0.132,73.72],"step3-vl-10b":[0.782,0.162,82.3],"qwen3-vl-32b-thinking":[0.759,0.13,74.97],"claude-sonnet-4.6":[0.745,0.226,71.5],"infinity-parser2-pro":[0.691,0.177,89.08],"claude-4.5-haiku":[0.685,0.145,60.12],"ming-flash-omni-2.0":[0.679,0.153,82.74],"longcat-next":[0.666,0.108,76.06],"glm-4.6v-flash":[0.655,0.113,64.14],"qwen3-vl-30b-a3b-instruct":[0.646,0.092,71.94],"pelican-vl-72b":[0.639,0.178,90.35],"gpt-5":[0.635,0.118,73.81],"gpt-4.1-mini":[0.634,0.15,65.97],"ernie-4.5-vl-28b-a3b-thinking":[0.63,0.118,80.85],"mimo-vl-7b-rl":[0.627,0.108,81.15],"claude-3.7-sonnet":[0.605,0.103,76.27],"apriel-1.6-15b-thinker":[0.602,0.13,73.19],"mimo-vl-7b-sft":[0.587,0.108,80.67],"gpt-4.1":[0.568,0.15,64.33],"mimo-vl-7b-rl-2508":[0.565,0.153,80.93],"rynnbrain-30b-a3b":[0.565,0.178,89.1],"claude-opus-4.1":[0.55,0.11,65.1],"o1":[0.538,0.134,66.78],"qwen2.5-vl-72b-instruct":[0.517,0.102,68.48],"qwen3-vl-8b-instruct":[0.515,0.094,71.81],"openpangu-vl-7b":[0.514,0.134,83.29],"glm-4.1v":[0.508,0.126,62.87],"mistral-small-3.2-24b-instruct":[0.505,0.21,91.72],"rynnbrain-8b":[0.498,0.178,88.4],"gemini-2.5-flash":[0.476,0.114,77.18],"plm-8b":[0.475,0.201,89.82],"gemini-2.5-flash-lite":[0.467,0.105,70.6],"claude-3.5-sonnet":[0.456,0.11,74.5],"step-3":[0.455,0.127,60.07],"qwen2-vl-72b-instruct":[0.449,0.146,79.5],"gpt-4.5":[0.432,0.138,64.23],"molmopoint-8b":[0.422,0.209,90.75],"minicpm-o-4.5":[0.416,0.198,88.42],"minicpm-v-4.5-8b":[0.414,0.183,87.96],"qwen3-omni-30b-a3b-instruct":[0.413,0.105,74.94],"mistral-medium-3":[0.408,0.214,90.53],"claude-3.5-sonnet-20240620":[0.405,0.127,81.55],"claude-sonnet-4.5":[0.396,0.138,76.9],"manzano-30b":[0.388,0.162,86.98],"hunyuanocr-1.5":[0.384,0.275,64.83],"mistral-small-3.1-24b-instruct":[0.375,0.214,91.35],"qwen3-vl-8b-thinking":[0.373,0.122,74.78],"apriel-1.5-15b-thinker":[0.368,0.13,68.04],"keye-vl-1.5-8b":[0.365,0.19,88.36],"internvl3.5-30b-a3b-flash":[0.356,0.108,70.19],"qwen2.5-vl-72b":[0.351,0.109,73.21],"penguin-vl-8b":[0.345,0.129,80.07],"doubao-1.5-vision-pro":[0.341,0.134,62.44],"molmo2-8b":[0.341,0.209,90.17],"claude-sonnet-4":[0.328,0.105,57.95],"qwen3-vl-4b-instruct":[0.327,0.091,67.55],"rynnbrain-4b":[0.309,0.178,86.73],"pixtral-large-2411":[0.309,0.169,78.42],"qwen2-vl-72b":[0.306,0.117,75.65],"plm-3b":[0.303,0.198,88.33],"gemma-4-12b-it":[0.263,0.137,73.21],"pelican-vl-7b":[0.259,0.178,86.72],"gpt-4o":[0.259,0.105,72.81],"gemini-2.0-pro":[0.254,0.162,73.07],"qwen3-omni-30b-a3b-thinking":[0.253,0.198,86.75],"glm-4.1v-9b-thinking":[0.238,0.145,77.04],"internvl2.5-78b":[0.237,0.111,75.81],"eagle2.5-8b":[0.229,0.198,87.45],"minicpm-o-4.5-thinking":[0.219,0.198,87.13],"internvl2-pro":[0.198,0.127,79.02],"kimi-vl-a3b-thinking-2506":[0.196,0.119,53.26],"internvl3-78b":[0.189,0.12,52.35],"qwen3-vl-4b-thinking":[0.169,0.147,61.72],"internvl2.5-38b":[0.168,0.109,75.04],"gpt-4o-0513":[0.168,0.207,87.53],"internvl3.5-gpt-oss-20b-a4b":[0.167,0.162,84.78],"mimo-embodied-7b":[0.159,0.144,78.77],"cosmos-reason2-8b":[0.152,0.144,78.35],"qwen3.5-2b":[0.15,0.115,71.08],"youtu-vl-4b-instruct":[0.127,0.125,78.56],"molmo-72b":[0.125,0.133,79.15],"gemini-2.5-flash-thinking":[0.123,0.198,85.15],"manzano-3b":[0.121,0.162,84.12],"mage-vl":[0.113,0.156,75.33],"internvl3.5-8b":[0.099,0.102,71.22],"molmo2-o-7b":[0.093,0.207,88.42],"molmopoint-o-7b":[0.093,0.207,88.42],"deepseek-vl2":[0.08,0.162,84.02],"aria":[0.079,0.216,86.7],"gpt-5-mini-minimal":[0.072,0.106,68.43],"glm-4v-plus":[0.064,0.183,85.84],"internvl3-38b":[0.055,0.126,50.05],"internvl3-14b":[0.054,0.134,54.1],"gpt-4o-2024-05-13":[0.039,0.109,73.88],"gpt-5-minimal":[0.034,0.108,65.44],"internvl2-llama-3-76b":[0.034,0.113,73.12],"xiaomi-ocr-0":[0.022,0.275,57.7],"dots.mocr":[0.016,0.121,72.94],"glm-ocr":[-0.001,0.278,60.95],"infinity-parser2-flash":[-0.014,0.177,83.25],"gemini-1.5-pro":[-0.014,0.107,68.57],"deepseek-vl2-small":[-0.015,0.162,83.23],"qwen2.5-vl-7b":[-0.022,0.105,67.45],"glm-4.1v-9b":[-0.028,0.207,82.7],"qwen2-vl-7b-instruct":[-0.034,0.144,74.89],"minicpm-v-4.7-1b":[-0.036,0.145,60.98],"internvl3.5-4b":[-0.043,0.105,69.95],"nemotron-nano-12b-v2-vl":[-0.053,0.178,42],"internvl2.5-26b":[-0.063,0.111,71.94],"molmo2-4b":[-0.068,0.174,82.52],"zaya1-vl-8b":[-0.081,0.162,81.73],"robobrain-2.0-7b":[-0.082,0.183,80.85],"gemini-1.0-ultra":[-0.108,0.172,82.76],"internvl-8b":[-0.109,0.129,76.3],"fastvlm-7b":[-0.113,0.162,80.93],"penguin-vl-2b":[-0.124,0.127,74.63],"nvlm-d-72b":[-0.137,0.134,75.99],"kanana-1.5-o-9.8b-instruct-2602":[-0.142,0.168,64.82],"gemini-1.5-flash":[-0.154,0.143,68.45],"grok-4-fast-thinking":[-0.155,0.14,57.96],"minicpm-v-4.6":[-0.158,0.124,62.59],"minicpm-v-4.6-thinking":[-0.16,0.162,62.33],"llama-3.2v-90b-instruct":[-0.163,0.142,76.02],"lfm2.5-vl-3b":[-0.175,0.177,74.88],"rynnbrain-2b":[-0.176,0.178,81.33],"kimi-vl-a3b-thinking":[-0.193,0.155,67.8],"internvl2-40b":[-0.197,0.113,69.76],"gpt-4o-mini":[-0.213,0.168,62.51],"gemma-3-27b-vl":[-0.222,0.126,47.63],"qwen3-vl-2b-thinking":[-0.222,0.147,54.82],"qwen3-vl-2b-instruct":[-0.228,0.092,59.34],"internvl3-8b":[-0.23,0.12,42.1],"cogvlm2-llama3-chat-19b":[-0.248,0.185,81.3],"qwen3.5-ocr":[-0.257,0.275,55.03],"llava-onevision-72b":[-0.259,0.106,69.33],"kimi-vl-a3b-instruct":[-0.26,0.155,69.88],"internvl3-9b":[-0.264,0.134,46.03],"qwen2.5-omni-7b":[-0.275,0.135,71.64],"robobrain-2.0":[-0.281,0.183,78.85],"internvl2.5-8b":[-0.281,0.107,69.16],"pixtral-12b":[-0.284,0.137,71.9],"gpt-4v":[-0.313,0.11,68.48],"bagel-7b-mot":[-0.314,0.146,77.02],"lfm2-vl-3b":[-0.316,0.177,72.98],"claude-3-sonnet":[-0.319,0.139,71.62],"internvl2-26b":[-0.33,0.11,68.44],"llada-o":[-0.345,0.146,76.3],"phi-4-multimodal-instruct":[-0.353,0.166,62.68],"jina-vlm-2.4b-20251117":[-0.358,0.125,72.86],"llada2.0-uni":[-0.363,0.141,77.63],"internlm-xcomposer2.5":[-0.368,0.162,78.62],"qwen2-vl-7b":[-0.375,0.113,64.83],"cogvlm2-llama3-chinese-chat-19b":[-0.381,0.197,81.53],"gemma-3-27b-it":[-0.386,0.116,67.04],"internvl3.5-2b":[-0.388,0.123,69.23],"minicpm-v-2_6":[-0.406,0.112,67.08],"qwen2.5-vl-3b":[-0.417,0.1,62.77],"mm1.5-30b":[-0.417,0.163,77.42],"llama-3.2v-11b-instruct":[-0.433,0.142,72.19],"deepseek-vl2-tiny":[-0.435,0.163,78.2],"ovis1.6-gemma2-9b":[-0.444,0.162,62.07],"molmo-7b-d":[-0.449,0.129,71.54],"grok-1.5v":[-0.458,0.202,82.02],"internvl2.5-4b":[-0.459,0.106,66.24],"north-micro-vision-instruct":[-0.468,0.138,70.21],"qwen3.5-0.8b-thinking":[-0.472,0.163,59.53],"claude-3-opus":[-0.474,0.107,64.4],"internvl2-8b":[-0.475,0.106,66.22],"gemma-4-e4b-it":[-0.493,0.151,65.47],"ministral-3-3b-instruct":[-0.496,0.144,70.46],"gpt-4-turbo-2024-04-09":[-0.503,0.195,80.62],"gpt-5-nano":[-0.504,0.128,60.07],"claude-3-haiku":[-0.513,0.134,69.6],"hyperclovax-seed-omni-8b":[-0.514,0.145,66.68],"qwen3.5-0.8b":[-0.524,0.118,54.74],"llava-next-110b":[-0.537,0.207,81.93],"bagel-14b":[-0.545,0.17,76.68],"baichuan-omni":[-0.546,0.249,74.63],"molmo-7b-o":[-0.549,0.137,68.9],"minicpm-o-2.6":[-0.562,0.132,49.12],"internvl-chat-v1.5":[-0.582,0.106,64.84],"gemma-4-e2b-it":[-0.586,0.123,57.59],"llm-jp-4-vl-9b-beta":[-0.599,0.115,59.06],"gpt-4-1106-vision-preview":[-0.604,0.198,77.65],"gemma-3-12b-it":[-0.62,0.261,64.9],"llm-jp-4-vl-9b":[-0.623,0.117,59.38],"internvl3-2b":[-0.639,0.1,59.45],"internlm-xcomposer2-4khd-7b":[-0.643,0.125,68.11],"internvl-u":[-0.662,0.143,73.97],"gemini-pro":[-0.682,0.128,67.37],"fastvlm-1.5b":[-0.686,0.162,74.35],"vita":[-0.702,0.249,72.3],"glm-4v-9b":[-0.711,0.134,68.79],"llava-onevision-7b":[-0.713,0.129,66.9],"qwen2-vl-2b-instruct":[-0.714,0.127,68.11],"qwen-vl-max":[-0.718,0.113,62.13],"internvl2-4b":[-0.723,0.106,62.09],"phi-4-reasoning-vision-15b":[-0.732,0.154,68.18],"aquila-vl-2b":[-0.737,0.126,66.69],"phi-3.5-vision-instruct":[-0.759,0.105,58.52],"lfm2.5-vl-1.6b":[-0.774,0.105,56.38],"minicpm-llama3-v2.5":[-0.78,0.134,66.92],"gemini-1.0-pro":[-0.781,0.128,66.38],"mm1.5-7b":[-0.782,0.162,73.07],"qwen2-vl-2b":[-0.783,0.107,61.81],"phi-3.5-vision-4b":[-0.803,0.221,75.3],"internvl2.5-2b":[-0.829,0.107,60.46],"phi-3-vision-4b":[-0.838,0.125,64.53],"deepseek-ocr":[-0.847,0.33,48.99],"internvl3-1b":[-0.867,0.134,28.97],"mm1.5-3b":[-0.873,0.163,71.38],"llada-v":[-0.885,0.141,69.42],"gpt-5-nano-minimal":[-0.893,0.115,48.44],"mini-gemini-hd-34b":[-0.981,0.142,60.5],"gemma-3n-e2b-it":[-0.983,0.127,61.11],"internvl2-2b":[-0.993,0.107,57.96],"cambrian-34b":[-1.002,0.125,62.57],"molmoe-1b":[-1.04,0.128,62.26],"cambrian-1-34b":[-1.042,0.183,73.5],"internvl2.5-1b":[-1.047,0.107,56.48],"cambrian-1-8b":[-1.05,0.198,73.95],"step-1v-32k":[-1.052,0.232,67.75],"llava-next-34b":[-1.082,0.125,60.44],"qwen-vl-plus":[-1.084,0.12,56.57],"fastvlm-0.5b":[-1.194,0.162,66.88],"emu3-8b":[-1.197,0.198,69.92],"mm1-30b":[-1.219,0.162,67.9],"vila1.5-40b":[-1.263,0.151,53.23],"internvl2-1b":[-1.266,0.107,52.82],"smolvlm2-2.2b":[-1.276,0.125,53.59],"mm1.5-1b":[-1.296,0.163,65.17],"docowl-1.5-chat":[-1.309,0.129,55.14],"cogagent-18b":[-1.329,0.129,54.96],"sphinx-v2":[-1.356,0.134,18.68],"paddleocr-vl-1.6":[-1.362,0.276,36.7],"idefics2-8b":[-1.384,0.153,49.49],"internlm-xcomposer2-vl-7b":[-1.397,0.12,49.02],"deepseek-vl-7b":[-1.462,0.159,44.04],"gemini-nano-2":[-1.494,0.179,59.52],"t5gemma-2-4b-4b":[-1.522,0.172,61.34],"xgen-mm-interleave-4b":[-1.529,0.203,66.65],"internvl-chat-v1.2":[-1.568,0.17,62.27],"minicpm-v-2.0-3b":[-1.574,0.125,52.63],"cogvlm-17b-chat":[-1.587,0.21,58.86],"qwen-vl":[-1.642,0.198,64.22],"llava-onevision-0.5b":[-1.69,0.127,47.88],"qwen-vl-chat":[-1.816,0.183,60.44],"mplug-docowl-7b":[-1.824,0.217,57.4],"llava-1.5-7b":[-1.846,0.198,33.62],"ureader":[-1.895,0.135,42.96],"paligemma-mix-3b":[-1.924,0.249,48.33],"llava-1.5-13b":[-1.949,0.199,35.99],"t5gemma-2-1b-1b":[-2.042,0.175,50.22],"deepseek-vl-1.3b":[-2.238,0.24,45.87],"textmonkey":[-2.299,0.137,43.79],"minicpm-v":[-2.373,0.231,45.13],"janus-pro-7b":[-2.424,0.172,46.05],"deepseek-ocr-2":[-2.512,0.18,53.37],"yi-vl-6b":[-2.698,0.267,30.53],"yi-vl-34b":[-2.819,0.258,29.77],"janus-pro-1.5b":[-2.93,0.172,38.43],"t5gemma-2-270m-270m":[-2.974,0.182,30.32],"lumina-dimoo":[-3.337,0.215,16.72]},"benchmarks":[{"id":"ai2d","name":"AI2D","topic":"Diagram understanding (VQA)","difficulty":-2.738,"discrimination":0.629,"n":249},{"id":"docvqa","name":"DocVQA","topic":"Document understanding (VQA)","difficulty":-2.503,"discrimination":0.998,"n":230},{"id":"ocrbench","name":"OCRBench V2","topic":"OCR (vision text extraction)","difficulty":-2.148,"discrimination":0.676,"n":224},{"id":"charxiv-rq","name":"CharXiv (RQ)","topic":"Chart reasoning (PDF)","difficulty":0.199,"discrimination":1.079,"n":212},{"id":"chartqa","name":"ChartQA","topic":"Chart understanding (VQA)","difficulty":-2.456,"discrimination":0.675,"n":211},{"id":"textvqa","name":"TextVQA","topic":"Text-based VQA","difficulty":-3.165,"discrimination":0.448,"n":178},{"id":"mathvision","name":"MathVision","topic":"Math reasoning (multimodal)","difficulty":0.31,"discrimination":1.566,"n":171},{"id":"infovqa","name":"InfoVQA","topic":"Infographic VQA","difficulty":-1.259,"discrimination":0.914,"n":161},{"id":"charxiv-dq","name":"CharXiv (DQ)","topic":"Chart description (PDF)","difficulty":-0.947,"discrimination":1.199,"n":150},{"id":"ocrbenchv2-en","name":"OCRBenchV2 (EN)","topic":"OCR (English)","difficulty":0.141,"discrimination":0.468,"n":75},{"id":"ocrbenchv2-cn","name":"OCRBenchV2 (CN)","topic":"OCR (Chinese)","difficulty":0.35,"discrimination":0.386,"n":61},{"id":"mmlongbench-doc","name":"MMLongBench-Doc","topic":"Long-context multimodal documents","difficulty":0.699,"discrimination":0.677,"n":52},{"id":"chartmuseum","name":"ChartMuseum","topic":"Chart understanding","difficulty":0.62,"discrimination":1.163,"n":45},{"id":"cc-ocr","name":"CC-OCR","topic":"OCR (cross-lingual)","difficulty":-1.326,"discrimination":0.55,"n":43},{"id":"chartqa-pro","name":"ChartQA-Pro","topic":"Chart understanding (VQA)","difficulty":0.523,"discrimination":0.824,"n":41},{"id":"omnidocbench","name":"OmniDocBench","topic":"Document understanding","difficulty":-8.894,"discrimination":0.2,"n":27},{"id":"olmocr-bench","name":"olmOCR-Bench","topic":"Document OCR","difficulty":-4.903,"discrimination":0.2,"n":17},{"id":"ocrreasoning","name":"OCRReasoning","topic":"OCR reasoning","difficulty":0.645,"discrimination":0.903,"n":16}]},"faix-stem":{"sd":0.436,"ext":{"gpt-5.2-thinking-xhigh":[2.533,0.102,91.35],"gemini-3-pro":[2.483,0.088,88.82],"claude-opus-4.5-thinking":[2.469,0.103,88.97],"claude-opus-4.8":[2.465,0.141,96.7],"gpt-5.5":[2.416,0.106,82.97],"claude-opus-4.6":[2.336,0.128,75.43],"gemini-3.1-pro":[2.323,0.151,80.88],"gpt-5.2":[2.306,0.125,88.17],"seed2.1-pro":[2.302,0.173,86.62],"seed2.0-pro":[2.295,0.124,91.2],"seed2.1-turbo":[2.248,0.175,85.18],"qwen3.8-27b":[2.08,0.113,93.04],"gemini-3.5-flash":[2.079,0.136,93.96],"gemini-3-flash":[2.017,0.124,89.27],"kimi-k2.5":[1.984,0.125,88.38],"gpt-5-thinking":[1.944,0.106,79.7],"qwen3.6-plus":[1.942,0.127,90.54],"claude-opus-4.7":[1.912,0.15,74.17],"gpt-5-high":[1.908,0.076,83.44],"claude-sonnet-4.6":[1.907,0.125,65.8],"gpt-5":[1.9,0.081,82.92],"kimi-k2.5-thinking":[1.897,0.123,82.72],"step3-vl-10b-pacore":[1.88,0.101,87],"qwen3.5-397b-a17b":[1.837,0.131,86.06],"qwen3.5-122b-a10b":[1.833,0.131,89.16],"seed2.0-lite":[1.831,0.124,85.13],"grok-4-fast":[1.83,0.104,92.07],"seed1.8":[1.806,0.09,81.7],"ternary-bonsai-2-27b":[1.776,0.121,96.82],"grok-4":[1.773,0.099,82.22],"qwen3.5-35b-a3b":[1.754,0.131,87.92],"nemotron-3-nano-30b-a3b":[1.731,0.142,86.3],"qwen3.6-27b":[1.72,0.125,86.13],"qwen3.8-27b-ud-q4-k-xl":[1.717,0.12,96.32],"gpt-oss-120b-high":[1.708,0.106,91.8],"claude-sonnet-4.5":[1.698,0.102,78.44],"gpt-oss-120b":[1.68,0.075,82.49],"exaone-4.5-33b-thinking":[1.673,0.128,84.24],"deepseek-v3.1-terminus":[1.672,0.103,80.19],"qwen3-235b-a22b-thinking-2507":[1.662,0.096,73.57],"qwen3-vl-235b-a22b-thinking":[1.658,0.122,84.85],"claude-opus-4.5":[1.651,0.113,79.47],"sarvam-105b":[1.638,0.112,86.65],"gemini-2.5-pro":[1.637,0.066,73.05],"qwen-3-235b-a22b-thinking":[1.622,0.102,91.12],"o3":[1.622,0.086,74.52],"o3-high":[1.617,0.085,80.34],"deepseek-v3.2":[1.606,0.082,90.4],"ernie-5.0":[1.599,0.1,84.93],"gpt-5-mini-high":[1.586,0.115,78.77],"qwen3-30b-a3b-thinking-2507":[1.586,0.085,84.75],"intellect-3":[1.566,0.098,92.3],"minicpm-v-4.7-35b-a3b":[1.565,0.246,82.9],"deepseek-r1-0528":[1.562,0.096,91.8],"qwen3-next-80b-a3b-thinking":[1.558,0.087,79.97],"gpt-5-mini":[1.544,0.097,78.47],"deepseek-v3.1-thinking":[1.54,0.095,71.59],"step3-vl-10b-sere":[1.53,0.101,80.16],"gpt-5-2025-08-07":[1.52,0.143,61.8],"solar-open-100b":[1.494,0.106,88.07],"zdtaichu5.0-9b":[1.485,0.131,83],"qwen3.6-35b-a3b":[1.48,0.106,86.65],"glm-4.7-flash":[1.473,0.11,83.48],"o4-mini":[1.472,0.099,72.86],"openreasoning-nemotron-32b":[1.469,0.087,82.33],"glm-4.5-air":[1.469,0.075,85.36],"step3-vl-10b":[1.463,0.121,80.48],"sarvam-30b":[1.456,0.112,82.17],"superapriel-15b-instruct":[1.451,0.1,91.03],"qwen3.5-omni-plus":[1.447,0.238,83.53],"qwen3-vl-235b-a22b":[1.44,0.095,80.45],"gemma-4-26b-a4b-it":[1.429,0.116,86.61],"nemotron-cascade-14b-thinking":[1.427,0.106,86.03],"ministral-3-14b-reasoning":[1.425,0.103,87.1],"openreasoning-nemotron-14b":[1.421,0.087,80.33],"deepseek-v3.2-exp":[1.416,0.099,84.97],"gpt-oss-20b":[1.415,0.089,77.59],"nemotron-32b":[1.414,0.085,73.99],"falcon-h1r-7b":[1.411,0.082,83.38],"dots-vlm1":[1.41,0.135,82.22],"qwen3-vl-32b-thinking":[1.397,0.084,79.75],"o3-2025-04-16":[1.392,0.141,60.8],"nemotron-cascade-8b-thinking":[1.384,0.106,84.73],"apriel-1.6-15b-thinker":[1.383,0.135,78.7],"nemotron-cascade-8b":[1.381,0.106,84.43],"qwen3-235b-a22b":[1.373,0.076,86.32],"k2-think":[1.371,0.085,72.79],"k2-high-70b":[1.371,0.1,85.22],"motif-2-12.7b-reasoning":[1.37,0.089,90.38],"qwen3-vl-30b-a3b-thinking":[1.369,0.104,79.43],"apriel-1.5-15b-thinker":[1.366,0.079,77.39],"glm-4.5":[1.363,0.095,76.78],"k2-think-v2":[1.359,0.088,86.14],"minimax-m1-80k":[1.328,0.098,86.57],"claude-4.5-haiku":[1.322,0.121,81.27],"seed-thinking-v1.5":[1.311,0.098,85.8],"gemma-4-31b-it":[1.31,0.094,86.18],"openreasoning-nemotron-7b":[1.294,0.078,74.15],"clef-flash":[1.293,0.197,96.53],"qwen3-30b-a3b":[1.292,0.071,81.82],"qwen3-14b-thinking":[1.291,0.098,84.87],"o3-mini":[1.289,0.097,86.07],"grok-3-mini":[1.286,0.126,84.17],"qwen3-32b-thinking":[1.285,0.074,77.12],"qwen3.5-9b":[1.281,0.092,85.27],"qwen3-vl-8b-thinking":[1.279,0.086,76.43],"claude-opus-4.1":[1.278,0.122,73.34],"minimax-m2":[1.276,0.096,80.62],"olmo-3.1-think-32b":[1.27,0.078,79.6],"nvidia-nemotron-nano-9b-v2":[1.263,0.085,78.82],"deepseek-r1-0528-qwen3-8b":[1.263,0.082,77.56],"minimax-m1-40k":[1.256,0.098,84.63],"gemini-2.5-flash-thinking":[1.256,0.086,77.32],"zgcm-1-7b":[1.254,0.098,83.69],"gpt-oss-120b-medium":[1.251,0.094,78.6],"ernie-4.5-vl-28b-a3b-thinking":[1.25,0.233,80.18],"qwen3-next-80b-a3b-instruct":[1.245,0.081,78.45],"clef-omni":[1.238,0.197,96.77],"minicpm4.1-8b":[1.237,0.098,84.09],"qwen3.5-4b":[1.236,0.09,81.73],"jev-1.13":[1.215,0.197,96.27],"claude-opus-4":[1.213,0.089,70.49],"deepseek-r1":[1.21,0.077,75.44],"gemini-2.5-flash":[1.208,0.077,69.82],"gemma-4-12b-it":[1.205,0.119,82.05],"o3-mini-medium":[1.203,0.087,69.13],"vibethinker-1.5b":[1.193,0.087,68.37],"jev-1.14":[1.189,0.197,96.2],"olmo-3-think-32b-dpo":[1.189,0.075,77.43],"instella-moe-16b-a3b-dpo":[1.183,0.096,81.82],"gpt-oss-20b-high":[1.18,0.154,89.35],"gpt-oss-20b-medium":[1.179,0.098,82.58],"instella-moe-16b-a3b-think":[1.177,0.096,81.6],"qwq-32b":[1.175,0.079,72.73],"glm-4.6v":[1.175,0.094,70.47],"qwen3-8b-thinking":[1.174,0.085,78],"clef":[1.173,0.197,95.67],"o1-2024-12-17":[1.172,0.097,82.7],"qwen3-32b":[1.17,0.068,80.34],"olmo-3-think-32b":[1.165,0.084,77.99],"instella-moe-16b-a3b-sft":[1.164,0.096,81.08],"o1":[1.162,0.092,72.82],"qwen3-vl-32b-instruct":[1.159,0.086,75.66],"qwen3.5-27b":[1.152,0.114,88.68],"qwen3.5-omni-flash":[1.146,0.238,79.15],"phi-4-reasoning-plus":[1.144,0.082,72.88],"claude-3.7-sonnet":[1.14,0.111,64.23],"telechat3-36b-thinking":[1.135,0.098,80.53],"qwen3-omni-30b-a3b-thinking":[1.135,0.146,79.93],"qwen3-vl-30b-a3b-instruct":[1.129,0.092,73.14],"olmo-3-think-7b-dpo":[1.129,0.092,71.37],"qwen3-30b-a3b-instruct-2507":[1.127,0.065,82.67],"motif-2-12.7b-instruct":[1.123,0.085,85.32],"deepseek-r1-0120":[1.12,0.087,63.83],"olmo-3-think-32b-sft":[1.119,0.074,75.26],"ovis2.6-30b-a3b":[1.115,0.208,74.82],"autotrust-jev-35b":[1.111,0.197,94.4],"olmo-3-think-7b-sft":[1.11,0.092,71.21],"lg-exaone-32b":[1.107,0.092,81.82],"vllm-sr-d3":[1.105,0.197,95.07],"qwen3-vl-4b-thinking":[1.101,0.104,76.28],"longcat-flash-lite":[1.098,0.096,79.43],"seed-1.5-vl":[1.089,0.097,67.53],"joyai-llm-flash":[1.089,0.111,87.06],"olmo-3-think-7b":[1.088,0.08,78.92],"longcat-flash-lite-sparse":[1.079,0.16,75.1],"mimo-v2.5-pro-base":[1.078,0.15,93.1],"pplx-decider-v1.2":[1.065,0.197,94.83],"phi-4-reasoning":[1.06,0.087,60.5],"apriel-nemotron-15b-thinker":[1.056,0.092,79.97],"acereason-nemotron-1.1":[1.052,0.087,60.1],"llada2.1-flash-q":[1.043,0.098,76.07],"ming-flash-omni-2.0":[1.037,0.244,76.79],"glm-4.5v":[1.037,0.176,72.17],"llada2.0-flash":[1.034,0.081,82.9],"magistral-small-2506":[1.033,0.087,59],"mimo-7b-rl":[1.032,0.087,58.9],"telechat3-105b-a4.7b-thinking":[1.031,0.098,77.27],"llada2.1-flash-s":[1.028,0.098,75.45],"nemotron-research-goosereason-4b-instruct":[1.023,0.078,73.83],"ovis2.6-80b-a3b":[1.018,0.212,71.98],"k2-medium-70b":[1.016,0.099,72.55],"kimi-linear-instruct":[1.015,0.081,69.82],"deepseek-r1-distill-qwen-32b":[1.01,0.092,69.22],"kimi-k2-instruct":[1.007,0.077,76.14],"questa-nemotron-1.5b":[1.005,0.078,61.7],"ling-flash-2.0":[1.001,0.082,82.88],"openthinker3-7b":[1.001,0.092,67.04],"llama-3.1-405b":[0.999,0.162,93.47],"glide-no-thinking":[0.994,0.197,93.83],"qwen3-14b":[0.992,0.085,84.02],"kimi-k2-0905":[0.978,0.103,52.84],"llama-3.1-nemotron-nano-8b-v1":[0.977,0.092,74.9],"seed1.5-vl-thinking":[0.976,0.243,75.25],"olmo-hybrid-think-7b-sft":[0.966,0.092,66.16],"autotrust-jev-27b":[0.964,0.197,93.07],"o1-mini":[0.94,0.091,75.22],"skywork-or1-7b":[0.931,0.087,52.27],"longcat-next":[0.927,0.25,77.25],"vllm-sr-d3-flash":[0.92,0.197,92.87],"claude-sonnet-4":[0.915,0.084,64.56],"qwen3-omni-30b-a3b-instruct":[0.911,0.124,70.72],"qwen3-4b":[0.911,0.077,79.41],"deepseek-r1-distill-32b":[0.908,0.078,55.6],"youtu-llm-2b":[0.908,0.098,69.63],"qwen3-8b":[0.905,0.071,75.26],"gemini-2.5-flash-lite":[0.903,0.088,68.7],"ling-mini-2.0":[0.899,0.082,64.69],"vllm-sr-decision-2.0-vega-27b":[0.896,0.197,92.53],"nemotron-h-47b-reasoning":[0.888,0.082,60.4],"olmo-3.1-instruct-32b":[0.868,0.083,75.46],"deepseek-v3-0324":[0.863,0.079,68.12],"grok-3":[0.856,0.102,71.73],"autotrust-gev-26b-decide":[0.855,0.197,92.9],"qwen3-vl-8b-instruct":[0.849,0.075,63.65],"pplx-decider-flash-v1.2":[0.847,0.197,91.63],"nemotron-1.5b":[0.845,0.078,51.86],"ernie-4.5":[0.836,0.088,77.68],"o1-mini-2024-09-12":[0.813,0.127,77.25],"gemini-3.5-flash-lite":[0.811,0.14,70.16],"gemini-2.0-pro":[0.81,0.125,75.5],"vllm-sr-d3-mini":[0.805,0.197,91.5],"gpt-5-nano":[0.797,0.181,69.47],"qwen3-4b-instruct-2507":[0.792,0.066,65.94],"llada2.1-mini-q":[0.782,0.098,67.03],"gemma-4-e4b-it":[0.775,0.079,67.96],"deepseek-v3":[0.762,0.084,77.95],"qwen3-vl-4b-instruct":[0.76,0.086,66.91],"llada2.0-mini":[0.756,0.098,65.66],"gemini-2.0-flash":[0.75,0.156,65.23],"glm-4.1v":[0.741,0.192,66.28],"gpt-4.1":[0.733,0.072,66.34],"marco-mini-instruct":[0.733,0.144,88.92],"llada2.1-mini-s":[0.73,0.098,64.84],"claude-3.7-sonnet-thinking":[0.725,0.224,75.53],"step-3":[0.724,0.189,66.72],"openreasoning-nemotron-1.5b":[0.723,0.08,58.54],"mimo-vl-7b-rl-2508":[0.715,0.269,74.82],"minicpm-v-4.5-8b":[0.712,0.334,82.1],"youtu-vl-4b-instruct":[0.705,0.251,78.9],"claude-opus-4.1-20250805":[0.705,0.141,73.64],"glm-4.1v-9b-thinking":[0.685,0.269,74.33],"deepseek-r1-distill-qwen-7b":[0.679,0.09,59.65],"granite-4.1-30b":[0.668,0.15,81.74],"k2-v2":[0.663,0.109,74.46],"smollm3-3b":[0.662,0.072,65.71],"glm-4.6v-flash":[0.662,0.21,65.96],"gemma-3-27b":[0.659,0.105,85.65],"bespoke-nimble-9b-v3":[0.655,0.197,90.97],"manzano-30b":[0.643,0.296,85.17],"nemotron-3-super-120b-a12b-base":[0.636,0.093,76.02],"keye-vl-1.5-8b":[0.634,0.334,80.53],"gpt-4.5":[0.631,0.118,52.33],"openpangu-vl-7b":[0.629,0.122,71.4],"kanana-2-30b-a3b-instruct-2601":[0.625,0.154,87.76],"o1-preview":[0.62,0.109,71.87],"deepseek-r1-distill-llama-8b":[0.617,0.095,59.14],"kolibri-1-base":[0.613,0.17,86.65],"nemotron-3-ultra-base":[0.594,0.141,82.14],"diffusiongemma-jev":[0.589,0.197,90.67],"granite-4.1-8b":[0.582,0.146,81.76],"qwen3.8-27b-iq2-xxs":[0.58,0.136,80.39],"gemini-2.0-flash-001":[0.576,0.137,68.63],"hunyuan-large-instruct":[0.574,0.167,87.3],"nemotron-3.5-super-vl-120b-a12b-base":[0.571,0.128,82.49],"autotrust-jev-9b":[0.568,0.197,89.7],"k2-low-70b":[0.564,0.096,55.92],"claude-3.5-sonnet-20240620":[0.558,0.154,83.2],"vllm-sr-decision-2.0-lux-9b":[0.549,0.197,89.43],"gpt-4.1-2025-04-14":[0.549,0.136,43.14],"gemma-4-e2b-it":[0.544,0.081,58.44],"nemotron-3-nano-30b-a3b-base":[0.539,0.11,80.69],"olmo-3.1-instruct-32b-dpo":[0.538,0.092,52.06],"gemma-3-27b-it":[0.533,0.074,63.3],"bespoke-nimble-9b-v2":[0.531,0.197,89.8],"mistral-3.2-24b":[0.529,0.132,87.47],"kanana-2-30b-a3b-instruct":[0.527,0.154,86.32],"qwen2.5-math-72b-instruct":[0.527,0.08,67.03],"minicpm-v-4.6-thinking":[0.524,0.224,66.78],"ling-3.0-flash-base":[0.516,0.121,67.7],"olmo-3-instruct-7b":[0.515,0.079,64.88],"qwen3-8b-non-thinking":[0.506,0.081,54.43],"mobilellm-r1.5-950m":[0.503,0.094,60.05],"ling-2.6-1t-base":[0.501,0.118,70.8],"claude-sonnet-4-20250514":[0.496,0.136,42.34],"openpangu-r-7b-diffusion":[0.492,0.154,85.94],"lfm2.5-1.2b-thinking":[0.486,0.117,68.83],"deepseek-v3.1":[0.481,0.107,74.18],"kimi-k2-base":[0.477,0.122,82.34],"alodlm-8b":[0.475,0.128,88.82],"motif-3-base":[0.463,0.139,86.35],"mistral-medium-3":[0.457,0.097,58.17],"nemotron-3.5-lightning-30b-a3b-base":[0.454,0.167,78.58],"mimo-v2-flash-base":[0.452,0.14,86.47],"qwen3.5-35b-a3b-base":[0.447,0.133,76.25],"qwen3-235b-a22b-base":[0.441,0.154,84.68],"qwen3-vl-2b-thinking":[0.441,0.313,73.57],"gpt-5-minimal":[0.44,0.133,54.95],"hunyuan-large":[0.439,0.125,87.46],"hy3-preview-base":[0.437,0.096,72.68],"qwen3-1.7b-thinking":[0.437,0.116,67.93],"kev-9b":[0.436,0.197,88.9],"mistral-small-3.1-24b-instruct":[0.431,0.135,80.84],"llama-3.1-tulu-3-405b":[0.431,0.154,83.27],"qwen3-1.7b":[0.426,0.063,58.09],"llama-4-maverick":[0.425,0.137,67.72],"mistral-large-instruct-2407":[0.413,0.149,85],"bagel-7b-mot":[0.411,0.276,69.27],"seed1.6":[0.411,0.155,84.93],"deepseek-r1-distill-qwen-1.5b":[0.411,0.087,59.78],"qwen3-32b-nothinking":[0.409,0.082,37.4],"llama-3.1-405b-instruct":[0.409,0.098,75.53],"qwen2.5-max":[0.406,0.154,83.63],"qwen2.5-14b-instruct":[0.405,0.143,81.09],"llada2.0-flash-preview":[0.4,0.089,68.44],"qwen2.5-vl-72b-instruct":[0.388,0.229,64.8],"qwen2-math-72b-instruct":[0.387,0.082,62.37],"ling-2.6-flash-base":[0.387,0.118,67.75],"qwen2.5-72b-instruct":[0.387,0.076,65.47],"kanana-1.5-32.5b-instruct":[0.384,0.154,84.08],"minicpm-o-4.5":[0.38,0.15,83.24],"vllm-sr-decision-2.0-nox-4b":[0.373,0.197,87.13],"ling-1t-base":[0.373,0.118,68.42],"kimi-vl-a3b-thinking":[0.368,0.229,64.78],"kimi-vl-a3b-thinking-2506":[0.365,0.195,57.27],"deepseek-v3-base":[0.364,0.115,86.33],"qwen3-8b-instruct":[0.362,0.119,84.03],"gpt-4o-2024-08-06":[0.36,0.091,59.45],"sdar-8b-chat":[0.359,0.154,82.83],"gpt-4-turbo-2024-04-09":[0.357,0.117,71.96],"lfm2-350m-math":[0.352,0.09,48.75],"gemma-3-12b-it":[0.35,0.075,64.71],"gemini-1.5-flash":[0.348,0.137,73.31],"qwen2.5-math-7b-instruct":[0.344,0.08,61.21],"ling-2.5-flash-base":[0.343,0.121,61.28],"olmo-3-instruct-7b-dpo":[0.338,0.092,43.08],"gpt-4o":[0.336,0.089,60.67],"claude-3-sonnet":[0.335,0.25,76.6],"claude-3.5-sonnet":[0.331,0.103,68.03],"tev1-4b-experimental":[0.331,0.197,87.37],"deepseek-v4-pro-base":[0.327,0.13,84.5],"llama-4-scout-17b":[0.327,0.082,58.98],"qwen2.5-32b-instruct":[0.325,0.075,59.68],"qwen2.5-vl-72b":[0.324,0.269,67.43],"gpt-4o-mini":[0.32,0.145,75.79],"deepseek-v3.2-exp-base":[0.32,0.132,77.86],"ling-flash-base-2.0":[0.318,0.096,68.82],"deepseek-v4-flash-base":[0.316,0.115,82.82],"qwen-2.5-72b":[0.316,0.077,70.04],"llama-3.3-70b-instruct":[0.31,0.119,82.18],"ministral-3-8b-instruct":[0.309,0.158,81.4],"gpt-4o-2024-11-24":[0.307,0.155,82.8],"nemotron-3.5-lightning-30b-a3b":[0.305,0.141,82.84],"grok-4-fast-thinking":[0.302,0.269,66.14],"keye-vl-8b":[0.298,0.239,47.67],"wedlm-8b-instruct":[0.296,0.111,84.05],"llama-3-70b":[0.294,0.156,77.95],"minicpm-v-4.6":[0.293,0.191,59.37],"nemotron-labs-twotower-30b-a3b-base":[0.288,0.132,84.41],"joyai-llm-flash-base":[0.287,0.128,82.16],"llama-3.1-tulu-3-405b-dpo":[0.285,0.154,80.23],"llama-3.1-tulu-3-405b-sft":[0.281,0.154,80.47],"phi-3-medium-4k-instruct":[0.28,0.179,86.87],"glm-4.5-base":[0.279,0.123,79.6],"deepseek-v3.2-base":[0.271,0.129,82.66],"deepseek-coder-v2-instruct":[0.27,0.08,67.95],"qwen2.5-coder-32b-instruct":[0.269,0.084,62.14],"claude-3.5-sonnet-20241022":[0.267,0.095,64.84],"llama-4-maverick-17b-128e-base":[0.266,0.182,79.67],"deepseek-v2.5":[0.266,0.099,68.38],"llama-3.1-tulu-3-70b":[0.263,0.154,79.87],"gemini-1.5-pro-002":[0.261,0.138,62.87],"gpt-4.1-nano":[0.257,0.178,78.07],"falcon-h1-34b-instruct":[0.257,0.083,60.33],"llama-3.1-tulu-3-70b-dpo":[0.257,0.154,79.7],"mistral-large-3-base":[0.248,0.118,75.01],"skywork-o1-open-llama-3.1-8b":[0.245,0.087,56.22],"internvl3.5-8b":[0.24,0.179,71.11],"qwen2-72b-instruct":[0.239,0.097,69.62],"glm-4-0520":[0.239,0.154,79.3],"apertus-v1.5-70b-thinking":[0.234,0.083,57.62],"gemini-1.5-pro":[0.23,0.089,62.44],"llama-3.1-70b-instruct":[0.224,0.096,70.73],"seed1.5":[0.224,0.155,81.51],"minicpm-v-4.7-1b":[0.222,0.246,55.45],"deepseek-v3.1-base":[0.221,0.155,80.47],"manzano-3b":[0.218,0.296,81.63],"marco-nano-instruct":[0.209,0.144,79],"qwen2.5-math-72b":[0.208,0.14,82.43],"phi-4-reasoning-vision-15b":[0.206,0.295,68.3],"gpt-4o-2024-05-13":[0.204,0.085,63.55],"qwen2-math-7b-instruct":[0.203,0.08,57.66],"yuan2.0-m32":[0.2,0.144,79.15],"hermes-3-llama-3.1-405b":[0.2,0.154,78.67],"deepseek-v4.1-flash-base":[0.197,0.149,78.1],"apertus-v1.5-8b-thinking":[0.197,0.083,55.93],"lfm2-8b-a1b":[0.196,0.093,67.32],"llada2.0-mini-preview":[0.195,0.154,78.33],"qwen3-30b-a3b-base":[0.192,0.128,78.67],"phi-3.5-moe-instruct":[0.191,0.179,86.12],"intern-decision-4b":[0.188,0.197,86.47],"phi-3-small-8k-instruct":[0.188,0.179,85.33],"mimo-v2.5-base":[0.181,0.098,66.56],"jamba-1.5-large":[0.18,0.17,85.8],"gpt-5-nano-minimal":[0.178,0.148,38.76],"step-3.5-flash-base":[0.173,0.096,65.61],"step-3.5-flash-base-midtrain":[0.164,0.154,79.33],"lfm2-24b-a2b":[0.159,0.156,78.45],"llama-3.1-70b":[0.155,0.139,67.43],"mistral-small-3.2-24b-instruct":[0.153,0.143,75.86],"gpt-4":[0.151,0.103,66.46],"motif-2-12.7b-base":[0.147,0.147,80.07],"qwen2.5-coder-14b-instruct":[0.144,0.087,55.47],"gemini-1.5-flash-002":[0.137,0.137,59.33],"granite-4.1-3b":[0.136,0.146,71.3],"gpt-4-0314":[0.129,0.155,77.1],"llama-4-maverick-base":[0.128,0.154,78.85],"claude-3-opus":[0.127,0.109,66.83],"deepseek-v2-chat-sft":[0.124,0.116,82.33],"qwen2.5-math-1.5b-instruct":[0.124,0.08,55.4],"internlm2-math-plus-mixtral8x22b":[0.122,0.16,62.4],"glm-4-air-0605":[0.118,0.154,76.9],"qwen3-6b":[0.117,0.09,38.92],"minicpm4-8b":[0.113,0.155,87.46],"granite-4.0-h-small":[0.111,0.104,65.06],"internvl3.5-4b":[0.1,0.186,57.01],"mobilellm-r1-950m":[0.098,0.081,47.92],"ling-3.0-tiny-base":[0.09,0.12,53.35],"olmo-3-32b":[0.089,0.162,74.38],"llama-3.1-405b-base":[0.089,0.119,81.39],"internlm2_5-20b-chat":[0.082,0.154,75.57],"llama-3.3-70b":[0.079,0.093,61.9],"qwen2.5-7b-instruct":[0.076,0.073,47.52],"ling-2.5-mini-base":[0.073,0.12,53.18],"falcon-h1-7b":[0.07,0.083,54.08],"olmo-3.1-instruct-32b-sft":[0.068,0.092,37.96],"qwen2-math-72b":[0.063,0.14,78.67],"olmo-hybrid-instruct-7b-dpo":[0.063,0.092,37.26],"llama-3.1-tulu-3-70b-sft":[0.06,0.154,74.57],"qwen2.5-math-7b":[0.054,0.14,77.33],"gemma-3-4b-it":[0.054,0.076,58.9],"gpt-4o-mini-2024-07-18":[0.053,0.127,62.83],"vllm-sr-d3-nano":[0.052,0.197,84.1],"abab6.5":[0.052,0.154,73.9],"kanana-1.5-o-9.8b-instruct-2602":[0.042,0.252,50.79],"gpt-5-mini-minimal":[0.033,0.229,55.85],"llm-jp-4-vl-9b":[0.032,0.191,57.67],"falcon-h1-1.5b-deep":[0.031,0.083,50.3],"numinamath-72b-cot":[0.029,0.088,51.17],"falcon-h1-3b":[0.028,0.083,51.1],"xverse-moe-a36b":[0.027,0.154,74.53],"gpt-4-1106-preview":[0.024,0.138,62],"qvq-72b":[0.023,0.149,42.57],"qwen3-8b-base":[0.021,0.128,70.52],"llama-3.2v-90b-instruct":[0.018,0.323,64.53],"llama-4-scout-17b-16e-base":[0.016,0.183,73.5],"gemini-1.0-ultra":[0.009,0.164,70.03],"gemma-4-26b-a4b":[0.008,0.167,68.59],"molmo-72b":[0.001,0.358,71.17],"claude-3-opus-20240229":[0.001,0.115,63.35],"internvl3.5-2b":[-0.006,0.334,70.73],"trinity-large-base":[-0.007,0.148,76.14],"qwen3.5-4b-base":[-0.007,0.098,67.29],"qwen2.5-coder-32b":[-0.01,0.144,74.47],"yi-1.5-34b-chat":[-0.013,0.154,72.37],"mixtral-8x22b-instruct-v0.1":[-0.014,0.117,79.82],"kimi-linear-base":[-0.015,0.14,76.77],"internlm2.5-7b-chat":[-0.017,0.154,73.13],"pixtral-12b":[-0.024,0.352,69.93],"glm-4.5-air-base":[-0.024,0.111,68.49],"lfm2.5-1.2b-instruct":[-0.031,0.119,47.24],"solar-pro-preview":[-0.031,0.191,79.23],"qwen3-0.6b":[-0.037,0.078,34.38],"baichuan-3":[-0.038,0.154,73.03],"qwen1.5-72b-chat":[-0.039,0.112,78.67],"qwen2.5-14b":[-0.047,0.145,73.2],"mixtral-8x22b":[-0.048,0.118,78.27],"qwen2.5-7b":[-0.051,0.074,55.29],"qwen3.5-9b-base":[-0.055,0.124,48.65],"llama-3-70b-instruct":[-0.058,0.107,71.19],"gemma-2-9b-it":[-0.06,0.144,72.19],"olmo-hybrid-instruct-7b-sft":[-0.061,0.092,34.02],"qwen2-72b":[-0.062,0.129,75.82],"qwen2-math-1.5b-instruct":[-0.065,0.087,49.54],"glm-4-0116":[-0.066,0.154,72.33],"llama-4-scout-17b-16e":[-0.068,0.214,54.3],"d1-3b":[-0.068,0.19,82.47],"internlm2-math-plus-20b":[-0.068,0.105,51.93],"granite-4.0-h-micro":[-0.074,0.155,58.72],"deepseek-math-7b-rl":[-0.076,0.105,53.8],"fast-dllm-v2-7b":[-0.076,0.154,70.63],"hermes-3-llama-3.1-70b":[-0.081,0.154,70.77],"molmo2-4b":[-0.082,0.357,69.6],"apertus-v1.5-70b":[-0.088,0.119,73.24],"qwen3.5-2b":[-0.09,0.085,59.79],"qwen2.5-omni-7b":[-0.09,0.165,61.87],"lfm2-2.6b":[-0.091,0.101,59.22],"ouro-2.6b":[-0.091,0.171,78.36],"qwen2.5-coder-7b-instruct":[-0.094,0.082,45.67],"tigerbot-70b-chat":[-0.097,0.214,79.31],"deepseek-v2-chat":[-0.102,0.091,69.69],"gemma-3n-e2b-it":[-0.102,0.146,44.56],"qwen3-vl-2b-instruct":[-0.103,0.132,63.57],"falcon-h1-1.5b":[-0.104,0.083,45.36],"olmo-3-7b-sft":[-0.111,0.092,32.1],"llama-3-70b-base":[-0.115,0.122,78.35],"llada2.0-uni":[-0.116,0.276,59.8],"claude-3-haiku":[-0.116,0.235,66.77],"qwen1.5-72b":[-0.118,0.119,78.07],"granite-3.3-8b-instruct":[-0.119,0.081,43.98],"internvl2.5-78b":[-0.119,0.139,51.38],"bitcpm-cann-8b":[-0.122,0.155,83.99],"deepseek-coder-v2-lite-instruct":[-0.123,0.076,56.9],"kanana-2-30b-a3b-base":[-0.124,0.154,70.85],"kanana-2-30b-a3b-mid-2601":[-0.124,0.154,70.85],"qwen2.5-32b-base":[-0.124,0.145,71.58],"internvl2.5-38b":[-0.128,0.139,50.56],"qwen2-57b-a14b-instruct":[-0.129,0.144,70.95],"moonlight-base":[-0.13,0.107,75.77],"internlm2-math-plus-7b":[-0.132,0.106,50.4],"claude-3.5-haiku-20241022":[-0.135,0.148,52.39],"deepseek-v2":[-0.138,0.116,76.57],"mm1.5-30b":[-0.138,0.296,74.9],"qwen2.5-coder-14b":[-0.139,0.145,70.67],"falcon3-10b":[-0.14,0.082,49.01],"llama-3.1-nemotron-70b":[-0.144,0.143,73.17],"kanana-1.5-32.5b-base":[-0.144,0.154,69.86],"yi-1.5-9b-chat":[-0.146,0.154,68.97],"mathstral-7b":[-0.151,0.096,49.72],"mistral-large-2411":[-0.153,0.141,58.84],"phi-3.5-mini-instruct":[-0.155,0.139,71.93],"deepseek-llm-67b-chat":[-0.16,0.12,73.83],"gemma-3-27b-vl":[-0.16,0.191,47.45],"granite-4.0-h-tiny":[-0.161,0.085,57],"llama-3.1-70b-base":[-0.161,0.129,74.96],"gpt-4v":[-0.161,0.14,44.46],"instella-moe-16b-a3b-base":[-0.163,0.136,77.79],"qwen2-7b-instruct":[-0.171,0.1,55.81],"hrm-text-1b":[-0.172,0.139,70.83],"phi-3-mini-4k-instruct":[-0.172,0.179,78.73],"deepseek-math-7b-instruct":[-0.175,0.14,71.43],"qwen1.5-110b-chat":[-0.176,0.154,69.27],"falcon3-7b":[-0.177,0.082,47.17],"glm-4-9b-chat":[-0.177,0.144,68.53],"llama-3.1-tulu-3-8b":[-0.183,0.154,66.5],"llava-onevision-72b":[-0.184,0.219,54.94],"llada-o":[-0.185,0.276,58.23],"qwen2-vl-72b":[-0.186,0.141,50.16],"qwen2-math-7b":[-0.192,0.14,71.33],"qwen2.5-coder-3b-instruct":[-0.194,0.087,41.77],"kimi-vl-a3b-instruct":[-0.197,0.229,53.7],"glm4-9b":[-0.2,0.128,61.22],"qwen1.5-110b":[-0.207,0.142,71.25],"eurollm-22b":[-0.212,0.114,68.94],"nemotron-nano-12b-v2-base":[-0.22,0.145,70.05],"qwen2-vl-72b-instruct":[-0.222,0.146,48.92],"ministral-3-3b-instruct":[-0.224,0.169,70.58],"hyperclovax-seed-omni-8b":[-0.233,0.174,52.84],"numinamath-7b-cot":[-0.233,0.104,49.56],"qwen2.5-vl-7b":[-0.234,0.192,45.3],"deepseek-coder-v2-base":[-0.239,0.149,66.9],"qwen2.5-math-1.5b":[-0.24,0.14,69.87],"llama-3.1-8b":[-0.243,0.132,72.54],"internvl2.5-26b":[-0.246,0.105,54.91],"kanana-2-3b-instruct":[-0.249,0.154,48.94],"llama-3.1-tulu-3-8b-dpo":[-0.26,0.154,65],"ovis1.6-gemma2-9b":[-0.269,0.262,56.8],"kanana-2-30b-a3b-base-2601":[-0.269,0.154,66.75],"minicpm3-4b":[-0.27,0.154,64.97],"moonlight-instruct":[-0.275,0.089,40.01],"mobilellm-r1.5-360m":[-0.276,0.101,32.73],"molmo-7b-d":[-0.284,0.353,65.47],"bielik-11b-v3.0-instruct":[-0.287,0.188,73.77],"kanana-2-1.3b-instruct":[-0.289,0.154,47.37],"openpangu-7b-diffusion-base":[-0.294,0.154,64.96],"olmo-2-32b-base":[-0.299,0.129,66.99],"qwen2.5-vl-3b":[-0.303,0.246,56.9],"qwen2-7b":[-0.307,0.112,63.3],"qwen2.5-3b":[-0.31,0.076,47.9],"gpt-3.5-turbo-0125":[-0.321,0.154,63.79],"bielik-11b-v2.5-instruct":[-0.324,0.189,71.64],"llama-3.1-8b-instruct":[-0.325,0.067,45.77],"qwen2.5-coder-7b":[-0.332,0.144,64.85],"alodlm-1.7b":[-0.332,0.128,74.62],"minicpm-o-2.6":[-0.338,0.209,38.99],"olmo-3-7b":[-0.339,0.108,65.68],"apertus-v1.5-8b":[-0.339,0.119,65.28],"gemma-2-27b":[-0.342,0.129,59.62],"gpt-4-turbo":[-0.344,0.134,40.69],"gemma-3-12b":[-0.346,0.137,73.5],"ministral-8b-instruct":[-0.348,0.154,62.83],"qwen1.5-32b-chat":[-0.353,0.133,66.65],"yi-1.5-34b":[-0.355,0.141,66.8],"phi-3-vision-4b":[-0.358,0.296,70.67],"gemma-2-27b-it":[-0.364,0.093,44.24],"trinity-mini-base":[-0.372,0.154,72.42],"qwen2-math-1.5b":[-0.376,0.14,65.1],"qwen2.57b-a14b":[-0.376,0.142,66.08],"qwen3.5-2b-base":[-0.377,0.136,73.23],"dream-7b-base":[-0.377,0.154,62.3],"dream-7b-instruct":[-0.382,0.111,68.33],"bielik-11b-v2.6-instruct":[-0.384,0.187,71.28],"yi-1.5-6b-chat":[-0.384,0.154,60.73],"gpt-3.5-turbo":[-0.394,0.154,61.63],"llada-v":[-0.394,0.276,54.03],"jamba-1.5-mini":[-0.395,0.181,63.7],"llama-3-8b":[-0.401,0.118,60.55],"internlm2-chat-20b":[-0.403,0.154,60.7],"apertus-70b":[-0.407,0.126,61.99],"cambrian-34b":[-0.411,0.296,72.83],"internvl2-llama-3-76b":[-0.415,0.136,46.5],"gpt-3.5":[-0.418,0.136,64.67],"internvl2.5-8b":[-0.42,0.106,51.91],"olmo-2-0325-32b-instruct":[-0.426,0.1,28.32],"internvl3-2b":[-0.427,0.269,52.63],"falcon-h1-0.5b-instruct":[-0.436,0.083,37.04],"minicpm-v-2_6":[-0.437,0.229,47.95],"trinity-large-truebase":[-0.437,0.144,67.34],"command-r-plus":[-0.44,0.17,71.55],"llada-8b-instruct":[-0.44,0.128,72.02],"smollm3-3b-base":[-0.443,0.136,72.87],"skywork-moe-base":[-0.443,0.154,61.8],"granite-4.0-micro":[-0.448,0.127,47.94],"internvl3-8b":[-0.45,0.239,28.43],"granite-4.0-1b":[-0.453,0.113,40.52],"bitcpm-cann-3b":[-0.457,0.155,77.8],"qwen1.5-32b":[-0.462,0.141,63.78],"granite-3.3-2b-instruct":[-0.464,0.11,47.43],"granite-3.2-8b-instruct":[-0.465,0.11,50.92],"internlm2.5-7b":[-0.466,0.154,60.13],"qwen2-vl-7b-instruct":[-0.471,0.262,52.5],"gemini-pro":[-0.478,0.147,51.29],"rnd1-base-0910":[-0.479,0.182,70.93],"llama-3-8b-instruct":[-0.48,0.131,66.73],"yi-1.5-9b":[-0.485,0.154,59.57],"map-neo-7b-instruct":[-0.486,0.139,66.48],"internlm2-chat-20b-sft":[-0.486,0.154,58.5],"bielik-11b-v2.3-instruct":[-0.487,0.187,68.38],"internlm2-20b":[-0.492,0.153,50.46],"deepseek-math-7b":[-0.494,0.113,50.93],"bielik-11b-v2.2-instruct":[-0.494,0.186,68.45],"qwen2-vl-7b":[-0.497,0.212,46.3],"map-neo-7b-sft":[-0.499,0.139,66.21],"falcon3-3b":[-0.502,0.082,38.54],"metamath-70b":[-0.503,0.14,59.93],"llama-3.1-tulu-3-8b-sft":[-0.505,0.154,57.87],"gemma-3-4b":[-0.505,0.175,54.56],"bielik-11b-v2.1-instruct":[-0.511,0.185,68.11],"qwen3-4b-base":[-0.521,0.167,58.93],"command-r-plus-08-2024":[-0.522,0.179,72.47],"qwen3-1.7b-base":[-0.524,0.143,59.07],"mixtral-8x7b":[-0.533,0.129,61.57],"trinity-nano-base":[-0.538,0.125,73.76],"mixtral-8x7b-instruct-v0.1":[-0.541,0.154,57.93],"granite-3.1-8b-instruct":[-0.544,0.11,49.16],"intern-decision-2b":[-0.546,0.197,75.37],"qwen2.5-coder-3b":[-0.548,0.145,57.45],"ouro-1.4b":[-0.55,0.132,62.41],"internvl2-8b":[-0.552,0.114,47.49],"gemma-2-9b":[-0.553,0.104,52.35],"llama3.0-70b":[-0.557,0.11,54.78],"qwen2.5-1.5b-instruct":[-0.559,0.089,37.16],"llm-jp-4-vl-9b-beta":[-0.561,0.179,46.57],"tigerbot-70b-base":[-0.562,0.215,74.31],"internlm-xcomposer2-vl-7b":[-0.565,0.262,51.11],"llada-moe-7b-a1b-base":[-0.567,0.154,55.7],"molmo-7b-o":[-0.57,0.349,59.9],"vllm-sr-d3-lite":[-0.571,0.197,74.73],"deepseek-coder-v2-lite-base":[-0.581,0.128,60.58],"marin-8b-instruct":[-0.583,0.119,56.54],"internvl2-26b":[-0.585,0.103,46.69],"cogvlm-17b-chat":[-0.585,0.307,63.07],"gemma-3-pt-27b":[-0.599,0.13,63.75],"llama-3.2-3b":[-0.6,0.107,61.43],"dbrx-instruct-preview":[-0.605,0.154,56.67],"internlm2-math-plus-1.8b":[-0.606,0.16,44.9],"stablebeluga2-70b":[-0.607,0.139,66.02],"qwen-14b":[-0.617,0.128,70.7],"wizardmath-70b-v1.0":[-0.618,0.144,56.57],"aquila-vl-2b":[-0.619,0.229,44.65],"llada-8b-base":[-0.62,0.154,54.63],"chatglm3-6b":[-0.622,0.154,54.8],"qwen-vl-max":[-0.625,0.262,48.63],"bielik-11b-v3.0":[-0.628,0.179,67.71],"internvl-u":[-0.63,0.276,50.13],"bielik-11b-v2.0-instruct":[-0.63,0.181,66.2],"internvl2-40b":[-0.63,0.136,41.62],"vllm-sr-decision-2.0-sol-2b":[-0.632,0.197,71.9],"openchat-3.5-0106-gemma":[-0.632,0.179,67.41],"chatglm3-6b-base":[-0.638,0.154,53.57],"kanana-2-3b-base":[-0.639,0.154,52.96],"internlm2-math-base-20b":[-0.643,0.14,48.5],"llama-3.2-3b-base":[-0.644,0.091,37.09],"deepseek-llm-67b-base":[-0.645,0.121,65.47],"xverse-65b-2":[-0.649,0.154,55.93],"phi-4-multimodal-instruct":[-0.65,0.295,50.5],"qwen2.5-1.5b":[-0.653,0.075,33.81],"llama-3.1-8b-base":[-0.659,0.075,44.9],"skywork-13b-math":[-0.659,0.144,55.53],"solar-10.7b-instruct-v1.0":[-0.667,0.179,67.35],"internlm2-chat-7b":[-0.68,0.154,52.67],"qwen3-0.8b":[-0.683,0.085,27.26],"bielik-4.5b-v3-instruct":[-0.691,0.182,64.47],"llama-3.2-3b-instruct":[-0.697,0.101,46.71],"deepseek-coder-7b-instruct-v1.5":[-0.699,0.144,51.07],"qwen3.5-0.8b-thinking":[-0.7,0.113,42.69],"granite-4.0-h-1b":[-0.701,0.113,39.27],"qwen1.5-14b":[-0.701,0.14,56.31],"strands-decider-2b":[-0.701,0.197,70.87],"eurollm-9b-instruct-2512":[-0.701,0.119,52.98],"yi-1.5-6b":[-0.703,0.154,51.37],"internlm2.5-1.8b-chat":[-0.705,0.154,48.07],"internlm2-chat-7b-sft":[-0.706,0.154,51.93],"qwen-14b-chat":[-0.708,0.154,51.83],"grok-1":[-0.711,0.154,53.27],"internvl2.5-4b":[-0.711,0.139,40.58],"llama-2-70b-chat":[-0.715,0.215,69.71],"mobilemoe-l":[-0.718,0.118,58.47],"meta-llama-3-8b-instruct":[-0.718,0.179,65.5],"trida-7b":[-0.72,0.157,55.32],"mm1.5-3b":[-0.724,0.296,65.3],"internlm2-7b":[-0.733,0.153,44.73],"gemma-7b":[-0.739,0.127,62.53],"apertus-70b-instruct":[-0.741,0.078,37.76],"bielik-11b-v2":[-0.757,0.179,63.81],"llava-next-34b":[-0.77,0.262,58.58],"llama-3-8b-base":[-0.771,0.139,55.65],"deepseek-v2-lite-chat":[-0.79,0.08,48.77],"qwen2.5-coder-1.5b":[-0.792,0.144,48.88],"jamba-v0.1":[-0.795,0.179,63.9],"mobilellm-r1-950m-base":[-0.797,0.154,45.27],"kanana-2-1.3b-base":[-0.798,0.154,46.41],"internlm-20b":[-0.799,0.137,66.45],"qwen1.5-moe-a2.7b":[-0.803,0.154,48.63],"olmo-2-1124-7b-instruct":[-0.805,0.092,19.72],"command-r-08-2024":[-0.808,0.179,63.77],"gemma-1.1-7b-it":[-0.814,0.154,47.53],"gemma-3-1b-it":[-0.816,0.078,33.11],"marin-32b-mantis":[-0.817,0.127,59.87],"yi-34b":[-0.821,0.155,52.63],"qwen2-1.5b-instruct":[-0.825,0.105,36.7],"llama-2-70b":[-0.831,0.12,62.79],"granite-3.1-2b-instruct":[-0.832,0.11,40.16],"granite-3.2-2b-instruct":[-0.832,0.11,40.16],"granite-3.3-8b-base":[-0.834,0.153,58.2],"mm1-30b":[-0.844,0.296,64.57],"lfm2-1.2b":[-0.851,0.188,56.19],"qwen1.5-7b":[-0.852,0.139,51.4],"qwen3-0.6b-base":[-0.859,0.142,47.86],"codellama-34b":[-0.86,0.16,33.83],"qwen2.5-0.5b-instruct":[-0.861,0.085,23.12],"orion-14b-base":[-0.866,0.141,64.85],"llemma-34b":[-0.88,0.14,40.3],"deepseek-coder-6.7b-instruct":[-0.882,0.148,41.5],"qwen2-vl-2b-instruct":[-0.886,0.262,43.37],"map-neo-7b":[-0.888,0.139,56.53],"aquila2-34b":[-0.89,0.177,63.93],"telechat-12b":[-0.891,0.154,48.83],"deepseek-coder-33b-base":[-0.899,0.146,42.85],"internvl2.5-2b":[-0.899,0.107,39.34],"apertus-8b-instruct":[-0.908,0.078,30.35],"bielik-4.5b-v3":[-0.913,0.179,58.71],"starcoder2-15b":[-0.92,0.141,48.17],"deepseek-coder-7b-base-v1.5":[-0.921,0.141,42.44],"bitcpm-cann-1b":[-0.924,0.155,66.35],"internlm2-math-base-7b":[-0.924,0.16,33.67],"tigerbot-13b-chat":[-0.936,0.214,58.2],"qwen1.5-7b-chat":[-0.94,0.131,48.13],"olmoe-1b-7b-base":[-0.942,0.136,64.04],"qwen-vl-plus":[-0.942,0.262,43.31],"phi-3.5-vision-instruct":[-0.946,0.218,39.6],"mobilellm-r1-360m":[-0.946,0.142,26.5],"mobilemoe-m":[-0.947,0.118,51.99],"qwen2-vl-2b":[-0.949,0.229,38.98],"llama-3.2-1b-instruct":[-0.955,0.091,16.32],"mistral-7b":[-0.959,0.129,58.04],"qwen2-1.5b":[-0.96,0.128,47.97],"deepseek-v2-lite":[-0.968,0.107,57.12],"qwen-7b":[-0.97,0.127,55.18],"deepseek-llm-7b-chat":[-0.971,0.116,56.22],"mistral-7b-instruct-v0.2":[-0.972,0.127,61.44],"lfm2.5-vl-1.6b":[-0.981,0.18,37.57],"minicpm-2b-sft":[-0.984,0.127,55.39],"wizardmath-13b-v1.0":[-0.992,0.14,42.91],"minicpm-v-2.0-3b":[-0.998,0.296,60.77],"marin-32b-bison":[-0.998,0.127,56.37],"qwen2.5-0.5b":[-1.013,0.075,21.03],"gemma-2-7b":[-1.015,0.127,53.75],"mistral-7b-v0.1":[-1.017,0.116,54.45],"yi-9b":[-1.018,0.139,48.05],"llama-3.2-1.24b":[-1.023,0.107,27.47],"phi-2":[-1.025,0.143,54.15],"olmo-2-0425-1b-instruct":[-1.028,0.077,33.39],"minicpm-moe-8x2b":[-1.04,0.154,43.66],"olmoe-1b-7b":[-1.044,0.078,33.85],"smollm2-1.7b-instruct":[-1.049,0.077,32.51],"internvl2-4b":[-1.055,0.139,37.42],"internvl2.5-1b":[-1.056,0.139,31.32],"magpie-8b":[-1.056,0.178,42.77],"llama-1-65b":[-1.059,0.127,56.51],"skywork-13b-base":[-1.065,0.127,60.17],"intern-decision-0.8b":[-1.068,0.197,63.67],"tev1-0.8b-experimental":[-1.07,0.197,63.3],"deepseek-moe-16b-chat":[-1.073,0.118,52.07],"deepseek-vl-7b":[-1.074,0.191,41.42],"qwen3.5-0.8b":[-1.079,0.108,44.23],"minicpm-2b-dpo-fp32":[-1.083,0.127,53.89],"bluelm-7b-chat":[-1.093,0.154,38.67],"gemma-4-e4b":[-1.097,0.153,51.9],"falcon3-1b":[-1.104,0.084,22.93],"palm-540b":[-1.109,0.161,59.88],"qwen1.5-4b":[-1.109,0.154,41.03],"smolvlm2-2.2b":[-1.111,0.375,43.3],"internvl-chat-v1.5":[-1.12,0.139,35.64],"yi-6b-chat":[-1.121,0.141,53.4],"lfm2-700m":[-1.129,0.188,47.22],"gemma-3-1b":[-1.132,0.159,41.02],"solar-10.7b-v1.0":[-1.152,0.144,46.45],"baichuan2-13b-chat":[-1.155,0.154,40.64],"baichuan2-13b-base":[-1.164,0.127,53.73],"mistral-7b-v0.2":[-1.164,0.179,53.06],"t5gemma-2-4b-4b":[-1.165,0.122,49.88],"llemma-7b":[-1.176,0.14,31.28],"llava-1.6-13b":[-1.185,0.313,42.43],"janus-pro-7b":[-1.187,0.196,50.58],"llama-1-33b":[-1.198,0.127,52.89],"minicpm4-0.5b":[-1.207,0.155,57.82],"aquila2-7b":[-1.211,0.248,58.13],"tigerbot-13b-base":[-1.212,0.214,54.54],"stablelm-zephyr-3b":[-1.213,0.127,48.02],"qwen1.5-14b-chat":[-1.215,0.179,52.63],"llama-2-13b-chat":[-1.217,0.168,48.61],"deepseek-coder-6.7b-base":[-1.229,0.142,33.85],"qwen2-0.5b-instruct":[-1.241,0.154,30.63],"vllm-sr-decision-2.0-eos-0.8b":[-1.245,0.197,58.27],"mobilellm-p1-base":[-1.245,0.21,57.5],"internlm2-chat-1.8b":[-1.247,0.154,33.67],"palm-62b":[-1.253,0.21,59.37],"mobilellm-r1-360m-base":[-1.258,0.157,26.53],"mobilemoe-s":[-1.258,0.118,42.2],"minicpm-1b-sft":[-1.259,0.127,47.95],"telechat-7b":[-1.268,0.154,35.83],"vllm-sr-decision-2.0-kai-0.6b":[-1.272,0.197,57.57],"vllm-sr-d3-edge":[-1.279,0.197,57.93],"internlm2-base-7b":[-1.3,0.154,36.3],"qwen-7b-chat":[-1.307,0.128,45.38],"qwen-vl":[-1.313,0.288,60.03],"smollm2-1.7b-base":[-1.318,0.129,31.25],"internvl2-1b":[-1.321,0.139,26.32],"llava-1.5-13b":[-1.323,0.23,42.88],"sharegpt4v-7b":[-1.324,0.264,31.44],"internvl2-2b":[-1.332,0.105,31.54],"llama-2-13b":[-1.334,0.127,50.85],"llama-2-34b":[-1.346,0.154,37.01],"qwen-vl-chat":[-1.347,0.296,55.2],"llava-onevision-0.5b":[-1.348,0.295,36.6],"internlm-7b":[-1.36,0.13,46.75],"qwen2.5-coder-0.5b":[-1.368,0.14,31.58],"gemma-2-2b":[-1.37,0.135,41.17],"baichuan2-7b-chat":[-1.384,0.127,46.42],"starcoder2-7b":[-1.388,0.139,31.2],"bitcpm-cann-0.5b":[-1.41,0.155,51.43],"huginn-3.5b":[-1.424,0.14,29.2],"chatglm2-6b":[-1.425,0.127,44.47],"mistral-7b-instruct-v0.1":[-1.426,0.136,46.64],"qwen2-0.5b":[-1.427,0.141,31.15],"d1-omni-600m":[-1.43,0.197,53.83],"llama-3.2-1.24b-base":[-1.434,0.103,12.11],"codeqwen1.5-7b":[-1.436,0.139,31.12],"bielik-7b-instruct-v0.1":[-1.437,0.179,42.32],"qwen1.5-1.8b":[-1.439,0.127,41.14],"gpt-3":[-1.45,0.155,51.14],"internlm-chat-7b":[-1.456,0.154,31],"llama-2-7b-chat":[-1.462,0.127,47.97],"telechat-1b":[-1.468,0.154,26.83],"falcon-40b":[-1.47,0.127,46.86],"chatglm2-6b-base":[-1.475,0.154,29.07],"gemma-2b":[-1.477,0.132,38.93],"lfm2-350m":[-1.486,0.188,35.84],"baichuan-13b-base":[-1.495,0.116,43.35],"yi-6b":[-1.498,0.139,37.67],"bielik-7b-v0.1":[-1.501,0.179,39.3],"olmo-2-0425-1b-base":[-1.502,0.154,29.13],"bluelm-7b-base":[-1.53,0.154,29.53],"open-llama-13b":[-1.549,0.171,45.65],"olmo-1.7-7b":[-1.55,0.139,40.21],"llama-1-13b":[-1.582,0.128,44.28],"codellama-7b":[-1.591,0.131,32.43],"mobilellm-p1":[-1.605,0.122,35.34],"starcoder2-3b":[-1.609,0.142,25.8],"qwen-1.8b":[-1.609,0.127,39.24],"llava-1.5-7b":[-1.623,0.213,34.6],"vicuna-13b":[-1.628,0.154,28.16],"deepseek-llm-7b-base":[-1.632,0.116,40.65],"baichuan2-7b-base":[-1.651,0.127,39.52],"llama-2-7b":[-1.669,0.116,40.28],"gemma-4-e2b":[-1.672,0.138,43.13],"deepseek-moe-16b-base":[-1.678,0.116,37.73],"pythia-2.8b":[-1.684,0.198,60.6],"xverse-13b":[-1.702,0.134,40.68],"gemini-nano-2":[-1.719,0.21,34.8],"llama-3.2-1b":[-1.764,0.143,37.3],"mpt-30b":[-1.767,0.128,40.49],"pythia-1.4b":[-1.773,0.198,58.47],"mobilellm-r1-140m":[-1.775,0.146,5.9],"emu3-8b":[-1.84,0.262,38.25],"qwen1.5-0.5b":[-1.845,0.154,21.43],"pythia-1b":[-1.847,0.198,56.67],"gliner2.5-decide":[-1.851,0.197,41.47],"deepseek-vl-1.3b":[-1.853,0.203,27.2],"llama-1-7b":[-1.862,0.129,37.87],"pythia-12b":[-1.868,0.137,37.29],"deepseek-coder-1.3b-base":[-1.889,0.162,20.65],"mpt-7b":[-1.92,0.131,35.32],"pythia-6.9b":[-1.933,0.137,35.92],"amberchat":[-1.935,0.148,24.9],"vicuna-7b":[-1.938,0.154,21.8],"trlm-135m":[-1.939,0.223,26.05],"t5gemma-2-1b-1b":[-1.965,0.129,29.33],"olmo-7b-instruct":[-1.974,0.145,38.88],"falcon-7b":[-1.984,0.134,34.68],"lumina-dimoo":[-2.009,0.294,19.9],"chinese-alpaca-plus-13b":[-2.045,0.154,19.46],"pythia-410m":[-2.057,0.198,51.5],"baichuan-7b":[-2.057,0.154,18.33],"chatglm-6b":[-2.061,0.172,16.18],"laya":[-2.064,0.197,35.43],"amber-7b":[-2.142,0.153,17.32],"gemma-3-270m-it":[-2.146,0.113,20.86],"smollm2-360m-instruct":[-2.175,0.105,21.6],"smollm2-135m-instruct":[-2.208,0.145,2.8],"alpaca-7b":[-2.233,0.16,15.97],"pythia-160m":[-2.249,0.198,45.37],"smollm2-360m-base":[-2.361,0.143,8.18],"gemma-3-pt-270m":[-2.395,0.141,22.98],"olmo-7b":[-2.402,0.139,16.92],"t5gemma-2-270m-270m":[-2.41,0.14,19.55],"tinyllama-1.1b":[-2.416,0.14,23.25],"pythia-70m":[-2.476,0.198,38.43],"smollm2-135m-base":[-2.643,0.182,12.2],"gemma-3-pt-1b":[-2.657,0.166,9.7]},"benchmarks":[{"id":"mmlu","name":"MMLU","topic":"Multi-domain knowledge","difficulty":-1.401,"discrimination":0.792,"n":637},{"id":"gsm8k","name":"GSM8K","topic":"Math (grade-school)","difficulty":-1.062,"discrimination":1.729,"n":580},{"id":"math","name":"MATH","topic":"Math (competition)","difficulty":-0.199,"discrimination":1.968,"n":466},{"id":"arc-challenge","name":"ARC-Challenge","topic":"Science QA","difficulty":-1.371,"discrimination":1.36,"n":363},{"id":"aime-2025","name":"AIME 2025","topic":"Math (competition)","difficulty":0.83,"discrimination":2.785,"n":302},{"id":"math500","name":"MATH500","topic":"Math reasoning","difficulty":-0.441,"discrimination":1.91,"n":232},{"id":"aime-2024","name":"AIME 2024","topic":"Math (competition)","difficulty":0.729,"discrimination":2.83,"n":219},{"id":"ai2d","name":"AI2D","topic":"Diagram understanding (VQA)","difficulty":-2.661,"discrimination":0.587,"n":186},{"id":"arc-easy","name":"ARC-Easy","topic":"Science QA","difficulty":-2.198,"discrimination":1.39,"n":170},{"id":"mathvision","name":"MathVision","topic":"Math reasoning (multimodal)","difficulty":0.599,"discrimination":1.195,"n":155},{"id":"mathvista-mini","name":"MathVista-Mini","topic":"Math reasoning (multimodal)","difficulty":-0.764,"discrimination":0.706,"n":148},{"id":"mgsm","name":"MGSM","topic":"Math (multilingual)","difficulty":-1.019,"discrimination":1.116,"n":128},{"id":"openbookqa","name":"OpenBookQA","topic":"Science QA","difficulty":-1.993,"discrimination":0.2,"n":97},{"id":"mathvista","name":"MathVista","topic":"Multimodal math reasoning","difficulty":-1.141,"discrimination":0.602,"n":93},{"id":"cmath","name":"CMath","topic":"Math (Chinese)","difficulty":-1.162,"discrimination":1.508,"n":93},{"id":"hmmt-2025","name":"HMMT 2025","topic":"Math (competition)","difficulty":1.107,"discrimination":2.931,"n":87},{"id":"olympiadbench","name":"OlympiadBench","topic":"Math (olympiad)","difficulty":0.522,"discrimination":2.481,"n":77},{"id":"mathverse-mini","name":"MathVerse-mini","topic":"Math reasoning (multimodal)","difficulty":0.175,"discrimination":0.921,"n":69},{"id":"minerva-math","name":"Minerva Math","topic":"University-level math","difficulty":0.324,"discrimination":1.368,"n":67},{"id":"dynamath","name":"DynaMath","topic":"Math reasoning (video)","difficulty":0.082,"discrimination":0.77,"n":67},{"id":"amc-23","name":"AMC-23","topic":"Math (competition)","difficulty":0.011,"discrimination":1.919,"n":64},{"id":"wemath","name":"WeMath","topic":"Math reasoning","difficulty":0.488,"discrimination":1.071,"n":49},{"id":"gsm-plus","name":"GSM-Plus","topic":"Math (grade-school, enhanced)","difficulty":-0.41,"discrimination":1.414,"n":39},{"id":"omega","name":"OMEGA","topic":"Math (advanced)","difficulty":1.378,"discrimination":1.27,"n":38},{"id":"omni-math","name":"Omni-MATH","topic":"Math reasoning","difficulty":1.01,"discrimination":1.051,"n":31},{"id":"beyondaime","name":"BeyondAIME","topic":"Math (beyond AIME)","difficulty":1.24,"discrimination":1.622,"n":29},{"id":"sciq","name":"SciQ","topic":"Science QA","difficulty":-3.855,"discrimination":0.75,"n":25},{"id":"minif2f-test","name":"MiniF2F (Test)","topic":"Math competition","difficulty":2.462,"discrimination":0.304,"n":22},{"id":"astabench","name":"AstaBench","topic":"Agent evaluation","difficulty":2.161,"discrimination":1.628,"n":22},{"id":"mathverse-vision","name":"MathVerse-Vision","topic":"Math reasoning (multimodal)","difficulty":0.202,"discrimination":0.962,"n":20},{"id":"scienceqa","name":"ScienceQA","topic":"Science QA (multimodal)","difficulty":-2.488,"discrimination":0.909,"n":19},{"id":"omni-math-hard","name":"Omni-MATH-HARD","topic":"Math","difficulty":1.351,"discrimination":1.294,"n":18},{"id":"deepmind-math","name":"DeepMind Mathematics","topic":"Math reasoning","difficulty":-0.05,"discrimination":1.564,"n":13},{"id":"vct","name":"VCT","topic":"Virology capability (protocol troubleshooting)","difficulty":1.878,"discrimination":0.853,"n":12},{"id":"hiddenmath","name":"HiddenMath","topic":"Math reasoning","difficulty":0.362,"discrimination":1.404,"n":11}]},"faix-text":{"sd":0.434,"ext":{"gpt-6-astra":[2.508,0.069,90.49],"claude-fable-5.1":[2.328,0.072,88.44],"claude-fable-5":[2.312,0.06,76.47],"claude-opus-5":[2.301,0.063,87.14],"claude-mythos-5":[2.2,0.113,87.62],"gpt-5.6-sol":[2.169,0.061,72.66],"claude-opus-5.5":[2.127,0.172,86.37],"gpt-5.4-pro":[2.12,0.071,89.2],"gpt-5.5":[2.109,0.047,75.96],"claude-mythos-preview":[2.094,0.099,74.94],"muse-spark-1.2":[2.087,0.196,76.27],"ling-3.1-flash":[2.084,0.121,83.24],"kimi-k3":[2.028,0.067,74.41],"glm-5.3":[2.023,0.103,77.11],"gpt-5.4-xhigh":[1.998,0.084,85.76],"mirothinker-h1":[1.989,0.123,87.03],"qwen3.8-max":[1.985,0.11,72.31],"claude-opus-4.8":[1.984,0.05,76.21],"deepseek-v4.1-flash":[1.975,0.126,77.89],"fugu-ultra":[1.955,0.143,78.88],"claude-opus-4.6-high":[1.947,0.085,84.09],"claude-opus-4.6-max":[1.93,0.084,82.38],"gpt-5.4-thinking":[1.912,0.131,86.17],"claude-opus-4.7":[1.906,0.05,70.66],"gemini-3.1-pro":[1.898,0.047,69.61],"seed2.1-pro":[1.893,0.067,72.19],"hy4-preview":[1.889,0.152,86.3],"gemini-3.5-flash":[1.889,0.085,70.63],"muse-spark-open":[1.889,0.189,78.9],"seed2.1-turbo":[1.888,0.073,67.83],"ornith-1.5-397b":[1.875,0.105,85],"gpt-5.4":[1.871,0.046,72.59],"deepseek-v4-pro-0813":[1.851,0.11,80.47],"claude-sonnet-5":[1.846,0.077,69.9],"claude-opus-4.6":[1.845,0.043,72.11],"gpt-5.6-terra":[1.843,0.097,74.91],"fugu":[1.836,0.145,76.44],"dots3-note-preview":[1.827,0.095,82.44],"muse-spark-1.1":[1.823,0.177,73.4],"gpt-5.2-pro":[1.819,0.073,77.98],"gemini-4-argon":[1.818,0.31,91.19],"qwen3.8-flash-next":[1.813,0.07,79.17],"deepseek-v4-flash-0731":[1.812,0.059,77.32],"qwen3.8-omni-flash":[1.804,0.132,81.78],"deepseek-v4-pro-thinking-max":[1.804,0.054,77.93],"gpt-5.2-high":[1.8,0.054,76.5],"grok-4.2":[1.794,0.069,70.31],"glm-5.2":[1.791,0.056,76.02],"deepseek-v4-pro":[1.787,0.055,77.03],"gpt-5.6-luna":[1.779,0.06,74.95],"qwen3.7-max":[1.773,0.066,77.85],"gpt-5.3-codex":[1.768,0.097,75.13],"claude-sonnet-4.6-high":[1.768,0.085,78.07],"nex-n2-pro":[1.758,0.105,81.27],"glm-5.3-flash":[1.753,0.078,75.85],"beam":[1.752,0.086,76.3],"gemini-3.8-flash":[1.739,0.226,84.9],"ornith-1.0-397b":[1.72,0.1,77.95],"ornith-1.5-122b":[1.701,0.108,73.56],"kimi-k2.6-thinking":[1.7,0.056,76.03],"gpt-5.2-extra-high":[1.694,0.092,75.1],"claude-sonnet-4.6":[1.694,0.056,71.23],"sage-a1.5":[1.694,0.134,70.35],"minimax-m3":[1.693,0.08,73.65],"hy3":[1.689,0.067,75.33],"qwen3.7-plus":[1.685,0.071,75.49],"gpt-6.1-sol":[1.679,0.213,87.54],"gpt-5.2-thinking-xhigh":[1.674,0.056,66.83],"k2-horizon-375b-a23b":[1.672,0.11,69.3],"kimi-k2.6":[1.671,0.076,76.62],"muse-spark":[1.664,0.078,64.74],"apodex-1.0":[1.66,0.121,72.47],"gpt-5.2":[1.658,0.043,71.27],"bigbang-v1":[1.657,0.115,66.32],"gpt-5.2-thinking":[1.649,0.058,75.81],"mirothinker-1.7":[1.646,0.123,77.33],"deepseek-v4-pro-thinking":[1.642,0.082,76.95],"intern-s2-397b":[1.637,0.188,73.8],"longcat-2.0":[1.63,0.129,83.98],"inkling-small":[1.628,0.057,75.26],"deepseek-v3.2-speciale":[1.625,0.146,80.6],"inkling":[1.624,0.061,69.59],"claude-opus-4.5-thinking":[1.62,0.07,68.01],"agents-a1":[1.618,0.095,69.5],"gemini-3-pro":[1.614,0.036,72.78],"claude-opus-4.5":[1.607,0.036,72.28],"glm-5.1":[1.603,0.052,74.11],"seed2.0-pro":[1.603,0.054,73.53],"deepseek-v4-flash-thinking-max":[1.598,0.065,73.97],"mimo-v2-pro":[1.596,0.114,74.9],"jais-3-375b-a23b":[1.594,0.116,70.43],"intern-s2-preview-397b":[1.594,0.188,73.51],"kat-coder-pro-v2":[1.593,0.104,71.78],"qwen3.6-plus":[1.592,0.068,74.58],"grm-3.2-sky":[1.59,0.132,89.22],"qwen3.5-397b-a17b":[1.586,0.052,72.81],"deepseek-v4-flash":[1.584,0.055,71.51],"kimi-k2.7-code":[1.579,0.149,71.29],"qwen3.6-max-preview":[1.577,0.152,58.3],"grok-4.5":[1.577,0.232,77.92],"mirothinker-v1.5-235b":[1.575,0.121,77.6],"gemini-3-pro-preview":[1.574,0.049,76.71],"mercury-3":[1.563,0.195,76.02],"motif-3":[1.558,0.121,74.23],"mirothinker-1.7-mini":[1.543,0.123,73.5],"longcat-flash-thinking-2601":[1.535,0.076,73.25],"ring-2.6-1t-xhigh":[1.534,0.074,74.13],"muse-glimmer-30b":[1.522,0.079,72.64],"openpangu-2.0-pro-thinking":[1.518,0.084,76.33],"ax-k2":[1.513,0.133,75.86],"ling-3.0-flash":[1.512,0.096,76.72],"gpt-6-sol":[1.511,0.289,87.32],"snowdon-1.1-small":[1.496,0.146,85.91],"gpt-5.2-medium":[1.492,0.076,67.09],"gemini-3.5-flash-lite":[1.491,0.118,73.46],"gemini-3-flash":[1.477,0.046,66.01],"nemotron-3.5-super-vl-120b-a12b":[1.471,0.076,73.07],"mimo-v2.5-pro":[1.467,0.122,80.15],"iquest-coder-v1-40b-loop-thinking":[1.464,0.157,91.3],"ornith-1.5-35b-a3b":[1.461,0.098,64.84],"areal-sea-235b-a22b":[1.454,0.145,81],"gpt-5.4-mini":[1.454,0.061,69.55],"kimi-k2.5":[1.453,0.05,66.18],"hy3-preview":[1.452,0.091,68.65],"nemotron-3-ultra":[1.45,0.062,72.03],"deepseek-v4-flash-thinking":[1.445,0.082,71.4],"qwen3.8-27b":[1.445,0.057,75.86],"kimi-k2.5-thinking":[1.442,0.047,66.28],"seed2.0-lite-0428":[1.441,0.088,66.41],"longcat-flash-thinking-zigzag":[1.44,0.079,76.09],"glm-5":[1.435,0.048,69.08],"minimax-m2.7":[1.427,0.06,69.77],"mimo-v2.5":[1.426,0.082,65.97],"step-3.5-flash-20260204":[1.42,0.076,67.06],"nemotron-3.5-bolt-74b-a9b":[1.418,0.121,65.26],"step-3.7-flash":[1.418,0.09,73.62],"qwen3.6-27b":[1.415,0.08,70.72],"gpt-5":[1.412,0.036,68.09],"gemini-3.6-flash":[1.412,0.226,69.34],"seed1.8":[1.41,0.061,70.01],"gpt-5-pro":[1.409,0.082,65.98],"gpt-5.1-thinking":[1.402,0.084,58.91],"ornith-1.0-35b":[1.401,0.098,62.82],"claude-sonnet-4.5":[1.4,0.037,67.72],"gpt-5.1-high":[1.399,0.059,59.77],"gpt-5-codex":[1.397,0.088,61.97],"comet-60b-a12b-fp8":[1.388,0.095,70.84],"iquest-coder-v1-40b-thinking":[1.385,0.156,83.94],"glm-4.7-thinking":[1.382,0.088,65.39],"ring-1t-2.5":[1.38,0.098,59.87],"seed2.0-lite":[1.379,0.054,68.3],"kimi-k2-thinking":[1.378,0.051,67.76],"flint":[1.377,0.156,84.7],"mai-thinking-1":[1.375,0.114,68.84],"openpangu-2.0-flash-thinking":[1.372,0.084,71.95],"flint-nvfp4":[1.372,0.156,84.4],"deepseek-v3.2-thinking":[1.371,0.045,64.33],"gpt-5.1":[1.371,0.059,68.41],"qwen3-max-thinking":[1.368,0.062,71.37],"qwen3.6-35b-a3b":[1.365,0.052,69.78],"gpt-5-thinking":[1.365,0.074,58.68],"mirothinker-v1.5-30b":[1.362,0.121,70.55],"comet-60b-a12b":[1.359,0.095,70.21],"solar-pro-4":[1.358,0.104,74.84],"qwen3.5-122b-a10b":[1.354,0.054,67.41],"gpt-5-high":[1.352,0.039,65.53],"raon-1-mini-preview":[1.348,0.109,69.82],"nemotron-3.5-super-vl-120b-a12b-nvfp4":[1.345,0.099,69.58],"gpt-5-thinking-high":[1.343,0.104,74.1],"nex-n2-mini":[1.343,0.085,60.67],"ernie-5.0":[1.343,0.077,81.56],"laguna-m.1":[1.335,0.122,59.22],"ring-2.6-1t-high":[1.335,0.116,79.93],"gpt-5-codex-high":[1.334,0.125,64.55],"comet-60b-a12b-nvfp4":[1.333,0.098,69.29],"gpt-6-luna-medium":[1.333,0.08,59.51],"pacore-8b":[1.33,0.127,73.23],"minimax-m2.5":[1.329,0.069,58.06],"mimo-v2-flash":[1.317,0.073,65.34],"oxcoder-9b":[1.312,0.115,68.62],"gpt-5-medium":[1.311,0.067,62.96],"solar-open-2-250b":[1.302,0.09,67.38],"mercury-2.5":[1.297,0.146,59.8],"xing4.0-29b-a4b":[1.296,0.148,67.92],"mai-code-1-flash":[1.282,0.103,66.57],"o3":[1.275,0.041,64.71],"agnes-3.0-flash-preview":[1.264,0.195,66.41],"qwen3.5-35b-a3b":[1.262,0.052,65.03],"minimax-m2.1":[1.259,0.066,62.68],"gemini-3-flash-preview":[1.252,0.096,76.54],"qwen3.5-27b":[1.25,0.048,71.49],"nanbeige4.2-3b":[1.247,0.086,63.19],"nova-2-pro":[1.237,0.101,73.88],"longcat-flash-prover":[1.235,0.111,73.4],"mirothinker-v1.0-72b":[1.235,0.128,61.53],"claude-opus-4.1":[1.235,0.055,59.71],"mistral-medium-3.5":[1.234,0.082,63.11],"spark-x2.6-4b":[1.229,0.092,65.16],"grok-4":[1.228,0.045,64.86],"ring-1t":[1.228,0.104,68.44],"deepseek-v3.2":[1.223,0.039,65.08],"trinity-large-thinking":[1.221,0.134,73.68],"gpt-5-mini-high":[1.219,0.047,65.92],"qwen3-moe-2507":[1.215,0.124,80],"claude-4.5-sonnet-thinking":[1.214,0.049,60.71],"kat-coder-v2.5-dev":[1.211,0.162,58.87],"ling-2.6-1t":[1.206,0.098,58],"glm-4.7":[1.205,0.065,70.42],"o3-pro-high":[1.204,0.078,61.27],"intern-s2-preview":[1.2,0.173,68.13],"claude-haiku-5.5-medium":[1.199,0.08,55.52],"qwen3.8-27b-ud-q4-k-xl":[1.194,0.106,85.95],"laguna-xs.2":[1.19,0.122,53.58],"o3-pro":[1.185,0.081,49.7],"kolibri-1":[1.185,0.09,74.83],"gpt-5.4-nano":[1.153,0.089,62.4],"claude-sonnet-4-thinking":[1.146,0.097,66.36],"tongyi-deepresearch":[1.142,0.122,62.9],"k2-horizon-7b":[1.141,0.1,58.67],"devstral-2":[1.139,0.133,55.37],"gpt-5-mini":[1.137,0.042,63.19],"grok-4-fast":[1.134,0.067,64.67],"ornith-1.0-9b":[1.132,0.1,56.83],"ring-1t-preview":[1.132,0.087,68.3],"gpt-5.1-medium":[1.131,0.082,43.4],"openpangu-2.0-pro":[1.129,0.094,67.07],"ternary-bonsai-2-27b":[1.127,0.109,86.37],"longcat-flash-thinking":[1.127,0.139,66.6],"o3-2025-04-16":[1.124,0.154,60.64],"gemini-3.7-flash":[1.124,0.336,75.35],"openai-deepresearch":[1.124,0.123,53.93],"o3-high":[1.123,0.051,57.35],"vibethinker-3b":[1.122,0.141,71.38],"k2-horizon-32b":[1.12,0.214,62.9],"gpt-5-low":[1.119,0.073,57.41],"north-mini-code-1.0":[1.119,0.103,47.23],"nova-2-omni":[1.117,0.155,76.22],"ling-2.5-1t":[1.108,0.097,58.39],"claude-opus-4-thinking":[1.107,0.104,72.46],"neohorse-1-9b":[1.106,0.142,72.2],"k-exaone-2.0":[1.104,0.113,69.11],"gemini-3.1-flash-lite":[1.104,0.103,65.39],"claude-4.5-haiku":[1.101,0.048,61.32],"nemotron-labs-dory1.0-4b-4loop":[1.1,0.154,64.21],"nemotron-3-super-120b-a12b":[1.1,0.059,65.39],"qwen3-coder-next":[1.094,0.101,58.95],"intern-s1-pro":[1.093,0.136,65.11],"gpt-5.4-none":[1.089,0.087,54.09],"nanbeige4.1-3b":[1.089,0.154,71.53],"deepseek-v3-0528":[1.085,0.133,80.95],"grok-4-0709":[1.081,0.245,65.62],"gemini-2.5-pro":[1.077,0.031,59.5],"minimax-m2":[1.074,0.053,61.72],"o4-mini":[1.072,0.052,51.56],"k2-horizon-mova-36b-a4b":[1.065,0.214,62],"nemotron-labs-dory1.0-4b":[1.062,0.154,63.16],"gpt-5-2025-08-07":[1.058,0.151,56.53],"keye-vl-2.0-30b-a3b":[1.057,0.145,57.7],"laguna-xs-2.1":[1.057,0.112,53.81],"qwen3-235b-a22b-thinking-2507":[1.056,0.044,64.51],"qwen3-coder-plus":[1.056,0.107,43.62],"ornith-1.5-9b":[1.052,0.09,60.14],"gemini-2.5-pro-preview-03-25":[1.052,0.134,67.6],"qwen3.5-omni-plus":[1.048,0.116,65.52],"o3-medium":[1.048,0.089,52.85],"deepseek-v3.1-terminus-thinking":[1.045,0.078,55.46],"glm-4.6":[1.044,0.052,61.4],"exaone-4.5-33b-thinking":[1.042,0.097,72.92],"telechat3-coder-36b-thinking":[1.039,0.121,69.55],"grok-3-mini-fast-high-reasoning":[1.038,0.115,80.8],"gemma-4-31b-it":[1.03,0.057,71.72],"grok-4-fast-thinking":[1.027,0.076,45.6],"qwen3-coder-480b-a35b":[1.027,0.089,37.47],"sarvam-105b":[1.026,0.086,74.65],"deepseek-v3.1-terminus":[1.023,0.053,55.46],"agents-a1-4b":[1.023,0.124,63.12],"o4-mini-high":[1.022,0.06,57.76],"openpangu-r-72b-2512-slow-thinking":[1.021,0.096,72.97],"gemma-4-26b-a4b-it":[1.019,0.056,61.86],"deepseek-v3.1-thinking":[1.012,0.06,55.15],"iquest-coder-v1-40b-instruct":[1.01,0.077,70.65],"gpt-5.3-instant":[1.009,0.229,55.27],"ling-1t":[1.007,0.075,56.67],"qwen3-next-80b-a3b-thinking":[1.003,0.05,68.86],"command-a-plus-05-2026":[0.998,0.093,56.43],"kimi-k2-0905-preview":[0.996,0.079,39.73],"longcat-flash-lite-sparse":[0.995,0.07,63.46],"k-exaone":[0.995,0.073,66.68],"nemotron-labs-3-puzzle-75b-a9b":[0.994,0.088,65.18],"gpt-5-mini-medium":[0.988,0.067,50.09],"intern-s2-mobius":[0.988,0.194,66.25],"gpt-oss-120b-high":[0.982,0.069,66.38],"claude-opus-4.1-20250805":[0.978,0.124,67.55],"claude-haiku-5.5":[0.976,0.185,73.1],"claude-3.7-sonnet-20250219":[0.975,0.109,70.71],"iquest-coder-v1-40b-loop-instruct":[0.968,0.077,72.34],"openpangu-2.0-flash":[0.967,0.106,63.72],"grok-code-fast-1":[0.967,0.088,56.56],"claude-opus-4-1-20250805-thinking":[0.966,0.178,85.03],"qwen3-max":[0.965,0.079,49.05],"deepseek-tng-r1t2-chimera":[0.965,0.132,78.3],"g9v3-39a5b":[0.962,0.214,58.83],"qwen3-vl-32b-thinking":[0.956,0.078,76.75],"underdog-saluki-27b-1.0":[0.953,0.24,77.92],"zdtaichu5.0-9b":[0.952,0.147,79.6],"claude-sonnet-4":[0.951,0.037,59.03],"o3-mini-2025-01-31-high":[0.949,0.101,68.96],"glm-4.5v":[0.942,0.19,56.13],"claude-3.7-sonnet-thinking":[0.94,0.122,76.49],"grok-4.1-fast":[0.94,0.073,52.75],"qwen3-max-instruct-preview":[0.937,0.087,64.54],"qwen3-coder-480b-a35b-instruct":[0.936,0.062,67.56],"ring-flash-2.0":[0.935,0.102,58.11],"kimi-k2-instruct-0711":[0.935,0.105,52.12],"gemini-2.5-pro-preview-06-05":[0.934,0.069,47.82],"kimi-k2-instruct-0905":[0.931,0.061,69.46],"claude-opus-4":[0.931,0.044,62.6],"kimi-k2-0711-preview":[0.926,0.148,40.77],"cogito-671b-v2.1":[0.923,0.117,70.03],"nova-2-lite":[0.92,0.089,60.44],"seed-oss-36b-instruct":[0.92,0.099,61.87],"gpt-5.4-nano-high":[0.919,0.087,31.22],"iterresearch-30b-a3b":[0.916,0.136,51.17],"spark-x2.5-4b":[0.915,0.074,56.38],"intellect-3":[0.915,0.121,79.98],"kimi-k2-instruct":[0.914,0.043,62.39],"qwen3-vl-235b-a22b-thinking":[0.913,0.09,62.1],"qwen-3-235b-a22b-thinking":[0.909,0.076,75.09],"o4-mini-medium":[0.901,0.078,51.65],"neohorse-1-4b":[0.897,0.142,68.41],"deepseek-r1-0528":[0.892,0.046,57.39],"nemotron-cascade-2-30b-a3b":[0.888,0.11,65.78],"glm-4.5":[0.888,0.052,54.87],"devstral-small-2":[0.886,0.1,38.31],"jev-1.13":[0.884,0.132,87.8],"lfm2.5-24b-a2b":[0.881,0.124,72.86],"openreasoning-nemotron-32b":[0.878,0.115,66.77],"deepseek-v3.2-exp":[0.877,0.049,65.71],"o1":[0.874,0.072,72.65],"qwen3-235b-2507":[0.872,0.104,58.59],"iquest-coder-v1-14b-thinking":[0.869,0.121,59.85],"gpt-oss-120b":[0.868,0.041,59.39],"ring-flash-linear-2.0":[0.868,0.102,55.34],"dots-vlm1":[0.868,0.175,44.09],"o1-2024-12-17-high":[0.867,0.117,64.43],"jev-1.14":[0.862,0.132,88.03],"longcat-flash-lite":[0.86,0.08,68.88],"seed2.0-mini":[0.858,0.068,61.54],"kimi-k2":[0.855,0.056,49.11],"minimax-m1-80k":[0.853,0.08,64.52],"hy-2.0-thinking":[0.851,0.106,49.7],"mirothinker-v1.0-8b":[0.851,0.136,50.63],"gemma-4-12b-it":[0.851,0.063,56.31],"seed1.6-thinking":[0.85,0.218,60.93],"granite-4.2-30b":[0.849,0.093,61.44],"claude-3.7-sonnet":[0.843,0.05,60.9],"nemotron-labs-dory1.0-4b-1loop":[0.841,0.154,56.82],"gemini-2.5-flash-thinking":[0.838,0.057,65.32],"joyai-llm-flash":[0.833,0.071,72.46],"o3-mini-2025-01-31-med":[0.833,0.106,66.78],"gpt-oss-swallow-120b-rl-v0.1":[0.831,0.14,78.78],"clef-flash":[0.831,0.142,86],"gpt-oss-120b-medium":[0.831,0.07,67.16],"ling-3.0-tiny":[0.831,0.184,60.61],"o3-mini":[0.83,0.059,61.64],"diffusiongemma-26b-a4b":[0.829,0.143,69.8],"grok-3-beta-think":[0.827,0.113,64.83],"rlvr-8b-0926":[0.816,0.127,59.77],"gpt-4.1-2025-04-14":[0.815,0.147,54.1],"clef-omni":[0.81,0.14,85.99],"qwen3.5-9b":[0.801,0.047,63.55],"openreasoning-nemotron-14b":[0.801,0.115,63.57],"deepseek-v3.1":[0.795,0.05,67.18],"minicpm5-2b":[0.791,0.083,65.15],"qwen3.5-4b":[0.791,0.049,62.59],"golongrl-30b-a3b":[0.79,0.192,71.62],"qwen3-vl-235b-a22b":[0.79,0.117,48.99],"seed-thinking-v1.5":[0.787,0.076,61.75],"qwen3-30b-a3b-2507":[0.787,0.105,61.36],"o1-2024-12-17":[0.786,0.07,69.72],"k2-think":[0.786,0.095,57.35],"ax-k1":[0.785,0.11,66.55],"claude-opus-4-20250514":[0.784,0.079,44.18],"ling-2.6-flash":[0.784,0.112,52.89],"qwen3-235b-a22b":[0.783,0.038,64.74],"qwen3-swallow-32b-rl-v0.2":[0.777,0.128,79.1],"gemini-2.5-pro-exp-03.25":[0.777,0.148,75.64],"minimax-m1-40k":[0.776,0.08,63.57],"glm-4.5-air":[0.776,0.05,61.99],"qwen3-30b-a3b-thinking-2507":[0.775,0.049,63.54],"nemotron-3-nano-30b-a3b":[0.774,0.063,64.69],"qwen3-14b-thinking":[0.774,0.081,70.16],"qwenlong-l1.5-30b-a3b":[0.772,0.192,71.17],"nemotron-32b":[0.771,0.095,51.24],"qwen3-next-80b-a3b":[0.762,0.109,55.9],"qwen3-vl-32b-instruct":[0.76,0.076,69.55],"k2-horizon-3.7b":[0.759,0.129,49.28],"o3-mini-high":[0.758,0.056,52.5],"kimi-k2-0905":[0.757,0.055,49.02],"gemini-2.5-flash":[0.754,0.036,54.35],"apriel-1.6-15b-thinker":[0.753,0.075,56.02],"grok-3-mini-fast-low-reasoning":[0.746,0.115,75.83],"mercury-2":[0.745,0.106,54.09],"deepseek-r1":[0.741,0.041,60.06],"openpangu-r-72b-2512-fast-thinking":[0.739,0.093,67.29],"qwen3-vl-30b-a3b-thinking":[0.739,0.085,69.71],"granite-4.2-8b":[0.734,0.087,58.67],"mellum2.1-12b-a2.5b-thinking":[0.733,0.113,78.9],"pulsar-16b":[0.733,0.213,72.33],"gpt-oss-swallow-120b-sft-v0.1":[0.731,0.128,79.8],"clef":[0.729,0.138,84.51],"mistral-small-4-thinking":[0.726,0.083,65.57],"qwen3-vl-8b-thinking":[0.725,0.074,70.96],"o3-mini-medium":[0.725,0.065,45.72],"sarvam-30b":[0.723,0.08,69.91],"o1-preview-2024-09-12":[0.722,0.079,82.84],"llada2.2-flash":[0.721,0.142,40.16],"olmo-3.1-think-32b":[0.721,0.058,72.99],"nemotron-cascade-14b-thinking":[0.719,0.094,70.75],"telechat3-36b-thinking":[0.718,0.111,73.92],"glm-4.7-flash":[0.716,0.063,64.89],"claude-sonnet-4-20250514":[0.711,0.069,36.86],"ring-mini-2.0":[0.711,0.107,50.31],"minicpm-v-4.7-35b-a3b":[0.71,0.161,67.83],"qwen3-next-80b-a3b-instruct":[0.71,0.054,63.07],"o4-mini-low":[0.707,0.082,29.64],"gemini-2.5-flash-preview-09-2025":[0.703,0.074,52.61],"qwen3-omni-flash-thinking":[0.699,0.13,72.94],"llada2.1-flash-q":[0.697,0.067,75.25],"agentcpm-explore":[0.697,0.136,45.6],"longcat-next":[0.692,0.095,58.97],"ernie-4.5":[0.692,0.071,78.77],"grok-3-mini-beta":[0.689,0.199,72.09],"o4-mini-2025-04-16":[0.687,0.124,59.52],"gemini-2.5-flash-preview-05-20":[0.687,0.069,40.64],"minimax-m1":[0.684,0.167,70.87],"qwen3-235b-a22b-instruct-2507":[0.683,0.052,57.66],"qwen3-235b-a22b-2507":[0.681,0.136,44.4],"qwen3-32b-thinking":[0.676,0.046,61.86],"nemotron-labs-3-elastic-30b-a3b":[0.674,0.118,61.43],"gpt-oss-swallow-20b-rl-v0.1":[0.672,0.128,77.5],"gpt-5-chat":[0.669,0.22,54.73],"deepseek-v3-0324":[0.668,0.053,60.8],"qwen3-omni-30b-a3b-thinking":[0.667,0.13,72.32],"st-moe-32b":[0.665,0.207,94.27],"yuan3.0-ultra":[0.664,0.37,59.2],"olmo-3-think-32b-dpo":[0.662,0.059,72.17],"nemotron-cascade-8b":[0.661,0.093,69.18],"vllm-sr-d3":[0.661,0.134,84.71],"openthinkeragent-32b":[0.657,0.109,37.53],"gpt-4.1":[0.656,0.038,62.44],"llada2.1-flash-s":[0.655,0.064,74.14],"gpt-5-nano-high":[0.653,0.075,34.45],"mirothinker-v0.2-32b":[0.651,0.128,36.9],"gemini-2.5-flash-preview-05-20-thinking":[0.651,0.119,64],"mistral-large-3":[0.65,0.145,61.06],"hypernova-60b-2605":[0.644,0.084,52.46],"llada2.0-flash":[0.643,0.055,78.05],"gka-primed-hqwen3-32b-reasoner":[0.642,0.167,52.89],"motif-2-12.7b-reasoning":[0.642,0.074,80.52],"gpt-oss-20b-medium":[0.64,0.091,66.89],"exaone-4.0-32b-thinking":[0.637,0.102,62.02],"claude-4.5-haiku-thinking":[0.636,0.128,56.25],"magistral-medium-1.2":[0.634,0.085,52.8],"solar-open-100b":[0.634,0.083,55.71],"o1-preview":[0.634,0.075,82.86],"vega-v2":[0.631,0.207,93.73],"gpt-5-mini-low":[0.631,0.079,24.83],"pplx-decider-v1.2":[0.63,0.133,84.1],"gpt-oss-20b":[0.628,0.047,58.45],"o1-mini":[0.628,0.061,71.81],"hunyuan-7b-instruct":[0.627,0.144,68.5],"gpt-oss-20b-a4b":[0.626,0.138,52.12],"abeja-qwq32b-reasoning-japanese-v1.0":[0.625,0.128,76.38],"codex-mini-latest":[0.624,0.085,13.31],"nemotron-cascade-8b-thinking":[0.623,0.094,68.85],"grok-code-fast":[0.622,0.143,46.65],"magistral-medium":[0.621,0.096,46.68],"openpangu-r-7b-2512-slow-thinking":[0.621,0.091,63.74],"gemma-4-26b-a4b":[0.62,0.099,70.47],"hyperclovax-seed-think":[0.619,0.116,47.5],"llama-4-behemoth":[0.617,0.123,77.34],"mimo-v2.5-pro-base":[0.614,0.079,80.11],"gpt-4.5":[0.613,0.068,64.88],"olmo-3-think-32b":[0.61,0.063,72.32],"nvidia-nemotron-nano-9b-v2":[0.606,0.061,70.58],"motif-2-12.7b-instruct":[0.605,0.074,78.32],"qwen3-30b-a3b-instruct-2507":[0.603,0.046,68.59],"apriel-1.5-15b-thinker":[0.602,0.06,48.72],"o3-mini-2025-01-31-low":[0.602,0.105,60.88],"gpt-5-minimal":[0.598,0.064,48.6],"k2-high-70b":[0.592,0.092,74.49],"apriel-1.5-15b-thinker-self-reported":[0.59,0.104,50.68],"qwen3-omni-flash-instruct":[0.59,0.107,71.98],"qwen3-swallow-32b-sft-v0.2":[0.589,0.128,75.88],"gpt-5-nano-medium":[0.586,0.078,9.3],"qwen3-32b":[0.586,0.039,61.76],"hairuo":[0.585,0.207,93.97],"grok-3-mini":[0.584,0.081,42.52],"zaya1-8b":[0.583,0.149,70.39],"autotrust-jev-35b":[0.582,0.134,81.55],"ling-flash-2.0":[0.58,0.058,77.37],"qwen3.5-omni-flash":[0.578,0.119,57.23],"deepseek-v3":[0.576,0.044,69.58],"nemotron-nano-v2-9b":[0.574,0.108,76.67],"olmo-3-think-32b-sft":[0.572,0.059,70.12],"falcon-h1r-7b":[0.57,0.071,60.95],"gpt-oss-120b-low":[0.569,0.182,56.51],"gpt-5-nano":[0.566,0.07,45.7],"nemotron-research-goosereason-4b-instruct":[0.563,0.092,75.13],"deepseek-r1-distill-qwen-32b":[0.562,0.075,64.48],"grok-3-mini-beta-low":[0.56,0.076,17.21],"qwen3-swallow-32b-cpt-v0.2":[0.554,0.128,76.04],"qwen3-32b-thinking-2504":[0.549,0.102,48.66],"phi-4-reasoning-plus":[0.549,0.079,54.39],"gpt-4.5-preview":[0.547,0.118,57.2],"nvidia-nemotron-3-nano-30b-a3b-bf16":[0.545,0.066,49.42],"claude-3.5-sonnet-20241022":[0.544,0.051,69.87],"gpt-5.2-none":[0.542,0.08,23.45],"telechat3-105b-a4.7b-thinking":[0.541,0.111,70.51],"ministral-3-r-8b":[0.539,0.111,70.55],"step3-vl-10b":[0.536,0.147,69.68],"gpt-oss-20b-high":[0.535,0.087,59.08],"minicpm-sala":[0.534,0.104,78.52],"superapriel-15b-instruct":[0.533,0.115,77.43],"grok-3":[0.532,0.073,55.66],"plamo-3.0-prime-thinking":[0.529,0.17,56.06],"qwen3-swallow-30b-a3b-rl-v0.2":[0.527,0.128,73.2],"gpt-oss-swallow-20b-sft-v0.1":[0.526,0.128,74.9],"nemotron-3.5-lightning-30b-a3b":[0.526,0.07,65.84],"glm-4.6v":[0.516,0.103,49.89],"qwen3-vl-30b-a3b-instruct":[0.516,0.082,59.2],"qwen3-coder-30b-a3b-instruct":[0.516,0.071,55.69],"gpt-5-mini-minimal":[0.513,0.085,31.67],"openreasoning-nemotron-7b":[0.511,0.067,55.17],"kolibri-origin":[0.511,0.1,57.91],"o1-mini-2024-09-12":[0.51,0.065,72.69],"grok-3-beta":[0.51,0.075,66.01],"minicpm4.1-8b":[0.508,0.095,78.22],"gemini-2.0-pro":[0.506,0.094,67.05],"glm-4.1v":[0.505,0.19,46.3],"glide-no-thinking":[0.504,0.132,81.29],"gemini-2.0-flash":[0.5,0.078,53.41],"deepseek-r1-0120":[0.498,0.121,59.7],"llama-3.1-405b":[0.497,0.089,73.08],"qwq-bakeneko-32b":[0.495,0.128,74.84],"llama-3.1-tulu-3-405b":[0.491,0.105,80.01],"qwq-32b":[0.489,0.065,56.9],"nanbeige4-3b-thinking-2511":[0.485,0.141,51.73],"hypernova-60b-2602":[0.479,0.084,46.53],"gpt-5.4-mini-none":[0.468,0.146,48.65],"kanana-2-30b-a3b-thinking":[0.468,0.154,64.38],"iquest-coder-v1-14b-instruct":[0.463,0.133,47.98],"qwen3-omni-30b-a3b-instruct":[0.46,0.089,66.06],"llama-4-maverick-17b-128e-instruct":[0.455,0.103,62.19],"claude-3.5-sonnet":[0.454,0.074,75.64],"magistral-medium-2506":[0.454,0.074,40.48],"apriel-nemotron-15b-thinker":[0.45,0.123,75.9],"qwen3-30b-a3b":[0.45,0.044,65.34],"deepseek-r1-lite-preview":[0.45,0.093,61.16],"golongrl-4b":[0.443,0.192,63.54],"kanana-2-30b-a3b-thinking-2601":[0.443,0.154,64.16],"vllm-sr-d3-flash":[0.441,0.134,80.17],"gpt-4.1-mini":[0.44,0.052,41.08],"mellum2-12b-a2.5b-thinking":[0.44,0.12,68.49],"deepseek-r1-distill-llama-70b":[0.439,0.166,57.08],"instella-moe-16b-a3b-think":[0.437,0.109,72.83],"phi-4-reasoning":[0.436,0.115,59.75],"midm-k-2.5-pro":[0.434,0.157,47.57],"qwen3-8b-thinking":[0.433,0.055,59.55],"tri-21b-think":[0.432,0.106,61.71],"gka-primed-hqwen3-8b-reasoner":[0.431,0.168,46.5],"claude-3.5-sonnet-20240620":[0.431,0.06,75.04],"olmo-3-think-7b":[0.43,0.059,66.11],"acereason-nemotron-1.1":[0.427,0.115,50.73],"lg-exaone-32b":[0.426,0.125,75.59],"mistral-medium-3":[0.425,0.074,67.44],"trinity-large-preview":[0.424,0.165,56.92],"deepseek-r1-0528-qwen3-8b":[0.423,0.088,49.1],"deberta-turingnlrv4":[0.423,0.207,93.03],"turing-nlr-v5":[0.42,0.207,93.7],"vibethinker-1.5b":[0.42,0.109,51.02],"o3-mini-2025-01-31":[0.419,0.153,56.42],"autotrust-gev-26b-decide":[0.418,0.135,80.16],"llama-3.1-tulu-3-405b-dpo":[0.416,0.112,78.98],"olmo-3-think-7b-dpo":[0.414,0.072,62.03],"gpt-5.1-none":[0.411,0.08,17.15],"gpt-4o-2024-11-24":[0.411,0.11,80.53],"llama-3.1-nemotron-nano-8b-v1":[0.411,0.111,65.43],"magistral-small-2506":[0.408,0.068,36.65],"hunyuan-turbos":[0.406,0.219,55.6],"gpt-4o-0327":[0.404,0.108,68.37],"qwen2.5-max":[0.403,0.112,81.27],"granite-4.2-3b":[0.402,0.076,53.58],"vllm-sr-decision-2.0-vega-27b":[0.402,0.135,78.76],"gdn-primed-hqwen3-8b-reasoner":[0.398,0.17,44.43],"gemini-2.5-flash-lite-thinking":[0.398,0.129,48.6],"kat-dev-32b":[0.398,0.078,57.24],"kimi-k2-base":[0.398,0.057,76.21],"kimi-linear-instruct":[0.397,0.066,56.43],"glm-5.3-flash-base":[0.396,0.154,66.58],"instella-moe-16b-a3b-dpo":[0.393,0.11,72.14],"gemini-2.5-flash-lite":[0.39,0.064,47.64],"qwen3-swallow-30b-a3b-cpt-v0.2":[0.389,0.128,72.8],"aliceai-foundation-80b-a3b-base":[0.389,0.126,67.7],"autotrust-jev-27b":[0.389,0.133,77.89],"solar-pro-3":[0.385,0.149,38.84],"glm-5-base":[0.384,0.157,66.84],"ministral-3-14b-reasoning":[0.384,0.119,61.38],"deepseek-v4-pro-base":[0.381,0.082,79.71],"qwen2.5-plus-1127":[0.381,0.079,75.17],"llama-nemotron-super-49b-v1.5":[0.379,0.11,46.54],"qwen3-swallow-8b-rl-v0.2":[0.377,0.128,69.96],"qwen3-swallow-30b-a3b-sft-v0.2":[0.375,0.128,71.2],"hunyuan-large-instruct":[0.37,0.087,80.45],"qwen3.8-27b-iq2-xxs":[0.368,0.105,76.52],"openpangu-r-7b-2512-fast-thinking":[0.367,0.092,57.54],"rnj-1.5":[0.363,0.138,63.71],"qwen3-vl-8b-instruct":[0.362,0.06,61.89],"exaone-4.0-32b":[0.358,0.101,47.76],"gpt-4o-2024-11-20":[0.356,0.065,45.25],"t5-plus-udg-single-model-google-brain":[0.356,0.207,93.27],"nemotron-3-ultra-base":[0.355,0.088,83.01],"gpt-4o":[0.354,0.038,54.54],"mistral-medium-3.1":[0.349,0.102,50.59],"qwen3-4b-thinking-2507":[0.347,0.078,57.08],"k2-think-v2":[0.347,0.097,70.03],"ling-mini-2.0":[0.347,0.063,65.77],"olmo-3-think-7b-sft":[0.344,0.072,60.52],"instella-moe-16b-a3b-sft":[0.341,0.11,71.01],"mimo-7b-rl":[0.34,0.094,47.38],"magistral-small-1.2":[0.337,0.096,46.46],"gpt-5-nano-low":[0.337,0.076,13.45],"pplx-decider-flash-v1.2":[0.336,0.133,77.62],"gpt-4o-2024-08-06":[0.336,0.056,68.83],"hermes-4.3-70b":[0.333,0.26,61.03],"seed1.6":[0.33,0.1,67.91],"gemini-2.0-flash-001":[0.328,0.137,65.18],"mistral-large-instruct-2407":[0.327,0.07,72.01],"plamo-3.0-prime-beta":[0.325,0.17,50.52],"kanana-2-30b-a3b-instruct-2601":[0.325,0.104,71.85],"vllm-sr-d3-mini":[0.323,0.133,78.16],"olmo-hybrid-think-7b-sft":[0.322,0.078,61.36],"mistral-small-4":[0.32,0.096,43.38],"kimi-dev-72b":[0.313,0.08,54.17],"gemini-1.5-pro":[0.312,0.056,66.11],"qwen2.5-math-72b-instruct":[0.31,0.092,79.32],"llama-4-maverick":[0.309,0.055,41],"claude-3.5-haiku":[0.303,0.14,57.37],"qwen2.5-72b-instruct":[0.302,0.047,67.86],"llama-3.2-90b-vision":[0.302,0.197,74.32],"k2-medium-70b":[0.301,0.092,65.44],"gpt-4o-2024-05-13":[0.3,0.052,66.32],"gpt-4-0125-preview":[0.299,0.193,78.05],"llada2.1-mini-q":[0.298,0.068,66.09],"gpt-4-turbo":[0.296,0.101,67.88],"olmo-3.1-instruct-32b-dpo":[0.296,0.074,63.07],"chatgpt-4o":[0.295,0.212,46.47],"youtu-llm-2b":[0.287,0.08,67.3],"deepseek-v4-flash-base":[0.286,0.072,73.82],"gemma-4-e4b-it":[0.286,0.05,53.27],"claude-3-opus":[0.285,0.08,78],"ling-3.0-flash-base":[0.284,0.084,70.05],"llama-3.1-tulu-3-405b-sft":[0.283,0.111,76.32],"gpt-4-turbo-2024-04-09":[0.282,0.061,72.67],"grok-2":[0.281,0.137,72.16],"ling-2.6-1t-base":[0.274,0.069,64.52],"nemotron-3-super-120b-a12b-base":[0.273,0.061,74.9],"llama-3.1-405b-instruct":[0.27,0.058,67.59],"glm-4.6v-flash":[0.269,0.132,41.02],"nemotron-h-47b-reasoning":[0.268,0.082,42.76],"spark-x2.5-1.7b":[0.264,0.091,34.91],"amazon-nova-premier":[0.262,0.097,39.01],"llama-4-scout-17b-16e":[0.257,0.12,52.26],"openpangu-vl-7b":[0.257,0.118,72.42],"qwen3-swallow-8b-sft-v0.2":[0.255,0.128,67.18],"llada2.0-mini":[0.254,0.063,62],"gpt-4-1106-preview":[0.253,0.07,77.68],"qwq-32b-preview":[0.253,0.095,62.15],"olmo-3.1-instruct-32b":[0.252,0.061,70.01],"llama-4-scout":[0.252,0.102,46.12],"mimo-v2-flash-base":[0.251,0.064,70.48],"ernie-3.0":[0.25,0.207,93],"llada2.1-mini-s":[0.248,0.067,64.49],"gemini-1.5-pro-002":[0.246,0.081,66.36],"qwen-3-235b-a22b-nonthinking":[0.245,0.107,66.06],"marco-mini-instruct":[0.243,0.097,73.11],"hunyuan-large":[0.24,0.082,83.19],"skywork-or1-7b":[0.239,0.115,40.77],"qwen3-4b-2507":[0.238,0.1,43.47],"qwen3-14b":[0.237,0.054,59.86],"qwen3-4b-instruct-2507":[0.233,0.058,62.27],"jamba2-3b":[0.233,0.326,61],"deepseek-v4.1-flash-base":[0.232,0.092,73.08],"qwen3-vl-4b-thinking":[0.231,0.175,32.58],"openpangu-embedded-7b-v1.1":[0.23,0.211,69.4],"qwen2-math-72b-instruct":[0.23,0.092,76.07],"hy3-preview-base":[0.228,0.063,69.56],"deepseek-v3.2-base":[0.226,0.084,78.47],"command-a":[0.224,0.139,57.87],"mimo-vl-7b-rl":[0.223,0.172,65.68],"llama-3.1-tulu-3-70b-dpo":[0.222,0.095,74.75],"llama-3.1-tulu-3-70b":[0.222,0.095,74.85],"gpt-4-0613":[0.222,0.158,78.28],"fanar-2-27b-instruct":[0.216,0.143,53.61],"ministral-3-14b-instruct":[0.214,0.087,61.16],"lfm2.5-2.6b":[0.212,0.09,50.79],"kanana-2-30b-a3b-instruct":[0.211,0.104,69.25],"hermes-3-llama-3.1-405b":[0.209,0.101,75.2],"nemotron-3-nano-4b-thinking":[0.206,0.097,47.73],"hunyuan-4b-instruct":[0.205,0.138,44.53],"qwen2.5-turbo":[0.203,0.073,77.21],"lfm2.5-8b-a1b":[0.2,0.085,49.12],"bespoke-nimble-9b-v3":[0.195,0.132,76.67],"qwen3-235b-a22b-base":[0.191,0.099,73.52],"qwen2.5-32b-instruct":[0.191,0.047,69.63],"deepseek-v2.5":[0.19,0.053,66.08],"openthinker3-7b":[0.19,0.079,55.86],"nemotron-3.5-super-vl-120b-a12b-base":[0.189,0.077,76.19],"gpt-4o-mini":[0.186,0.056,67.1],"gpt-4o-mini-2024-07-18":[0.182,0.061,59.68],"qwen3-vl-4b-instruct":[0.181,0.077,60.91],"qwen3-8b":[0.178,0.042,56.48],"granite-4.1-30b":[0.176,0.074,71.03],"gemini-2.0-flash-exp":[0.175,0.107,44.48],"yi-lightning":[0.173,0.092,65.61],"kat-dev-72b-exp":[0.171,0.083,54.82],"mistral-large-2411":[0.169,0.11,52.56],"aquif-3-moe-17b-a2.8b":[0.169,0.133,64.98],"deepseek-v3-base":[0.166,0.063,74.46],"openpangu-r-7b-diffusion":[0.166,0.102,78.77],"qwen2.5-math-7b-instruct":[0.161,0.092,74.43],"trinity-mini":[0.16,0.113,59.28],"llama-3.1-405b-instruct-bf16":[0.157,0.114,70.76],"qwen-turbo-0919":[0.157,0.079,68.83],"alodlm-8b":[0.157,0.085,80.32],"deepseek-v3.2-exp-base":[0.156,0.072,73.88],"qwen2.5-coder-32b-instruct":[0.154,0.056,60.23],"iquest-coder-v1-7b-thinking":[0.152,0.123,31.6],"qwen3-4b":[0.15,0.057,64.09],"grok-2-1212":[0.148,0.116,55.69],"llama-3.3-70b-instruct":[0.147,0.072,69.75],"claude-3-opus-20240229":[0.143,0.065,69.88],"glm-4.5-base":[0.142,0.063,71.39],"telechat2-115b":[0.138,0.117,84.35],"llama-3.1-405b-instruct-fp8":[0.136,0.079,70.03],"gemma-3-27b-it":[0.135,0.049,58.83],"motif-3-base":[0.135,0.099,82.66],"llama-3.3-70b":[0.133,0.07,68.75],"mistral-large-2407":[0.131,0.111,73.14],"ling-1t-base":[0.13,0.067,60.97],"nemotron-3-nano-4b":[0.127,0.079,47.78],"mimo-vl-7b-sft":[0.118,0.172,63.34],"command-a-reasoning-08-2025":[0.117,0.13,35.8],"stable-diffcoder-8b-instruct":[0.113,0.125,70.18],"mimo-v2.5-base":[0.111,0.065,68.97],"qwen2.5-14b-instruct":[0.109,0.064,72.63],"rnj-1":[0.108,0.14,54.63],"gemma-3-27b":[0.106,0.068,71.64],"qwen3-8b-non-thinking":[0.1,0.058,61.05],"ling-2.5-flash-base":[0.099,0.084,65.13],"qwen3-32b-nothinking":[0.097,0.061,52.02],"nemotron-3-nano-30b-a3b-base":[0.093,0.077,79.96],"deepseek-coder-v2-instruct":[0.088,0.051,65.73],"lfm2-2.6b-exp":[0.088,0.191,60.15],"chatgpt-4o-latest-20240903":[0.086,0.129,67.08],"llama-3.1-70b":[0.086,0.084,69.75],"step-3.5-flash-base-midtrain":[0.085,0.081,69.72],"step-2":[0.083,0.124,82.17],"grok-beta":[0.083,0.11,72.38],"step-3.5-flash-base":[0.08,0.062,66.6],"claude-3.5-haiku-20241022":[0.079,0.084,50.45],"vllm-sr-decision-2.0-lux-9b":[0.077,0.132,74.28],"joyai-llm-flash-base":[0.077,0.09,76.27],"qwen3-4b-saferl-thinking":[0.076,0.178,38.43],"diffusiongemma-jev":[0.072,0.132,73.99],"llama-4-maverick-17b-128e-base":[0.07,0.164,79.67],"gemini-1.5-pro-exp-0801":[0.07,0.114,68.58],"gpt-5-nano-minimal":[0.066,0.078,27.97],"exaone-4.0-1.2b":[0.066,0.09,50.84],"deepseek-v3.1-base":[0.066,0.08,69.81],"seed1.5":[0.064,0.106,70.35],"kolibri-1-base":[0.063,0.112,81.27],"kanana-1.5-32.5b-instruct":[0.062,0.104,65.23],"llada2.1-mini":[0.061,0.118,47.39],"mistral-3.2-24b":[0.06,0.091,77.42],"mistral-small-3.2-24b-instruct":[0.059,0.086,60.2],"llama-4-scout-17b":[0.058,0.074,63.61],"llama-3.1-70b-instruct":[0.053,0.05,69.42],"granite-4.1-8b":[0.052,0.074,67.52],"deepseek-v2-chat-0628":[0.051,0.072,68.08],"qwen3-swallow-8b-cpt-v0.2":[0.049,0.128,62.8],"ling-2.6-flash-base":[0.049,0.067,58.3],"gemini-1.5-flash-exp-0827":[0.048,0.114,67.37],"llama-3.1-tulu-3-70b-sft":[0.046,0.101,70.59],"telechat2-35b":[0.046,0.117,83.05],"qwen3.5-35b-a3b-base":[0.041,0.088,72.6],"step-3":[0.038,0.194,39.55],"mellum2-12b-a2.5b-instruct":[0.037,0.115,65.17],"mistral-large-3-base":[0.037,0.074,70.32],"mistral-small-3.1-24b-instruct":[0.036,0.087,53.92],"qwen-2.5-72b":[0.035,0.058,71.17],"minicpm-o-4.5":[0.035,0.104,81.77],"llada2.2-mini":[0.027,0.116,47.61],"magistral-small-2509":[0.026,0.135,56.24],"autotrust-jev-9b":[0.024,0.132,72.64],"gpt-4":[0.022,0.073,74.21],"skywork-o1-open-llama-3.1-8b":[0.017,0.08,66.43],"qwen2-72b-instruct":[0.014,0.056,68.47],"qwen2.5-math-72b":[0.014,0.12,82.53],"bespoke-nimble-9b-v2":[0.013,0.132,72.75],"frozen-t5-1.1-plus-spot":[0.011,0.207,91.97],"stable-diffcoder-8b-base":[0.011,0.15,73.53],"qwen3-8b-instruct":[0.009,0.085,77.22],"deepseek-coder-v2-instruct-0724":[0.009,0.076,56.12],"jamba2-mini":[0.006,0.184,56.25],"k2-horizon-0.9b":[0.001,0.157,53.15],"gemini-1.5-flash":[0,0.071,62.23],"exaone-deep-2.4b":[-0.003,0.094,47.23],"k2-low-70b":[-0.006,0.092,56.26],"llada2.0-flash-preview":[-0.007,0.071,68.35],"gpt-3.5-turbo-nov-2023":[-0.008,0.187,74.3],"glm-4-0520":[-0.012,0.107,75.23],"qwen2-math-7b-instruct":[-0.014,0.092,69.92],"iquest-coder-v1-7b-instruct":[-0.016,0.129,27.88],"hermes-3-llama-3.1-70b":[-0.023,0.099,70.05],"gemma-3-12b-it":[-0.029,0.056,59.41],"qwen3-4b-thinking":[-0.029,0.158,33.1],"phi-4-14b":[-0.031,0.118,56.83],"nemotron-3.5-lightning-30b-a3b-base":[-0.033,0.104,77.2],"ministral-3-14b-base":[-0.039,0.136,73.82],"qwen2.5-coder-14b-instruct":[-0.04,0.06,54.82],"opencodeinterpreter-ds-33b":[-0.042,0.13,75.12],"wedlm-8b-instruct":[-0.043,0.078,75.02],"claude-3-sonnet":[-0.044,0.138,76.81],"llama-3.1-nemotron-70b":[-0.051,0.101,71.46],"mistral-small-3.1-24b-instruct-2503":[-0.051,0.229,61.6],"t5":[-0.052,0.207,91.77],"olmo-3.1-instruct-32b-sft":[-0.053,0.074,53.04],"qwen3-30b-a3b-base":[-0.055,0.075,72.54],"gemini-1.5-flash-002":[-0.056,0.078,58.23],"kimi-vl-a3b-thinking-2506":[-0.057,0.191,34.62],"ling-flash-base-2.0":[-0.058,0.055,62.94],"sdar-8b-chat":[-0.059,0.101,73.99],"falcon-h1-34b-instruct":[-0.064,0.071,61.06],"qwen2.5-math-1.5b-instruct":[-0.068,0.093,67.65],"wizardcoder-33b-v1.1":[-0.071,0.146,75.43],"granite-4.0-h-small":[-0.077,0.064,64.42],"claude-3-haiku-mar-2024":[-0.078,0.187,72.63],"gpt-4.1-nano":[-0.078,0.064,38.37],"kev-9b":[-0.08,0.132,71.2],"qwen3-14b-base":[-0.081,0.136,72.98],"claude-3-sonnet-mar-2024":[-0.083,0.187,72.3],"magicoder-s-ds-6.7b":[-0.085,0.098,65.58],"yuan2.0-m32":[-0.085,0.113,78.2],"artigenz-coder-ds-6.7b":[-0.087,0.13,74.22],"nemotron-labs-twotower-30b-a3b-base":[-0.087,0.09,79.25],"seed-coder-8b-base":[-0.087,0.15,70.45],"gpt-4-0314":[-0.088,0.084,67.95],"llama-4-maverick-base":[-0.091,0.09,64.39],"yi-coder-9b-chat":[-0.093,0.089,56.93],"midm-2.0-base-instruct":[-0.094,0.127,67.9],"internlm2-math-plus-mixtral8x22b":[-0.095,0.144,62.4],"gemma-4-e2b-it":[-0.1,0.056,43.63],"mellum2-12b-a2.5b-thinking-sft":[-0.104,0.154,65.06],"gpt-oss-20b-moe":[-0.104,0.185,48.18],"jamba-1.5-large":[-0.11,0.136,76.71],"mobilellm-r1.5-950m":[-0.111,0.124,66.1],"opencodeinterpreter-ds-6.7b":[-0.119,0.13,72.86],"vllm-sr-decision-2.0-nox-4b":[-0.119,0.132,70.69],"qwen2-math-72b":[-0.123,0.12,78.78],"ministral-3-8b-instruct":[-0.125,0.093,63.04],"numinamath-72b-cot":[-0.125,0.092,65.73],"k2-v2":[-0.127,0.104,73.53],"deepseek-v2-chat-sft":[-0.127,0.07,70.9],"claude-3-sonnet-20240229":[-0.128,0.077,68.52],"lfm2-350m-math":[-0.13,0.14,58],"olmo-hybrid-instruct-7b-dpo":[-0.132,0.077,48.88],"glm-4-air-0605":[-0.133,0.107,72.67],"internvl-8b":[-0.133,0.173,57.18],"codestral-22b-v0.1":[-0.134,0.09,61.77],"mistral-small-instruct-2409":[-0.137,0.144,57.22],"yi-large-preview":[-0.14,0.083,64.38],"deepseek-v2-chat":[-0.14,0.059,65.54],"g9v3-3b":[-0.147,0.178,25.97],"llama-3.1-405b-base":[-0.147,0.068,73.78],"mellum2-12b-a2.5b-instruct-sft":[-0.147,0.115,59.59],"seed-coder-8b-instruct":[-0.149,0.068,48.62],"tev1-4b-experimental":[-0.149,0.132,69.92],"codegeex4-all-9b":[-0.149,0.14,58.4],"llama-3-70b":[-0.152,0.077,64.99],"speechless-codellama-34b-v2.0":[-0.153,0.13,71.32],"amazon-nova-pro-v1.0":[-0.153,0.14,39.56],"trinity-large-base":[-0.154,0.105,74.83],"abab6.5":[-0.154,0.12,74.92],"yi-34b-200k":[-0.155,0.218,73.58],"gpt-3.5-turbo-1106":[-0.155,0.114,65.06],"olmo-3-instruct-7b-dpo":[-0.156,0.077,49.57],"qwen2.5-7b-instruct":[-0.16,0.049,59.95],"minicpm5-1b":[-0.16,0.089,48.77],"ling-3.0-tiny-base":[-0.161,0.082,58.97],"qwen-72b":[-0.161,0.231,76.78],"minicpm4-8b":[-0.161,0.109,81.31],"llama-3-70b-instruct":[-0.161,0.053,65.86],"llama-4-scout-17b-16e-base":[-0.162,0.165,73.5],"llada2.0-mini-preview":[-0.163,0.101,71],"olmo-3-instruct-7b":[-0.163,0.055,57.74],"opencoder-8b-instruct":[-0.164,0.09,53.17],"deepseek-coder-33b-instruct":[-0.172,0.085,50.37],"xwincoder-34b":[-0.173,0.13,71.28],"code-millenials-34b":[-0.173,0.13,71.32],"ouro-2.6b":[-0.175,0.095,75.13],"qwen2.5-math-7b":[-0.18,0.12,74.95],"phi-3.5-moe-instruct":[-0.181,0.105,71.95],"qwen2.5-32b-base":[-0.182,0.078,73.51],"hy-1.8b":[-0.183,0.118,67.15],"codestral-2501":[-0.186,0.117,26.42],"motif-2-12.7b-base":[-0.19,0.076,69.21],"starchat2-15b-v0.1":[-0.191,0.128,71.52],"youtu-vl-4b-instruct":[-0.191,0.139,66.08],"llm-jp-4-vl-9b":[-0.194,0.142,52.73],"deepseek-coder-33b":[-0.195,0.145,59.1],"wavecoder-ultra-6.7b":[-0.196,0.13,70.48],"openreasoning-nemotron-1.5b":[-0.197,0.1,41.41],"deepseek-r1-distill-qwen-7b":[-0.198,0.075,49.88],"qwen2-72b":[-0.198,0.073,72.33],"glm-4.5-air-base":[-0.199,0.077,68.99],"ministral-3-8b-base":[-0.199,0.136,69.3],"internlm2_5-20b-chat":[-0.206,0.09,71.43],"gemma-2-27b-it":[-0.206,0.054,58.44],"hyperclovax-seed-omni-8b":[-0.207,0.153,61.2],"kimi-linear-base":[-0.215,0.083,62.01],"ling-2.5-mini-base":[-0.218,0.082,56.9],"smollm3-3b":[-0.219,0.055,54.31],"qwen2.5-coder-32b":[-0.222,0.084,70.52],"codestral-22b":[-0.223,0.102,52.72],"lfm2.5-vl-3b":[-0.227,0.269,55.83],"whiterabbitneo-33b-v1":[-0.227,0.13,70.02],"phi-3-small-8k-instruct":[-0.228,0.126,78.1],"falcon-h1-7b":[-0.232,0.07,56.28],"qwen2-math-1.5b-instruct":[-0.235,0.092,61.5],"plamo-3.0-prime":[-0.235,0.167,37.66],"athene-70b":[-0.237,0.114,60],"amazon-nova-lite-v1.0":[-0.237,0.14,34.52],"yi-large":[-0.239,0.11,59.53],"nezha-plus":[-0.24,0.207,89.37],"llama-3.1-tulu-3-8b":[-0.242,0.093,62.93],"mixtral-8x22b-instruct-v0.1":[-0.244,0.059,66.41],"aquif-3.5-nano-1b":[-0.245,0.176,46.57],"databricks-dbrx-instruct":[-0.247,0.125,69.17],"glm-4-0116":[-0.251,0.109,67.83],"qwen3-8b-nothinking-2504":[-0.256,0.124,30.03],"select-step-by-step":[-0.257,0.226,70.17],"intern-decision-4b":[-0.259,0.132,68.29],"deepseek-r1-distill-llama-8b":[-0.261,0.081,58.15],"qwen1.5-110b-chat":[-0.262,0.075,62.54],"speechless-coder-ds-6.7b":[-0.265,0.13,68.68],"gpt-3.5-may-2023":[-0.266,0.146,68.73],"mistral-small-3-24b-base":[-0.267,0.137,74.02],"claude-3-haiku-20240307":[-0.272,0.072,56.28],"kanana-2-30b-a3b-base":[-0.273,0.091,73.38],"kanana-2-30b-a3b-mid-2601":[-0.273,0.091,73.38],"hermes-4.3-36b-pyche":[-0.274,0.264,57.43],"internlm2.5-7b-chat":[-0.274,0.09,69.98],"wizardcoder-python-34b-v1.0":[-0.275,0.13,68.14],"diffucoder-7b-instruct":[-0.275,0.147,68.55],"apertus-v1.5-70b-thinking":[-0.276,0.107,59.82],"granite-3.2-8b-instruct":[-0.276,0.094,65.63],"vllm-sr-d3-nano":[-0.277,0.132,69.8],"granite-3.3-8b-instruct":[-0.277,0.063,56.29],"telechat2-7b":[-0.277,0.118,75.25],"qwen2.5-coder-7b-instruct":[-0.277,0.059,48.4],"internvl2.5-26b":[-0.28,0.086,70.61],"qwen3-1.7b":[-0.281,0.049,53.69],"baichuan-3":[-0.281,0.109,72.58],"apertus-v1.5-8b-thinking":[-0.281,0.107,60.88],"deepseek-math-7b-rl":[-0.281,0.1,62.64],"claude-3-haiku":[-0.285,0.127,63.28],"qwen1.5-72b-chat":[-0.289,0.056,65.76],"reka-core-20240501":[-0.289,0.114,58.94],"llama-3.1-tulu-3-8b-dpo":[-0.29,0.094,62.35],"internlm2.5-20b":[-0.292,0.122,65.35],"magicoder-s-cl-7b":[-0.292,0.13,67.36],"d1-3b":[-0.293,0.121,71.92],"qwen3-8b-base":[-0.293,0.071,67.21],"qwen2-57b-a14b-instruct":[-0.295,0.075,61.03],"yi-1.5-34b-chat":[-0.296,0.073,61.44],"qwen2.5-7b":[-0.297,0.06,63.74],"hy-1.8b-2bit":[-0.299,0.119,63.18],"codestral-mamba":[-0.3,0.173,67.43],"xverse-moe-a36b":[-0.3,0.11,72.65],"lfm2-24b-a2b":[-0.301,0.098,60.44],"gemma-3-12b-base":[-0.303,0.136,67.72],"qwen2.5-14b":[-0.304,0.082,67.38],"lfm2.5-1.2b-thinking":[-0.306,0.083,46.42],"mistral-large-2402":[-0.31,0.126,68.56],"granite-4.1-3b":[-0.311,0.073,59.35],"mistral-large":[-0.311,0.137,61.46],"hy-1.8b-int4gptq":[-0.312,0.115,63.31],"internlm2-math-plus-20b":[-0.317,0.096,56],"solar-pro-preview":[-0.32,0.11,68.2],"marco-nano-instruct":[-0.321,0.098,59.94],"aquif-3.5-2.7b":[-0.322,0.168,52],"olmo-hybrid-instruct-7b-sft":[-0.324,0.076,42.65],"qwen2.5-omni-7b":[-0.325,0.134,57.55],"qwen3-1.7b-thinking":[-0.325,0.085,48.17],"qwen2.5-coder-14b":[-0.326,0.084,67.94],"phi-4-mini":[-0.329,0.141,65.46],"openchat-3.5-7b-0106":[-0.33,0.13,65.26],"opencoder-8b-base":[-0.331,0.151,62.83],"glm4-9b":[-0.331,0.086,69.66],"ernie-4.5-21b-a3b-pt":[-0.332,0.124,32.83],"falcon-h1-3b":[-0.335,0.071,53.34],"qwen3-6b":[-0.336,0.137,51.37],"qwen3.5-9b-base":[-0.337,0.084,59.47],"apertus-v1.5-70b":[-0.338,0.077,64.53],"qwen3-4b-saferl":[-0.344,0.177,26.4],"kanana-1.5-32.5b-base":[-0.347,0.092,71.34],"codellama-70b-instruct":[-0.348,0.114,57.97],"pai-albert":[-0.349,0.207,88.67],"yi-34b-chat-8bits":[-0.352,0.147,73.75],"deepseek-v2":[-0.353,0.065,67.13],"hermes-4.3-36b":[-0.354,0.26,54.03],"phind-codellama-34b-v2":[-0.356,0.129,61.1],"falcon-h1-1.5b-deep":[-0.356,0.075,55.3],"speechless-starcoder2-15b":[-0.358,0.13,65.72],"glm-4-9b-chat":[-0.359,0.077,65.41],"hrm-text-1b":[-0.37,0.114,73.44],"qwen3.5-4b-base":[-0.372,0.069,68.26],"qwen3.5-2b":[-0.372,0.05,46.37],"roberta-icets":[-0.374,0.207,88.57],"qwen1.5-110b":[-0.375,0.085,67.45],"gemma-2-9b-it":[-0.376,0.053,52.72],"bitcpm-cann-8b":[-0.379,0.109,77.84],"gpt-3.5-turbo-0613":[-0.379,0.194,54.16],"llama-3-70b-base":[-0.383,0.064,68.17],"olmo-3-32b":[-0.385,0.111,74.03],"kanana-2-30b-a3b-base-2601":[-0.385,0.092,71.05],"llama-3.1-70b-base":[-0.387,0.092,76.49],"qwen2-7b-instruct":[-0.388,0.053,55.19],"deepseek-coder-v2-base":[-0.39,0.093,66.11],"qwen2-math-7b":[-0.392,0.12,69.93],"internlm2-math-plus-7b":[-0.393,0.096,53.4],"plamo-2.2-prime":[-0.396,0.168,33.7],"roberta-mtl-adv":[-0.399,0.207,88],"internvl2.5-8b":[-0.399,0.087,67.41],"roberta-ensemble":[-0.399,0.207,88.3],"yi-34b-chat":[-0.404,0.137,70.45],"lfm2-8b-a1b":[-0.405,0.065,49.99],"granite-4.0-h-micro":[-0.406,0.077,58.3],"yi-34b-chat-4bits":[-0.407,0.147,72.58],"internvl3.5-8b":[-0.408,0.145,54.64],"minicpm3-4b":[-0.411,0.071,55.75],"ministral-3-3b-base":[-0.416,0.135,58.6],"olmo-3-7b-sft":[-0.417,0.073,39.32],"gemma-3-4b-it":[-0.418,0.057,50.76],"mixtral-8x22b":[-0.418,0.062,65.56],"mobilellm-r1-950m":[-0.419,0.1,50.6],"falcon3-10b":[-0.419,0.077,55.31],"deepseek-math-7b-instruct":[-0.42,0.12,62.4],"mathstral-7b":[-0.42,0.076,49.64],"kanana-2-3b-instruct":[-0.421,0.128,61.22],"fanar-1-9b-instruct":[-0.426,0.121,45.81],"granite-4.0-micro":[-0.429,0.074,56.63],"claude-2":[-0.432,0.135,64.72],"qwen-2.5-3b-instruct":[-0.438,0.077,46.75],"numinamath-7b-cot":[-0.438,0.1,57.9],"marin-32b-base":[-0.438,0.316,78.12],"lfm2.5-350m":[-0.439,0.124,36.75],"exaone-3.5-7.8b-instruct":[-0.439,0.13,61.72],"granite-4.0-h-tiny":[-0.44,0.053,50.39],"deepseek-coder-v2-lite-instruct":[-0.442,0.049,49.72],"roberta":[-0.444,0.207,87.43],"kanana-2-1.3b-instruct":[-0.452,0.128,60.32],"gemma-3-12b":[-0.453,0.076,61.8],"olmo-2-0325-32b-instruct":[-0.453,0.075,44.37],"palm-cont-62b":[-0.453,0.314,80.72],"phi-3-medium-4k-instruct":[-0.455,0.093,63.09],"code-290k-6.7b-instruct":[-0.458,0.146,61.33],"qwen2.5-coder-7b":[-0.458,0.082,63.09],"lfm2.5-1.2b-instruct":[-0.458,0.114,54.83],"mistral-nemo-instruct-2407":[-0.459,0.082,47.43],"gemini-pro":[-0.459,0.138,64.73],"deepseek-llm-67b-chat":[-0.459,0.068,65.56],"gemini-1.0-pro":[-0.463,0.13,62.24],"qwen2.5-coder-3b-instruct":[-0.464,0.075,51.63],"ministral-8b-instruct":[-0.464,0.102,58.54],"bielik-11b-v3.0-instruct":[-0.465,0.154,72.45],"phi-3-mini-4k-instruct":[-0.465,0.078,60.4],"qwen1.5-72b":[-0.466,0.067,64.49],"starcoder2-15b-instruct-v0.1":[-0.47,0.106,55.01],"aquif-3-3.2b":[-0.47,0.168,49.48],"gpt-3.5-turbo-0125":[-0.471,0.072,55.33],"dolphin-2.6-mixtral-8x7b":[-0.474,0.13,61.64],"glm-4-9b-chat-1m":[-0.475,0.079,65.85],"yuan2.0-102b":[-0.477,0.153,67.23],"lfm2-2.6b":[-0.481,0.081,52.54],"yi-1.5-9b-chat":[-0.481,0.075,56.62],"command-r-plus":[-0.483,0.069,56.1],"gemma-2-27b":[-0.485,0.072,55.56],"granite-3.1-8b-instruct":[-0.485,0.088,59.34],"qwen2.5-vl-7b":[-0.485,0.158,46.73],"qwen2.5-math-1.5b":[-0.485,0.12,65.23],"ministral-8b":[-0.489,0.139,56.69],"alodlm-1.7b":[-0.49,0.085,65.45],"bielik-11b-v2.5-instruct":[-0.49,0.155,71.42],"openpangu-7b-diffusion-base":[-0.493,0.099,65.26],"qwen1.5-32b-chat":[-0.494,0.068,59.8],"aya-expanse-32b":[-0.496,0.199,35.64],"ouro-1.4b":[-0.497,0.085,65.94],"internvl2-8b":[-0.5,0.088,65.8],"qwen-72b-chat":[-0.503,0.129,63.8],"gpt-3.5-turbo":[-0.505,0.091,60.86],"olmo-2-32b-base":[-0.505,0.08,68.64],"qwen2.57b-a14b":[-0.509,0.076,64.25],"mimo-7b-base":[-0.511,0.101,66.8],"phi-3.5-mini-instruct":[-0.513,0.062,52.77],"yi-1.5-34b":[-0.514,0.077,62.77],"llama3.0-70b":[-0.515,0.095,64.98],"apertus-v1.5-8b":[-0.519,0.076,58.89],"granite-3.3-2b-instruct":[-0.525,0.086,57.99],"trinity-large-truebase":[-0.528,0.096,66.92],"falcon3-7b":[-0.529,0.077,52.9],"llama-3.1-8b-instruct":[-0.531,0.042,48.07],"reka-flash-21b-20240226":[-0.533,0.114,49.57],"codeqwen1.5-7b-chat":[-0.536,0.096,49.92],"bielik-11b-v2.6-instruct":[-0.539,0.153,71.1],"llama-3.1-tulu-3-8b-sft":[-0.545,0.102,57.43],"moonlight-base":[-0.548,0.069,57.86],"gemini-1.5-flash-8b-001":[-0.548,0.236,52],"codestral-12b-instruct":[-0.548,0.163,41.94],"instella-moe-16b-a3b-base":[-0.549,0.097,79.47],"eurollm-22b":[-0.555,0.073,58.18],"moonlight-instruct":[-0.555,0.086,48.82],"falcon-h1-1.5b":[-0.559,0.078,49.69],"gemma-3-27b-vl":[-0.56,0.192,26.38],"internlm2.5-7b":[-0.563,0.118,60.15],"deepseek-coder-7b-instruct-v1.5":[-0.565,0.091,62.4],"granite-4.0-tiny-preview":[-0.566,0.094,57.1],"qwen2.5-coder-1.5b-instruct":[-0.568,0.121,50.69],"codegemma-1.1-7b":[-0.571,0.173,58.33],"codegemma-7b-it":[-0.571,0.13,58.26],"qwen2-7b":[-0.575,0.07,61.02],"jamba-1.5-mini":[-0.581,0.156,63.7],"gpt-3.5":[-0.582,0.093,66.84],"nemotron-nano-12b-v2-base":[-0.583,0.09,69.92],"internlm2-chat-20b":[-0.584,0.082,59.27],"exaone-3.5-2.4b-instruct":[-0.585,0.128,55.78],"command-r-plus-08-2024":[-0.586,0.148,78.28],"step-audio-2-mini":[-0.588,0.157,54.75],"olmo-hybrid-7b":[-0.589,0.1,65.35],"llama-3.1-8b":[-0.589,0.067,54.57],"jamba-mini-1.6":[-0.59,0.141,45.92],"internvl2-26b":[-0.592,0.086,62.19],"gpt-2":[-0.593,0.285,50.88],"fast-dllm-v2-7b":[-0.597,0.097,58.74],"qwen2-math-1.5b":[-0.598,0.12,61.42],"midm-2.0-mini-instruct":[-0.6,0.137,56.7],"ailabs-team-transformers":[-0.606,0.207,85.83],"deepseek-instruct-33b":[-0.607,0.185,50.25],"skywork-moe-base":[-0.608,0.114,65.17],"qwen2.5-3b":[-0.609,0.062,53.19],"deepseek-coder-6.7b-instruct":[-0.609,0.075,47.33],"baichuan-omni":[-0.612,0.214,63.53],"ipet-albert-few-shot-32-examples":[-0.618,0.207,82.47],"qwen1.5-32b":[-0.618,0.075,61.23],"bielik-11b-v2.3-instruct":[-0.62,0.153,69.82],"speechless-starcoder2-7b":[-0.623,0.13,56.54],"dream-7b-base":[-0.623,0.087,58.39],"bielik-11b-v2.2-instruct":[-0.627,0.153,69.86],"trinity-mini-base":[-0.628,0.1,65.98],"apriel-5b-instruct":[-0.629,0.168,46.35],"chatglm3-6b-base":[-0.629,0.082,63.96],"command-r7b":[-0.633,0.161,24.42],"qwen3-vl-2b-instruct":[-0.633,0.09,49.29],"bielik-11b-v2.1-instruct":[-0.637,0.153,69.82],"internlm2-20b":[-0.638,0.086,59.63],"code-13b":[-0.641,0.146,53.63],"rnd1-base-0910":[-0.642,0.122,67.99],"yi-6b-200k":[-0.644,0.214,63.7],"wizardcoder-15b-v1.0":[-0.647,0.13,55.4],"codellama-70b":[-0.651,0.117,47.83],"metamath-70b":[-0.652,0.127,59.93],"command-r":[-0.652,0.092,41.08],"bitcpm-cann-3b":[-0.653,0.109,72.32],"aya-expanse-8b":[-0.655,0.199,31.23],"claude-instant-1-mar-2024":[-0.657,0.146,52.83],"bort-alexa-ai":[-0.658,0.207,82.47],"olmo-3-7b":[-0.659,0.068,66.94],"lfm2-vl-3b":[-0.66,0.269,46.73],"dream-7b-instruct":[-0.662,0.071,58.88],"gemma-3n-e2b-it":[-0.671,0.151,43.97],"yi-1.5-6b-chat":[-0.673,0.086,49.82],"deepseek-r1-distill-qwen-1.5b":[-0.674,0.08,44.88],"speechless-coding-7b-16k-tora":[-0.675,0.13,54.18],"internlm2-chat-20b-sft":[-0.678,0.084,57.64],"apertus-v1.5-70b-base":[-0.678,0.316,76.05],"llama-3-8b-instruct":[-0.679,0.057,55.14],"gemma-3-pt-27b":[-0.68,0.083,65.04],"yi-coder-1.5b-chat":[-0.681,0.126,44.5],"ministral-3-3b-instruct":[-0.682,0.09,48.8],"exaone-3.5-2.4b":[-0.683,0.168,43.73],"deepseek-llm-67b-base":[-0.684,0.075,64.19],"qwen3-4b-base":[-0.685,0.119,63.34],"deepseek-coder-1.3b-instruct":[-0.686,0.115,44.19],"gemma-2-9b":[-0.694,0.063,55.06],"code-33b":[-0.695,0.146,51.23],"deepseek-math-7b":[-0.695,0.083,56.89],"ministral-8b-2410":[-0.705,0.185,33.36],"llm-jp-4-vl-9b-beta":[-0.707,0.14,38.68],"apertus-70b":[-0.707,0.087,62.97],"qwen3.5-2b-base":[-0.711,0.098,75.41],"coda-1.7b-instruct":[-0.712,0.13,53.54],"yi-coder-9b":[-0.714,0.111,54.52],"codellama-python-34b":[-0.714,0.153,51.68],"apertus-70b-instruct":[-0.714,0.054,40.96],"vllm-sr-d3-lite":[-0.715,0.132,62.67],"qwen-14b":[-0.717,0.074,68.11],"yi-1.5-9b":[-0.718,0.092,55.15],"magpie-8b":[-0.718,0.117,48.95],"dbrx-instruct-preview":[-0.72,0.108,61.1],"tigerbot-70b-chat":[-0.723,0.149,70.82],"mixtral-8x7b":[-0.736,0.067,56.24],"qwen2.5-1.5b-instruct":[-0.736,0.074,45.91],"bielik-11b-v2.0-instruct":[-0.739,0.151,68.04],"bielik-11b-v3.0":[-0.739,0.148,68.45],"fsl-plus-plus-albert-few-shot-32-examples":[-0.742,0.207,81.93],"openchat-3.5-0106-gemma":[-0.743,0.146,69.42],"llama-3.1-8b-base":[-0.743,0.061,55.99],"phi-2-2.7b":[-0.746,0.147,53.18],"wizardmath-70b-v1.0":[-0.749,0.13,56.57],"llama-3.1-3b":[-0.751,0.158,50.45],"internlm2-math-plus-1.8b":[-0.753,0.144,44.9],"phi-4-mini-3.8b":[-0.756,0.168,42.88],"marin-32b-mantis":[-0.756,0.086,66.77],"internlm2-7b":[-0.757,0.087,56.79],"llama-2-70b":[-0.758,0.073,64.08],"internlm2-math-base-20b":[-0.763,0.119,51.4],"granite-3.2-2b-instruct":[-0.764,0.091,50.24],"grok-1":[-0.766,0.12,55.75],"qwen2.5-coder-3b":[-0.77,0.084,55.24],"skywork-13b-math":[-0.771,0.133,55.53],"openhermes-2.5-code-290k-13b":[-0.771,0.13,50.02],"codellama-34b-instruct":[-0.775,0.115,44.13],"granite-4.0-h-1b":[-0.775,0.114,46.51],"llama-3.2-3b-instruct":[-0.776,0.068,38.28],"minerva-540b":[-0.777,0.135,52.1],"granite-4.0-1b":[-0.777,0.109,44.1],"mixtral-8x7b-instruct-v0.1":[-0.778,0.059,50.05],"marin-8b-base":[-0.784,0.107,61.96],"intern-decision-2b":[-0.786,0.133,58.2],"granite-3.1-2b-instruct":[-0.797,0.088,48.37],"wizardcoder-python-7b-v1.0":[-0.798,0.13,49.76],"deepseek-coder-v2-lite-base":[-0.804,0.079,55.8],"xverse-65b":[-0.806,0.132,65.14],"xverse-65b-2":[-0.807,0.102,62.04],"llada-moe-7b-a1b-base":[-0.809,0.099,54.26],"kanana-2-3b-base":[-0.809,0.099,50.16],"telechat2-3b":[-0.813,0.115,62.23],"qwen3-0.6b":[-0.815,0.063,30.7],"mobilellm-r1.5-360m":[-0.818,0.127,41.6],"marin-8b-instruct":[-0.82,0.076,48.36],"codegemma-7b":[-0.821,0.115,42.8],"adapet-albert-few-shot":[-0.824,0.207,80.47],"install-albert-few-shot-32examples":[-0.825,0.207,80.2],"codellama-34b":[-0.83,0.091,47.85],"gemma-3-4b":[-0.831,0.094,46.89],"xverse-7b-chat":[-0.831,0.24,56],"gemma-3-4b-base":[-0.833,0.136,51.58],"smollm3-3b-base":[-0.835,0.097,74.48],"trinity-nano-base":[-0.838,0.086,65.88],"qwen3-1.7b-base":[-0.839,0.092,53.88],"gopher-280b":[-0.841,0.304,67.98],"internvl3.5-4b":[-0.842,0.259,45.34],"bolmo-7b":[-0.843,0.124,46.13],"command-r-08-2024":[-0.844,0.148,71.96],"lfm2.5-230m":[-0.845,0.123,31.96],"bielik-4.5b-v3-instruct":[-0.848,0.149,64.88],"llama-3-8b":[-0.851,0.07,54.27],"tiny-aya-global":[-0.853,0.281,45.13],"olmo-2-1124-7b-instruct":[-0.857,0.075,32.13],"nemotron-flash-3b":[-0.858,0.239,47.59],"mistral-codealpaca-7b":[-0.859,0.146,44.13],"gemma-2-2b-it":[-0.861,0.077,38.58],"vllm-sr-decision-2.0-sol-2b":[-0.861,0.132,57.75],"qwen1.5-14b-chat":[-0.862,0.139,63.17],"internlm2-chat-7b":[-0.863,0.081,53.95],"falcon-180b":[-0.863,0.125,63.21],"bielik-11b-v2":[-0.864,0.146,65.87],"speechless-code-mistral-7b-v1.0":[-0.864,0.13,47.46],"mistralhermes-codepro-7b-v1":[-0.868,0.13,47.12],"qwen1.5-14b":[-0.87,0.095,60.3],"llama-3.1-swallow-8b-instruct-v0.5":[-0.87,0.128,37.78],"eurollm-22b-base":[-0.871,0.322,72.95],"lfm2-1.2b":[-0.872,0.131,48.91],"internlm2-chat-7b-sft":[-0.872,0.083,53.41],"llama-tfree-hat-pretrained-7b-dpo":[-0.882,0.211,67.4],"codellama-python-13b":[-0.885,0.153,46.12],"audio-flamingo-3":[-0.887,0.157,45.88],"falcon3-3b":[-0.888,0.078,43.37],"solar-10.7b-instruct-v1.0":[-0.889,0.096,60.8],"marin-32b-bison":[-0.892,0.09,64.15],"llada-8b-base":[-0.896,0.099,51.96],"hy-0.5b":[-0.897,0.112,45.28],"aquila2-34b":[-0.898,0.113,67.92],"strands-decider-2b":[-0.899,0.133,55.35],"llada-8b-instruct":[-0.902,0.079,50.85],"chatglm3-6b":[-0.908,0.086,53.05],"stablebeluga2-70b":[-0.913,0.091,60.49],"orion-14b-chat":[-0.914,0.19,64.92],"qwen2.5-1.5b":[-0.915,0.063,41.22],"eurollm-9b-instruct-2512":[-0.917,0.076,47.67],"deepseek-v2-lite-chat":[-0.917,0.063,47.95],"apertus-v1.5-8b-base":[-0.922,0.316,72.38],"qwen2.5-coder-0.5b-instruct":[-0.923,0.126,39.81],"yi-1.5-6b":[-0.925,0.094,50.88],"mobilellm-r1-950m-base":[-0.927,0.138,45.27],"vita":[-0.929,0.214,55.12],"granite-3.3-8b-base":[-0.93,0.094,58.72],"yi-34b":[-0.931,0.104,58.18],"tigerbot-70b-base":[-0.932,0.135,68.69],"text-to-text-petl":[-0.934,0.207,79.73],"minerva-62b":[-0.935,0.135,44.63],"llama-3.2-3b-base":[-0.937,0.079,42.49],"falcon-h1-0.5b-instruct":[-0.939,0.078,40.14],"aquilachat2-34b":[-0.941,0.155,62.21],"xverse-13b-2":[-0.944,0.124,61.84],"mobilemoe-l":[-0.944,0.08,57.25],"apertus-8b-instruct":[-0.946,0.061,39.15],"trida-7b":[-0.958,0.104,51.19],"afm-4.5b":[-0.959,0.176,50.13],"deepseek-coder-33b-base":[-0.959,0.082,47.81],"starcoder2-15b":[-0.961,0.076,46.94],"qwen-14b-chat":[-0.963,0.081,52.19],"baichuan2-13b-chat-4bits":[-0.965,0.247,57.04],"aquif-3.5-a0.6b":[-0.966,0.168,47.13],"north-micro-vision-instruct":[-0.967,0.217,48.32],"internlm-20b":[-0.97,0.075,63.5],"kanana-2-1.3b-base":[-0.972,0.1,43.37],"yi-6b-chat-8bits":[-0.974,0.147,58.62],"codellama-13b-instruct":[-0.974,0.115,40.16],"gemma-4-e4b":[-0.976,0.112,65.08],"codellama-python-7b":[-0.977,0.153,43.03],"meta-llama-3-8b-instruct":[-0.98,0.127,58.76],"qwen3.5-0.8b-thinking":[-0.983,0.081,30.93],"llama-3-8b-instruct-gradient-1048k":[-0.984,0.094,55.35],"skywork-13b":[-0.99,0.203,56.55],"gemma-7b":[-0.991,0.07,52.26],"aquif-3-0.4b":[-0.992,0.168,45.4],"llemma-34b":[-0.993,0.119,42.82],"internlm2-base-20b":[-1.005,0.096,54.6],"qwen2.5-coder-1.5b":[-1.008,0.084,48.23],"llama-3-8b-base":[-1.009,0.074,53.32],"qwen1.5-7b":[-1.011,0.077,49.31],"jamba-v0.1":[-1.013,0.118,60.3],"internlm2.5-1.8b":[-1.014,0.122,41.27],"llama-2-70b-chat":[-1.021,0.115,63.01],"kwaiyii-13b-chat":[-1.024,0.134,54.18],"qwen1.5-7b-chat":[-1.024,0.065,47.2],"qwen1.5-moe-a2.7b":[-1.025,0.104,51.77],"codellama-13b":[-1.025,0.092,43.28],"telechat-12b":[-1.026,0.107,53.86],"llama-3.1-nemotron-70b-instruct-hf":[-1.033,0.14,25.23],"bielik-4.5b-v3":[-1.033,0.146,61.02],"qwen1.5-4b-chat":[-1.034,0.279,46.87],"deepseek-coder-7b-base-v1.5":[-1.035,0.097,50.26],"internlm2-math-base-7b":[-1.037,0.144,33.67],"codet5-16b":[-1.039,0.187,43.5],"chinchilla-70b":[-1.041,0.178,72.98],"map-neo-7b-instruct":[-1.043,0.074,48.5],"olmo-2-1124-7b":[-1.045,0.116,55.34],"kwaiyii-13b-base":[-1.048,0.134,54.19],"minicpm-moe-8x2b":[-1.05,0.106,49.36],"bitcpm-cann-1b":[-1.052,0.11,63.42],"orion-14b-base":[-1.052,0.082,61.58],"yi-9b":[-1.056,0.1,56.47],"phi-2":[-1.058,0.081,48.28],"qwen-7b":[-1.061,0.078,59.65],"llama-3.2-3b":[-1.062,0.078,47.96],"qwen2-1.5b-instruct":[-1.064,0.071,39.54],"gemma-1.1-7b-it":[-1.067,0.08,39.57],"lfm2-700m":[-1.068,0.131,43.74],"yi-6b-chat-4bits":[-1.072,0.15,56.3],"internlm2.5-1.8b-chat":[-1.08,0.094,48.34],"xdan-l1-chat-rl-v1-7b":[-1.08,0.13,39.52],"qwen3-0.6b-base":[-1.08,0.121,51.71],"bert-mtl":[-1.082,0.207,77.37],"xverse-moe-a4.2b":[-1.086,0.124,58.21],"wizardmath-13b-v1.0":[-1.09,0.127,42.91],"apertus-8b":[-1.091,0.104,56.14],"palm-540b":[-1.1,0.106,69.22],"gemma-2-7b":[-1.103,0.094,59.44],"deepseek-llm-7b-chat":[-1.106,0.076,53.75],"minicpm-2b-sft":[-1.108,0.087,50.83],"baichuan-13b-chat":[-1.11,0.247,53.13],"tfree-hat-pretrained-7b-base":[-1.11,0.124,37.57],"mistral-7b":[-1.113,0.069,51.52],"map-neo-7b-sft":[-1.114,0.075,49.44],"codellama-7b-instruct":[-1.116,0.103,31.98],"bluelm-7b-chat":[-1.122,0.108,49.15],"mistral-7b-instruct-v0.2":[-1.122,0.062,50.36],"baichuan2-7b-chat-4bits":[-1.132,0.247,52.53],"starcoder-15b":[-1.135,0.13,38.78],"qwen2-1.5b":[-1.139,0.075,46.27],"mobilemoe-m":[-1.14,0.08,52.02],"llama-1-65b":[-1.142,0.08,58.89],"codet5-6b":[-1.149,0.187,39.6],"mistral-7b-v0.2":[-1.151,0.137,56.1],"qwen2.5-0.5b-instruct":[-1.158,0.086,28.66],"lfm2.5-vl-450m":[-1.158,0.209,35.19],"qwen3-0.8b":[-1.159,0.078,33.9],"internlm2-base-7b":[-1.16,0.09,51.61],"bert-plus-plus":[-1.16,0.207,74.77],"intern-decision-0.8b":[-1.16,0.133,49.2],"internvl2.5-2b":[-1.166,0.085,46.29],"apertus-v1.1-4b":[-1.167,0.222,65.08],"codegen-16b":[-1.168,0.13,37.72],"deepseek-coder-6.7b-base":[-1.17,0.078,42.38],"chatglm2-12b-base":[-1.171,0.174,52.91],"x-omni":[-1.176,0.158,34.67],"deepseek-v2-lite":[-1.176,0.07,58.53],"python-code-13b":[-1.177,0.146,31.3],"codet5plus-16b":[-1.178,0.13,37.8],"mobilellm-r1-360m":[-1.178,0.114,21.15],"glm-130b":[-1.182,0.295,62.19],"tev1-0.8b-experimental":[-1.189,0.134,48.67],"mistral-7b-v0.1":[-1.189,0.065,48.37],"minicpm-2b-dpo-fp32":[-1.191,0.09,52.91],"deepseek-moe-16b-chat":[-1.195,0.078,51.41],"stablecode-3b":[-1.199,0.117,36.87],"gemma-3-1b-it":[-1.201,0.063,32.48],"t5gemma-2-4b-4b":[-1.206,0.074,51.52],"palm-62b":[-1.206,0.163,71.44],"qwen-vl":[-1.209,0.247,50.43],"baichuan2-13b-base":[-1.212,0.073,57.93],"tigerbot-13b-chat":[-1.219,0.131,60.36],"evabyte-6.5b":[-1.22,0.124,29.57],"qwen2.5-1.5b-pretrained":[-1.221,0.173,52.08],"internvl3.5-2b":[-1.222,0.309,24.37],"codeqwen1.5-7b":[-1.228,0.083,43.74],"yi-6b-chat":[-1.231,0.094,51.52],"chatglm2-12b":[-1.237,0.174,50.44],"solar-10.7b-v1.0":[-1.24,0.103,50.94],"deepseek-vl-7b":[-1.243,0.148,47.76],"codegen-6b":[-1.255,0.13,34.84],"internlm-chat-20b":[-1.264,0.142,55.33],"llama-1-33b":[-1.266,0.08,56.07],"codet5plus-6b":[-1.268,0.13,34.5],"coda-1.7b-base":[-1.272,0.13,33.84],"granite-4-h-300m":[-1.274,0.116,28.06],"skywork-13b-base":[-1.276,0.075,56.55],"gemma-7b-it":[-1.278,0.125,37.39],"llemma-7b":[-1.28,0.114,31.94],"yi-coder-1.5b":[-1.282,0.115,32.3],"minicpm4-0.5b":[-1.283,0.11,57.71],"llama-3.2-1.24b":[-1.285,0.104,30.73],"qwen1.5-4b":[-1.285,0.102,43.09],"zephyr-7b-beta":[-1.285,0.117,39.66],"lfm2.5-vl-1.6b":[-1.295,0.196,40.18],"vllm-sr-d3-edge":[-1.297,0.133,49.46],"lfm2-350m":[-1.298,0.101,28.88],"starcoderbase-16b":[-1.299,0.111,32.48],"map-neo-7b":[-1.314,0.08,48.57],"codegemma-2b":[-1.324,0.13,34.08],"gpt-3":[-1.331,0.112,63.44],"olmoe-1b-7b-base":[-1.334,0.112,49.35],"qwen-7b-chat":[-1.336,0.078,45.77],"mobilellm-r1-360m-base":[-1.341,0.141,26.53],"janus-pro-7b":[-1.342,0.157,32.02],"llama-2-13b":[-1.343,0.074,54.16],"olmoe-1b-7b":[-1.344,0.066,41.24],"vllm-sr-decision-2.0-eos-0.8b":[-1.348,0.134,45.5],"starcoder2-7b":[-1.354,0.08,38.74],"qwen3.5-0.8b":[-1.358,0.064,33.13],"baichuan2-13b-chat":[-1.36,0.085,45.75],"vllm-sr-decision-2.0-kai-0.6b":[-1.36,0.133,45.42],"aquila2-7b":[-1.361,0.13,60.73],"stablelm-zephyr-3b":[-1.366,0.09,45.81],"minicpm-1b-sft":[-1.371,0.091,45.67],"starcoderbase-7b":[-1.371,0.129,28.32],"internlm2-1.8b":[-1.372,0.122,31.91],"codet5-2b":[-1.374,0.13,31.1],"internlm2-chat-1.8b":[-1.375,0.091,42.33],"lfm2-vl-450m":[-1.38,0.209,29.58],"qwen2-audio-7b-instruct":[-1.38,0.157,30.93],"d1-omni-600m":[-1.382,0.125,51.36],"codegen-2b":[-1.386,0.13,30.38],"phi-3.5-vision-instruct":[-1.389,0.218,37.2],"telechat-7b":[-1.391,0.106,39.94],"apertus-v1.1-1.5b":[-1.395,0.223,59.31],"granite-4-300m":[-1.396,0.105,24.71],"codellama-7b":[-1.399,0.079,40.37],"falcon-40b":[-1.411,0.086,49.61],"mistral-7b-instruct-v0.1":[-1.429,0.088,46.66],"qwen2.5-0.5b":[-1.431,0.064,28.72],"llama-2-34b":[-1.437,0.107,35.26],"codegeex2-6b":[-1.438,0.118,26.02],"minerva-8b":[-1.444,0.148,21.97],"llama-3.2-1b-instruct":[-1.446,0.085,21.48],"mobilellm-p1-base":[-1.452,0.135,56.17],"smollm2-1.7b-instruct":[-1.453,0.074,40.68],"bitcpm-cann-0.5b":[-1.454,0.11,51.98],"internlm-chat-7b":[-1.458,0.097,47.33],"tigerbot-13b-base":[-1.462,0.131,56.63],"qwen1.5-1.8b-chat":[-1.464,0.119,39.63],"starcoder2-3b":[-1.472,0.081,36.62],"bielik-7b-instruct-v0.1":[-1.473,0.146,51.26],"qwen2.5-coder-0.5b":[-1.479,0.083,35.66],"bluelm-7b-base":[-1.48,0.105,40.76],"mobilemoe-s":[-1.485,0.081,42.79],"baichuan2-7b-chat":[-1.486,0.078,43.1],"llama-spark-8b":[-1.489,0.203,29.67],"gemma-3-1b":[-1.489,0.077,34.61],"yi-6b":[-1.49,0.094,46.28],"qwen2-0.5b-instruct":[-1.498,0.089,24.19],"gemma-2-2b":[-1.504,0.068,38.31],"olmo-2-0425-1b-instruct":[-1.509,0.076,39.93],"blt-7b":[-1.512,0.124,21],"deepseek-llm-7b-base":[-1.516,0.077,47.04],"bielik-7b-v0.1":[-1.52,0.146,49.97],"llama-2-13b-chat":[-1.526,0.085,43.68],"baichuan2-7b-base":[-1.529,0.079,50.35],"falcon3-1b":[-1.531,0.079,29.19],"internvl2-2b":[-1.534,0.081,37.26],"internlm-7b":[-1.54,0.081,49.34],"olmo-2-0425-1b-base":[-1.543,0.138,29.13],"gemma-4-e2b":[-1.545,0.104,57.43],"xverse-7b":[-1.545,0.131,49.05],"qwen1.5-1.8b":[-1.556,0.088,42.93],"mpt-30b":[-1.567,0.089,44.56],"baichuan-13b-base":[-1.571,0.079,48.79],"deepseek-moe-16b-base":[-1.572,0.077,46.19],"vicuna-7b-v1.5":[-1.573,0.255,33.13],"deepseek-coder-1.3b-base":[-1.577,0.088,31.39],"smollm2-1.7b-pretrained":[-1.587,0.164,52.46],"apertus-v1.1-0.5b":[-1.591,0.224,53.43],"huginn-3.5b":[-1.592,0.113,41.12],"gemma-2b":[-1.599,0.079,36.3],"qwen2-0.5b":[-1.599,0.078,33.88],"codegen2-7b":[-1.602,0.146,17.9],"gemini-nano-2":[-1.602,0.156,30.8],"chatglm2-6b":[-1.609,0.082,48.82],"codegen2-16b":[-1.616,0.146,17.5],"gemma-1.1-2b-it":[-1.621,0.13,22.22],"llama-1-13b":[-1.621,0.08,49.05],"telechat-1b":[-1.632,0.104,31.98],"smollm2-1.7b-base":[-1.639,0.101,32.48],"bloomz-7b1":[-1.647,0.24,34.02],"chatglm2-6b-base":[-1.65,0.099,44.08],"llama-2-7b":[-1.652,0.069,45.06],"xverse-13b":[-1.657,0.084,47.65],"starcoderbase-3b":[-1.657,0.146,16.5],"smolvlm2-0.5b":[-1.658,0.235,18.59],"llama-2-7b-chat":[-1.661,0.064,39.27],"mobilellm-p1":[-1.67,0.083,40.51],"llama-1b":[-1.674,0.16,46.32],"open-llama-13b":[-1.674,0.116,53.68],"llama-3.2-1.24b-base":[-1.688,0.077,24.97],"olmo-1.7-7b":[-1.699,0.083,42.17],"qwen-1.8b-chat":[-1.714,0.126,32.35],"gemma-2b-it":[-1.744,0.141,17.84],"qwen-1.8b":[-1.747,0.086,42.9],"vicuna-13b":[-1.752,0.089,26.55],"santacoder-1.1b":[-1.76,0.146,14.2],"pythia-2.8b":[-1.76,0.165,63.2],"codegen2-3b":[-1.777,0.146,13.83],"gliner2.5-decide":[-1.791,0.138,36.25],"mobilellm-r1.5-140m":[-1.796,0.135,8.6],"incoder-6.7b":[-1.797,0.146,13.43],"mpt-7b":[-1.798,0.084,43.57],"chinese-llama-plus-13b":[-1.802,0.247,34.77],"ziya-llama-13b-pretrain":[-1.803,0.214,33.21],"starcoderbase-1b":[-1.818,0.146,13],"llama-3.2-1b":[-1.824,0.084,39.54],"pythia-1.4b":[-1.849,0.165,60.98],"warp-albert-xxl-v2-few-shot-32-examples":[-1.85,0.207,54.17],"llama-1-7b":[-1.867,0.08,44.26],"t5gemma-2-1b-1b":[-1.891,0.076,36.18],"gpt-j-6b":[-1.904,0.146,11.4],"incoder-1.3b":[-1.904,0.146,11.4],"mobilellm-r1-140m":[-1.911,0.118,4.85],"qwen1.5-0.5b":[-1.934,0.105,24.84],"pythia-1b":[-1.935,0.165,58.48],"olmo-7b-instruct":[-1.939,0.072,35.9],"chinese-alpaca-plus-13b":[-1.953,0.099,25.72],"vicuna-7b":[-1.954,0.091,35.47],"laya":[-1.963,0.141,34.29],"trlm-135m":[-1.965,0.156,39.65],"falcon-7b":[-2.004,0.092,38.2],"codegen2-1b":[-2.006,0.146,9.73],"bloom-7b1":[-2.007,0.244,24.95],"smolvlm2-2.2b":[-2.008,0.236,23],"qwen1.5-0.5b-chat":[-2.045,0.121,27.65],"amberchat":[-2.058,0.073,30.24],"baichuan-7b":[-2.069,0.095,30.39],"deepseek-vl-1.3b":[-2.104,0.152,26.1],"emu3-8b":[-2.11,0.192,16.23],"pythia-410m":[-2.116,0.165,54.63],"falcon-e-1b-base":[-2.116,0.191,13.4],"amber-7b":[-2.133,0.086,31.2],"moss-moon-003-base":[-2.149,0.247,26.87],"alpaca-7b":[-2.177,0.105,29.98],"pythia-12b":[-2.187,0.084,36.12],"pythia-6.9b":[-2.198,0.083,35.19],"gpt-neo-2.7b":[-2.203,0.146,7.1],"olmo-7b":[-2.205,0.084,32.19],"smollm2-360m-instruct":[-2.219,0.073,26.5],"gemma-3-270m-it":[-2.222,0.072,23.9],"llama-1b-pretrained":[-2.24,0.162,44.74],"polycoder-2.7b":[-2.298,0.146,6.1],"smollm2-135m-instruct":[-2.3,0.105,23.44],"pythia-160m":[-2.304,0.165,46.97],"tinyllama-1.1b":[-2.32,0.095,25.37],"smollm1-1.7b-pretrained":[-2.321,0.149,41.54],"falcon-3-1b-base":[-2.384,0.178,9.89],"smollm1-1.7b-instruct":[-2.397,0.16,37.37],"t5gemma-2-270m-270m":[-2.437,0.08,26.96],"gemma-3-pt-270m":[-2.473,0.118,35.23],"pythia-70m":[-2.478,0.167,40.58],"chatglm-6b":[-2.507,0.111,25.17],"smollm2-360m-base":[-2.607,0.112,8.72],"gemma-3-pt-1b":[-2.629,0.144,9.7],"smollm2-135m-base":[-2.719,0.132,29.14],"stablelm-7b":[-2.856,0.146,2.4],"zyte-1b":[-2.982,0.131,4.66],"smollm2-135m-pretrained":[-3.064,0.168,34.99]},"benchmarks":[{"id":"mmlu","name":"MMLU","topic":"Multi-domain knowledge","difficulty":-1.421,"discrimination":0.954,"n":743},{"id":"mmlu-pro","name":"MMLU-Pro","topic":"Multi-domain knowledge","difficulty":-0.362,"discrimination":1.145,"n":712},{"id":"gsm8k","name":"GSM8K","topic":"Math (grade-school)","difficulty":-1.152,"discrimination":2.003,"n":672},{"id":"livecodebench","name":"LiveCodeBench","topic":"Code generation","difficulty":0.417,"discrimination":1.748,"n":630},{"id":"gpqa-diamond","name":"GPQA-diamond","topic":"Graduate-level QA","difficulty":-0.007,"discrimination":1.263,"n":611},{"id":"humaneval","name":"HumanEval","topic":"Code generation","difficulty":-0.827,"discrimination":1.823,"n":608},{"id":"mbpp","name":"MBPP","topic":"Code generation","difficulty":-1.021,"discrimination":1.308,"n":509},{"id":"math","name":"MATH","topic":"Math (competition)","difficulty":-0.395,"discrimination":2.109,"n":502},{"id":"ifeval","name":"IFEval","topic":"Instruction following","difficulty":-1.696,"discrimination":0.806,"n":467},{"id":"bbh","name":"BBH","topic":"Multi-task reasoning","difficulty":-1.094,"discrimination":1.216,"n":450},{"id":"humaneval-plus","name":"HumanEval+","topic":"Code generation","difficulty":-0.72,"discrimination":1.578,"n":439},{"id":"hellaswag","name":"HellaSwag","topic":"Commonsense reasoning","difficulty":-2.663,"discrimination":0.665,"n":413},{"id":"mbpp-plus","name":"MBPP+","topic":"Code generation","difficulty":-0.869,"discrimination":0.813,"n":379},{"id":"arc-challenge","name":"ARC-Challenge","topic":"Science QA","difficulty":-1.46,"discrimination":1.562,"n":374},{"id":"ifbench","name":"IFBench","topic":"Instruction following","difficulty":0.504,"discrimination":0.908,"n":366},{"id":"c-eval","name":"C-Eval","topic":"Chinese exams","difficulty":-1.423,"discrimination":0.913,"n":325},{"id":"winogrande","name":"WinoGrande","topic":"Coreference reasoning","difficulty":-2.529,"discrimination":0.615,"n":322},{"id":"gpqa","name":"GPQA","topic":"Graduate-level QA","difficulty":0.079,"discrimination":1.11,"n":321},{"id":"swe-bench-verified","name":"SWE-Bench Verified","topic":"Code repair","difficulty":0.805,"discrimination":1.782,"n":295},{"id":"cmmlu","name":"CMMLU","topic":"Chinese multi-domain","difficulty":-1.445,"discrimination":0.922,"n":280},{"id":"mmlu-redux","name":"MMLU-Redux","topic":"Multi-domain knowledge","difficulty":-1.243,"discrimination":1.106,"n":270},{"id":"math500","name":"MATH500","topic":"Math reasoning","difficulty":-0.758,"discrimination":2.148,"n":264},{"id":"agieval","name":"AGIEval (English)","topic":"Exams","difficulty":-0.844,"discrimination":1.011,"n":222},{"id":"scicode","name":"SciCode (sub)","topic":"Code","difficulty":1.622,"discrimination":0.827,"n":210},{"id":"piqa","name":"PIQA","topic":"Physical commonsense","difficulty":-4.25,"discrimination":0.428,"n":207},{"id":"tau2-telecom","name":"TAU2-Telecom","topic":"Agent tasks (telecom)","difficulty":0.488,"discrimination":2.182,"n":203},{"id":"aa-lcr","name":"AA-LCR","topic":"Long-context reasoning","difficulty":0.748,"discrimination":1.156,"n":197},{"id":"browsecomp","name":"BrowseComp","topic":"Web browsing","difficulty":1.18,"discrimination":2.376,"n":173},{"id":"evalplus","name":"EvalPlus","topic":"Code generation","difficulty":-0.687,"discrimination":1.593,"n":173},{"id":"arc-easy","name":"ARC-Easy","topic":"Science QA","difficulty":-2.169,"discrimination":1.633,"n":170},{"id":"triviaqa","name":"TriviaQA","topic":"Open-domain QA","difficulty":-1.234,"discrimination":0.934,"n":167},{"id":"truthfulqa","name":"TruthfulQA","topic":"Truthfulness / hallucination","difficulty":-0.892,"discrimination":0.439,"n":166},{"id":"swe-bench-multilingual","name":"SWE-Bench Multilingual","topic":"Code repair (multilingual)","difficulty":0.971,"discrimination":1.679,"n":159},{"id":"livebench","name":"LiveBench","topic":"General capability","difficulty":0.187,"discrimination":1.175,"n":155},{"id":"mgsm","name":"MGSM","topic":"Math (multilingual)","difficulty":-1.01,"discrimination":1.379,"n":150},{"id":"supergpqa","name":"SuperGPQA","topic":"Graduate-level QA","difficulty":0.611,"discrimination":0.864,"n":149},{"id":"drop","name":"DROP","topic":"Reading + reasoning","difficulty":-0.947,"discrimination":1.248,"n":148},{"id":"boolq","name":"BoolQ","topic":"Reading comprehension","difficulty":-3.212,"discrimination":0.637,"n":148},{"id":"zebralogic","name":"ZebraLogic","topic":"Logical reasoning","difficulty":0.291,"discrimination":2.944,"n":146},{"id":"crux-o","name":"CRUX-O","topic":"Code reasoning","difficulty":-0.667,"discrimination":1.128,"n":144},{"id":"arc-agi-2","name":"ARC-AGI-2","topic":"General reasoning","difficulty":1.765,"discrimination":3.616,"n":138},{"id":"longbench-v2","name":"longbench-v2","topic":"Long-context eval","difficulty":0.845,"discrimination":0.684,"n":135},{"id":"simpleqa","name":"SimpleQA","topic":"QA","difficulty":1.429,"discrimination":1.271,"n":131},{"id":"livecodebench-v5","name":"LiveCodeBench v5 (2024.10-2025.02)","topic":"Code generation","difficulty":0.431,"discrimination":1.838,"n":131},{"id":"mcp-atlas","name":"MCP-Atlas","topic":"Agent evaluation","difficulty":1.14,"discrimination":1.789,"n":129},{"id":"multichallenge","name":"MultiChallenge","topic":"Instruction following","difficulty":0.955,"discrimination":0.827,"n":129},{"id":"bfcl-v3","name":"BFCL v3","topic":"Code reasoning","difficulty":-0.418,"discrimination":0.676,"n":129},{"id":"multipl-e","name":"MultiPL-E","topic":"Code generation (multilingual)","difficulty":-0.453,"discrimination":1.234,"n":129},{"id":"multi-if","name":"Multi-IF","topic":"Instruction following (multi-task)","difficulty":-0.738,"discrimination":0.793,"n":129},{"id":"naturalquestions","name":"NaturalQuestions","topic":"Open-domain QA","difficulty":0.032,"discrimination":1.229,"n":124},{"id":"terminal-bench-2.0","name":"Terminal-Bench 2.0","topic":"Agent terminal tasks","difficulty":1.365,"discrimination":2.047,"n":123},{"id":"creative-writing-longform","name":"Longform Creative Writing","topic":"Creative writing","difficulty":0.686,"discrimination":1.002,"n":123},{"id":"arc-agi-1","name":"ARC-AGI-1","topic":"General reasoning","difficulty":1.153,"discrimination":3.381,"n":122},{"id":"alpacaeval-2.0","name":"AlpacaEval 2.0","topic":"Instruction following","difficulty":0.172,"discrimination":1.486,"n":121},{"id":"tau2-retail","name":"TAU2-Retail","topic":"Agent tasks (retail)","difficulty":0.42,"discrimination":1.488,"n":114},{"id":"commonsenseqa","name":"CommonsenseQA","topic":"Commonsense QA","difficulty":-2.23,"discrimination":0.805,"n":113},{"id":"mmmlu","name":"MMMLU","topic":"Multi-domain knowledge (multilingual)","difficulty":-0.792,"discrimination":0.939,"n":112},{"id":"crux-i","name":"CRUX-I","topic":"Code reasoning","difficulty":-0.579,"discrimination":1.107,"n":110},{"id":"aider-polyglot","name":"Aider-Polyglot","topic":"Code assistant eval","difficulty":0.742,"discrimination":2.805,"n":106},{"id":"mmlu-stem","name":"MMLU-STEM","topic":"STEM knowledge","difficulty":-1.023,"discrimination":1.163,"n":106}]},"faix-visual":{"sd":0.301,"ext":{"gpt-6-astra":[2.28,0.134,83.53],"qwen3.8-max":[2.236,0.085,84.63],"qwen3.8-omni-flash":[2.208,0.119,85.05],"qwen3.8-flash-next":[2.074,0.105,79.31],"claude-fable-5":[2.056,0.099,80.32],"claude-mythos-5":[1.909,0.125,83.42],"gemini-3.6-flash":[1.835,0.148,81.62],"kimi-k3":[1.83,0.107,83.96],"gpt-5.6-sol":[1.811,0.082,78.72],"qwen3.7-plus":[1.789,0.082,79.49],"gemini-3.1-pro":[1.786,0.067,79.34],"gemini-3.5-flash":[1.758,0.11,81.34],"gemini-3.8-flash":[1.747,0.199,84.83],"seed2.1-pro":[1.745,0.083,79.41],"muse-spark":[1.742,0.131,77.88],"gpt-5.4":[1.686,0.088,79.31],"claude-opus-5.5":[1.673,0.186,78.81],"seed2.1-turbo":[1.663,0.082,79.41],"gemini-3.7-flash":[1.659,0.18,83.6],"qwen3.6-plus":[1.618,0.076,79.57],"qwen3.5-397b-a17b":[1.611,0.067,77.27],"seed2.0-lite-0428":[1.602,0.099,80.31],"gpt-5.2-extra-high":[1.584,0.138,83.45],"gpt-5.5":[1.567,0.076,77.51],"dots3-note-preview":[1.557,0.116,81.52],"gemini-3-pro":[1.542,0.055,79.82],"claude-opus-4.8":[1.515,0.082,73.73],"gpt-5.6-terra":[1.514,0.151,79.26],"gemini-3-flash":[1.514,0.077,78.24],"qwen3.5-122b-a10b":[1.511,0.065,75.11],"seed2.0-pro":[1.504,0.095,74.92],"ace-brain-0.6-9b":[1.452,0.224,78.45],"ling-3.0-flash-vl":[1.445,0.125,85.62],"glm-5v-turbo":[1.432,0.161,76.3],"kimi-k2.5-thinking":[1.425,0.091,77.91],"qwen3.8-27b":[1.422,0.09,78.86],"qwen3.6-27b":[1.418,0.067,80.32],"qwen3.5-27b":[1.416,0.065,74.97],"kimi-k2.6-thinking":[1.412,0.125,85.72],"sensenova-mars-32b":[1.41,0.232,80.35],"glm-5.3-flash":[1.401,0.114,74.31],"claude-opus-5":[1.385,0.134,75.57],"qwen3.5-35b-a3b":[1.381,0.067,74.91],"kimi-k2.5":[1.377,0.073,80.58],"qwen3.6-35b-a3b":[1.35,0.067,79.72],"mimo-v2.5":[1.342,0.171,82.2],"seed2.0-lite":[1.332,0.097,73.2],"ui-venus-1.5-30b-a3b":[1.319,0.125,78.5],"holo2-235b-a22b":[1.318,0.115,84.28],"muse-glimmer-30b":[1.277,0.142,76.07],"intern-s2-preview":[1.257,0.142,76.38],"mimo-v2-omni":[1.251,0.171,80.73],"gpt-5.2-thinking-xhigh":[1.249,0.106,77.94],"mai-ui-32b":[1.245,0.125,76.32],"ui-venus-1.5-8b":[1.238,0.125,76.93],"gemini-3.5-flash-lite":[1.235,0.126,82.46],"seed1.8":[1.232,0.071,76.4],"qwen3.5-omni-plus":[1.224,0.083,78.36],"o3":[1.221,0.129,65],"claude-opus-4.7":[1.206,0.082,72.19],"minimax-m3":[1.205,0.181,82.7],"sensenova-mars-8b":[1.195,0.22,76.76],"holo2-30b-a3b":[1.167,0.105,80.44],"gpt-5.2":[1.166,0.075,75.66],"claude-opus-4.6":[1.149,0.092,71.29],"nemotron-3.5-super-vl-120b-a12b":[1.145,0.109,72.25],"o3-high":[1.135,0.14,78.17],"vista-9b":[1.125,0.142,77.7],"gpt-5.4-mini":[1.119,0.178,69.87],"claude-sonnet-5":[1.116,0.153,71.87],"qwen3-vl-235b-a22b-thinking":[1.094,0.052,74.42],"qwen3.5-9b":[1.092,0.058,76.31],"gemini-4-argon":[1.09,0.229,77.98],"gemini-3.1-flash-lite":[1.074,0.118,74.6],"holo1.5-72b":[1.073,0.098,84.33],"minicpm-v-4.7-35b-a3b":[1.069,0.092,77.82],"mai-ui-8b":[1.068,0.125,72.95],"qwen3-vl-235b-a22b":[1.067,0.065,72.42],"gemma-4-31b-it":[1.059,0.072,74.49],"hy-embodied-vlm-1.0":[1.057,0.186,72.64],"step-gui-8b":[1.048,0.136,75.13],"gemini-2.5-pro":[1.037,0.05,70.21],"o4-mini-high":[1.015,0.14,75.93],"step3-vl-10b-pacore":[1.009,0.132,83.43],"claude-opus-4.5-thinking":[0.997,0.105,75.36],"ernie-5.0":[0.996,0.083,78.05],"inkling-small":[0.976,0.117,62.83],"gta1-32b":[0.976,0.142,74.67],"rynnbrain1.1-9b":[0.967,0.2,72.48],"points-gui-g-8b":[0.965,0.142,73.87],"gpt-5-high":[0.958,0.065,72.99],"intern-s1-pro":[0.952,0.12,73.73],"ovis2.6-80b-a3b":[0.948,0.081,77.01],"nemotron-3.5-super-vl-120b-a12b-nvfp4":[0.94,0.108,70.47],"exaone-4.5-33b-thinking":[0.928,0.1,72.9],"gemma-4-26b-a4b-it":[0.925,0.093,72.58],"seed1.5-vl-thinking":[0.916,0.057,70.84],"seed-1.5-vl":[0.904,0.08,72.39],"zwz-8b":[0.903,0.204,78.42],"ovis2.6-30b-a3b":[0.901,0.073,78.36],"physbrain1.5-8b":[0.892,0.201,72.88],"molmopoint-gui-8b":[0.887,0.142,74.53],"claude-opus-4.5":[0.884,0.069,72.71],"ui-venus-72b":[0.883,0.097,78.57],"holo2-8b":[0.881,0.105,75.49],"keye-vl-2.0-30b-a3b":[0.879,0.206,80.37],"step-gui-4b":[0.879,0.125,69.5],"vista-4b":[0.873,0.142,73.07],"claude-sonnet-4.6":[0.872,0.178,66.57],"qwen3-vl-32b-instruct":[0.865,0.056,71.16],"qwen3-vl-32b-thinking":[0.862,0.084,76.51],"skywork-r1v4":[0.856,0.232,76.73],"step3-vl-10b-sere":[0.853,0.132,81.53],"dots-vlm1":[0.843,0.076,78.39],"holo1.5-7b":[0.842,0.098,81.66],"holo2-4b":[0.835,0.115,77.77],"gpt-5-mini-high":[0.83,0.086,69.48],"comet-60b-a12b-fp8":[0.822,0.108,68.11],"comet-60b-a12b":[0.815,0.109,68.11],"zwz-4b":[0.813,0.214,77.66],"qwen3.5-omni-flash":[0.809,0.082,73.52],"robobrain2.5-8b":[0.803,0.197,69.63],"qwen3-vl-235b-a22b-instruct":[0.803,0.119,78.5],"gpt-5":[0.796,0.067,72.63],"gpt-5.4-nano":[0.788,0.142,65.17],"qwen3.5-4b":[0.785,0.057,72.28],"comet-60b-a12b-nvfp4":[0.777,0.108,67.51],"gui-owl-7b":[0.774,0.127,67.5],"step3-vl-10b":[0.772,0.083,73.49],"ming-flash-omni-2.0":[0.769,0.093,77.86],"interfaze":[0.767,0.231,74.63],"glm-4.6v":[0.763,0.061,72.28],"zdtaichu5.0-9b":[0.762,0.139,75.83],"nemotron-3-nano-omni-30b-a3b-reasoning":[0.76,0.152,62.08],"interfaze-1.1-lite":[0.751,0.227,72.63],"ui-venus-1.5-2b":[0.747,0.125,66.38],"ovisocr3":[0.743,0.263,72],"gui-owl-32b":[0.727,0.142,69.7],"gpt-5-mini":[0.725,0.06,71.59],"seed2.0-mini":[0.725,0.155,66.54],"opencua-32b":[0.719,0.142,69.43],"grok-4.2":[0.719,0.168,61.9],"qwen3-vl-30b-a3b-instruct":[0.715,0.05,69.45],"glm-4.5v":[0.712,0.059,70.12],"claude-3.7-sonnet-thinking":[0.705,0.093,69.74],"qwen3-vl-30b-a3b-thinking":[0.693,0.095,72.93],"gta1-7b":[0.685,0.142,69.33],"hy-embodied-0.5-mot-2b":[0.685,0.185,66.54],"embodied-r1.5-8b":[0.676,0.197,68.37],"ernie-4.5-vl-28b-a3b-thinking":[0.663,0.086,74.75],"claude-4.5-sonnet-thinking":[0.647,0.139,62.62],"molmo2-er":[0.636,0.197,67.68],"claude-4.5-haiku":[0.629,0.112,58.85],"mai-ui-2b":[0.627,0.125,62.75],"qianfan-ocr":[0.621,0.147,75.45],"deepseek-v4-flash-vision-exp":[0.617,0.211,67.17],"ace-brain-0.5-8b":[0.615,0.196,67.53],"ui-tars-1.5-7b":[0.611,0.099,74.44],"llada-ui":[0.61,0.136,65.7],"claude-sonnet-4.5":[0.605,0.063,70.26],"qwen-drive-1.0-4b":[0.604,0.109,65.87],"egm-8b":[0.603,0.342,91.73],"molmo2-gui-8b":[0.586,0.142,69.07],"ui-venus-7b":[0.585,0.094,73.91],"groundnext-7b":[0.58,0.143,68.9],"reka-edge-2603":[0.579,0.245,78.13],"gpt-5.1":[0.574,0.13,62.39],"opencua-7b":[0.566,0.142,65.87],"internvl3.5-241b":[0.561,0.16,71.67],"holo1.5-3b":[0.542,0.098,77.95],"claude-opus-4.1":[0.538,0.072,66.71],"jedi-7b":[0.535,0.142,65.33],"command-a-plus-05-2026":[0.528,0.131,71.88],"gpt-4.1-mini":[0.528,0.14,65.97],"qwen2.5-vl-72b":[0.527,0.063,72.98],"gpt-4.1":[0.52,0.122,57.63],"rynnbrain-30b-a3b":[0.52,0.134,73.74],"longcat-next":[0.518,0.081,72.11],"glm-4.6v-flash":[0.514,0.067,64.51],"pelican-vl-72b":[0.511,0.134,72.66],"qwen3-vl-8b-thinking":[0.51,0.069,75.19],"apriel-1.6-15b-thinker":[0.509,0.093,68.28],"gemini-2.5-flash":[0.502,0.063,71.39],"nova-2-omni":[0.499,0.18,77.75],"gemini-2.5-flash-thinking":[0.481,0.129,81.21],"qwen3-vl-8b-instruct":[0.478,0.05,67.79],"rynnbrain-8b":[0.473,0.135,73.63],"cogvlm-grounding-generalist":[0.449,0.339,90.43],"internvl2-76b":[0.44,0.335,90.17],"o1":[0.44,0.13,66.78],"mimo-vl-7b-rl-2508":[0.438,0.09,72.56],"qwen3-omni-30b-a3b-thinking":[0.437,0.125,81],"mimo-vl-7b-rl":[0.423,0.059,72.22],"r-4b-base":[0.422,0.119,67.5],"gemini-robotics-er-1.5-thinking":[0.42,0.197,64.76],"infinity-parser2-pro":[0.42,0.126,81.63],"qwen3-vl-4b-thinking":[0.417,0.066,65.06],"qwen2.5-vl-72b-instruct":[0.414,0.057,62.91],"gemini-2.5-flash-lite":[0.413,0.065,66.94],"minicpm-o-4.5-thinking":[0.409,0.128,80.55],"openpangu-vl-7b":[0.406,0.09,75.74],"zwz-7b":[0.399,0.21,72.98],"llama-4-maverick":[0.395,0.153,78.22],"llama-4-maverick-17b-128e-instruct":[0.395,0.153,78.22],"physbrain1.5-2b":[0.387,0.2,65.83],"grok-4":[0.382,0.198,68.28],"robobrain-2.5-4b":[0.378,0.195,61.02],"claude-sonnet-4":[0.375,0.054,62.56],"glm-4.1v":[0.373,0.069,64.83],"grok-4.1-fast":[0.368,0.171,53.88],"ui-tars-72b":[0.367,0.141,47.27],"ferret-v2-13b":[0.364,0.339,89.8],"ferret-v2-7b":[0.364,0.34,89.87],"minicpm-o-4.5":[0.359,0.094,73.08],"step-3":[0.353,0.079,62.59],"holotron-12b":[0.348,0.134,74.16],"joyai-vl-interaction":[0.345,0.193,66.8],"rynnbrain-4b":[0.332,0.138,73.1],"qwen2-vl-72b-instruct":[0.331,0.098,76.08],"hunyuanocr-1.5":[0.326,0.263,64.83],"mimo-vl-7b-sft":[0.32,0.059,70.98],"longcat-flash-omni":[0.315,0.164,77.97],"penguin-vl-8b":[0.311,0.095,71.18],"gpt-4.5":[0.31,0.118,72.32],"qwen2.5-vl-32b-instruct":[0.3,0.12,63.18],"apriel-1.5-15b-thinker":[0.292,0.093,64.21],"molmopoint-8b":[0.285,0.089,71.66],"mistral-medium-3":[0.277,0.191,84.43],"claude-3.7-sonnet":[0.27,0.067,67.62],"deepseek-v4.1-flash-base":[0.27,0.181,79],"internvl2.5-78b":[0.257,0.07,72.22],"internvl3.5-30b-a3b-flash":[0.256,0.083,69.11],"texthawk2":[0.253,0.336,88.77],"qwen3-omni-30b-a3b-instruct":[0.252,0.062,69.06],"qwen3-vl-4b-instruct":[0.245,0.05,64.75],"gemini-robotics-er-1.5":[0.243,0.197,62.2],"manzano-30b":[0.222,0.116,81.56],"molmo2-8b":[0.22,0.09,71.24],"llama-4-scout-17b":[0.218,0.153,75.1],"llama-4-scout-17b-16e":[0.218,0.153,75.1],"gemma-4-12b-it":[0.218,0.116,70.94],"doubao-1.5-vision-pro":[0.21,0.116,63.27],"keye-vl-8b":[0.197,0.096,58.12],"ui-tars-7b":[0.197,0.126,51.95],"internvl3-78b":[0.177,0.105,58.93],"gemini-2.0-pro":[0.16,0.112,67.85],"oryx-1.5-32b":[0.158,0.22,71.15],"mistral-small-3.2-24b-instruct":[0.156,0.148,75.64],"youtu-vl-4b-instruct":[0.155,0.075,68.58],"glm-4.1v-9b":[0.154,0.126,75.58],"glm-4.1v-9b-thinking":[0.153,0.094,69.79],"mistral-small-3.1-24b-instruct":[0.147,0.171,81.39],"eagle2.5-8b":[0.146,0.105,72.77],"qwen2-vl-72b":[0.143,0.076,70.84],"holo1-7b":[0.13,0.099,69.02],"cosmos3-nano":[0.127,0.108,61.86],"pixtral-large-2411":[0.127,0.137,67.7],"internvl2.5-38b":[0.126,0.07,68.96],"gpt-4o-2024-11-20":[0.119,0.182,73.07],"command-a-vision-07-2025":[0.116,0.146,66.92],"claude-3.5-sonnet-20240620":[0.111,0.087,69.8],"molmo2-4b":[0.097,0.095,70.95],"minicpm-v-4.5-8b":[0.096,0.085,71.44],"internvl2-pro":[0.086,0.104,77.33],"claude-3.5-sonnet":[0.08,0.075,68.75],"ovis2-8b":[0.075,0.221,64.27],"kimi-vl-a3b-thinking-2506":[0.075,0.069,57.5],"gpt-4o":[0.073,0.053,65.08],"qwen3.5-2b":[0.062,0.066,64.88],"internvl3-38b":[0.062,0.108,57.27],"internvl3.5-gpt-oss-20b-a4b":[0.044,0.119,77.24],"cosmos-reason2-8b":[0.033,0.089,64.13],"moondream-9b-a2b":[0.032,0.213,88.37],"gpt-4o-0513":[0.029,0.14,78.46],"pelican-vl-7b":[0.022,0.137,67.08],"gpt-4o-2024-05-13":[0.013,0.071,67.48],"keye-vl-1.5-8b":[0.011,0.098,70.58],"molmo-72b":[0.01,0.097,75],"mage-vl":[0.004,0.104,68.12],"internvl3-14b":[-0.009,0.119,65.9],"qvq-72b":[-0.017,0.15,59.2],"xiaomi-ocr-0":[-0.021,0.264,57.7],"plm-8b":[-0.023,0.112,68.07],"dots.mocr":[-0.024,0.12,74.7],"molmopoint-o-7b":[-0.024,0.14,75.57],"d1-3b":[-0.03,0.196,71.41],"gpt-5-mini-minimal":[-0.03,0.061,59.37],"gpt-03-cua":[-0.032,0.133,47.5],"mimo-embodied-7b":[-0.036,0.101,61.96],"gpt-5-minimal":[-0.046,0.08,62.98],"gemini-2.0-flash":[-0.048,0.146,65.3],"ferret-13b":[-0.054,0.334,86.04],"internvl3.5-8b":[-0.055,0.056,64.69],"ovis2-34b":[-0.059,0.154,68.33],"glm-ocr":[-0.064,0.273,54.93],"molmo2-o-7b":[-0.072,0.114,70.42],"minicpm-v-4.7-1b":[-0.081,0.091,61.06],"minicpm-v-4.6-thinking":[-0.091,0.09,61.79],"deepseek-vl2":[-0.094,0.116,79.28],"gemini-1.5-pro":[-0.099,0.066,66.22],"internvl2-llama-3-76b":[-0.101,0.067,69.02],"internvl2.5-26b":[-0.115,0.071,67.35],"videotemp-o3-7b":[-0.121,0.167,54.54],"ovis2-16b":[-0.126,0.154,67.13],"qwen2.5-vl-7b":[-0.128,0.049,60.12],"qwen3-vl-2b-thinking":[-0.132,0.076,56.3],"uground-v1-7b":[-0.133,0.137,57.62],"manzano-3b":[-0.142,0.116,78.02],"glm-4v-plus":[-0.148,0.122,73.87],"holo1-3b":[-0.15,0.102,64.86],"kimi-vl-a3b-thinking":[-0.15,0.106,69.26],"rynnbrain-2b":[-0.157,0.138,67.19],"kanana-1.5-o-9.8b-instruct-2602":[-0.163,0.102,63.31],"videochat-flash-7b":[-0.179,0.176,60.73],"grok-4-fast-thinking":[-0.184,0.101,56.48],"bagel-7b-mot":[-0.195,0.095,67.77],"fastvlm-7b":[-0.199,0.135,77.37],"minicpm-v-4.6":[-0.202,0.076,61.12],"internvl3.5-4b":[-0.204,0.06,64.57],"robobrain-2.0":[-0.21,0.14,67.33],"deepseek-vl2-small":[-0.216,0.116,77.75],"kimi-vl-a3b-instruct":[-0.217,0.107,68.07],"qwen3-vl-2b-instruct":[-0.222,0.053,56.47],"aria":[-0.224,0.144,76.56],"qwen2-vl-7b-instruct":[-0.234,0.098,69.8],"internvl-8b":[-0.234,0.063,66.72],"nvlm-d-72b":[-0.243,0.108,74.11],"zaya1-vl-8b":[-0.246,0.121,74.63],"penguin-vl-2b":[-0.247,0.092,64.12],"plm-3b":[-0.263,0.109,65.62],"internvl2-40b":[-0.271,0.07,64.54],"shikra-13b":[-0.272,0.324,82.68],"internvl3-9b":[-0.292,0.119,60.48],"gpt-5-nano":[-0.293,0.073,59.38],"qwen3.5-ocr":[-0.296,0.263,55.03],"llava-onevision-7b-si":[-0.297,0.221,59.6],"shikra-7b":[-0.299,0.334,83.64],"lfm2.5-vl-3b":[-0.308,0.089,66.81],"gemini-1.5-flash":[-0.312,0.104,69.68],"cosmos-reason1-7b":[-0.312,0.116,47.83],"llava-onevision-2-8b":[-0.314,0.116,55.73],"bagel-14b":[-0.317,0.135,74.98],"gemini-1.0-ultra":[-0.32,0.143,75.17],"internvl2.5-8b":[-0.327,0.07,66.21],"internvl3-8b":[-0.338,0.089,51.22],"llava-onevision-72b":[-0.34,0.067,64.36],"gpt-4o-mini":[-0.342,0.121,58.27],"ovis1.6-gemma2-9b":[-0.346,0.132,67.06],"claude-3.5-sonnet-20241022":[-0.354,0.163,60.17],"llava-video-7b":[-0.359,0.175,57.16],"videollama2-72b":[-0.363,0.252,62.17],"infinity-parser2-flash":[-0.363,0.127,71.83],"moss-vl-realtime":[-0.372,0.193,55.14],"llama-3.2v-90b-instruct":[-0.374,0.099,70.49],"qwen2.5-omni-7b":[-0.379,0.089,64.97],"gemma-3-27b-vl":[-0.395,0.072,49.23],"llada2.0-uni":[-0.4,0.09,66.74],"qwen2.5-vl-3b":[-0.4,0.064,65.02],"robobrain-2.0-7b":[-0.408,0.136,59.54],"jina-vlm-2.4b-20251117":[-0.431,0.118,72.23],"phi-4-reasoning-vision-15b":[-0.458,0.099,63.56],"internvl2-26b":[-0.493,0.068,61.29],"gpt-4o-mini-2024-07-18":[-0.506,0.143,66.72],"gpt-4-turbo-2024-04-09":[-0.51,0.13,70.55],"gpt-4v":[-0.512,0.074,62.66],"qwen2-vl-7b":[-0.523,0.069,63.49],"mm1.5-30b":[-0.537,0.12,73.04],"internvl2.5-4b":[-0.54,0.068,61.63],"internvl3.5-2b":[-0.549,0.074,61.38],"molmo-7b-d":[-0.553,0.095,69.43],"pixtral-12b":[-0.553,0.098,64.93],"gemma-3-27b-it":[-0.562,0.073,60.35],"minicpm-o-2.6":[-0.571,0.089,56.05],"blip-3o-4b":[-0.581,0.209,67.48],"ovis1.5-gemma2-9b":[-0.583,0.147,61.4],"lfm2-vl-3b":[-0.585,0.097,61.5],"cogvlm2-llama3-chinese-chat-19b":[-0.592,0.164,71.57],"grok-1.5v":[-0.594,0.167,74.93],"internlm-xcomposer2.5":[-0.598,0.1,66.01],"qwen3.5-0.8b-thinking":[-0.611,0.091,54.38],"ovis1.5-llama3-8b":[-0.632,0.147,60.39],"minicpm-v-2_6":[-0.634,0.074,58.2],"internvl2-8b":[-0.637,0.066,61.32],"llm-jp-4-vl-9b":[-0.637,0.108,60.2],"llm-jp-4-vl-9b-beta":[-0.644,0.102,60.43],"gpt-4-1106-vision-preview":[-0.651,0.107,65.4],"gemma-4-e4b-it":[-0.652,0.085,59.71],"llada-o":[-0.654,0.094,62.51],"llava-onevision-7b":[-0.663,0.089,62.51],"internvl3-2b":[-0.664,0.081,63.59],"claude-3-sonnet":[-0.674,0.11,62.88],"qwen3.5-0.8b":[-0.679,0.065,52.19],"baichuan-omni":[-0.686,0.144,62.97],"internvl-chat-v1.5":[-0.732,0.071,58.69],"llava-next-110b":[-0.734,0.162,68.98],"internlm-xcomposer2-4khd-7b":[-0.758,0.096,63.75],"llama-3.2v-11b-instruct":[-0.767,0.104,66.2],"north-micro-vision-instruct":[-0.767,0.111,64.47],"ofa-large":[-0.774,0.36,71.97],"reka-flash":[-0.775,0.147,57.24],"molmo-7b-o":[-0.775,0.101,67.68],"unified-io-2-xxl":[-0.775,0.223,79.73],"cogvlm2-llama3-chat-19b":[-0.777,0.126,67.04],"ministral-3-3b-instruct":[-0.779,0.114,62.82],"gemma-3-12b-it":[-0.785,0.127,55.39],"qwen-vl-max":[-0.786,0.091,61.25],"claude-3-opus":[-0.794,0.086,59.09],"fastvlm-1.5b":[-0.805,0.126,68.5],"hyperclovax-seed-omni-8b":[-0.806,0.098,55.78],"deepseek-vl2-tiny":[-0.815,0.116,69.99],"gemini-pro":[-0.818,0.102,63.05],"aquila-vl-2b":[-0.827,0.096,62.52],"gemma-4-e2b-it":[-0.836,0.074,54.6],"glm-4v-9b":[-0.836,0.101,63.71],"internvl2-4b":[-0.852,0.069,56.14],"moondream2":[-0.86,0.28,43.16],"gemini-1.5-flash-8b-0827":[-0.881,0.178,66.12],"minicpm-llama3-v2.5":[-0.887,0.099,62.23],"deepseek-ocr":[-0.887,0.331,27.3],"cambrian-1-34b":[-0.892,0.122,65.83],"gemini-1.0-pro":[-0.898,0.093,61.64],"llada-v":[-0.899,0.092,59.13],"cambrian-34b":[-0.908,0.092,62.19],"qwen2-vl-2b-instruct":[-0.912,0.092,61.63],"step-1v-32k":[-0.919,0.138,61.43],"claude-3-haiku":[-0.923,0.102,60.18],"internvl2.5-2b":[-0.939,0.068,55.66],"mm1.5-7b":[-0.943,0.132,65.59],"internvl-u":[-0.944,0.092,58.92],"videochat2-hd-mistral":[-0.953,0.22,52.8],"phi-3-vision-4b":[-0.957,0.094,64.5],"blip-3-4b":[-0.971,0.167,60.34],"internvl3-1b":[-0.972,0.119,44.64],"gemini-1.0-pro-vision":[-0.997,0.194,57.48],"bunny-llama3-8b":[-1.003,0.182,55.48],"mini-gemini-hd-34b":[-1.009,0.116,57.06],"qwen2-vl-2b":[-1.015,0.074,53.48],"lfm2.5-vl-1.6b":[-1.037,0.069,50.68],"vila1.5-40b":[-1.047,0.097,53.35],"gpt-5-nano-minimal":[-1.05,0.079,46.54],"phi-4-multimodal-instruct":[-1.054,0.1,52.59],"harmon-1.5b":[-1.057,0.239,57.17],"lfm2-vl-1.6b":[-1.066,0.18,48.88],"internvl3.5-1b":[-1.066,0.18,48],"mm1.5-3b":[-1.072,0.115,66.44],"llava-next-34b":[-1.079,0.088,59.54],"qwen-vl-plus":[-1.086,0.097,58],"sharegpt4v-13b":[-1.091,0.154,47.46],"phi-3.5-vision-instruct":[-1.091,0.074,52.94],"cambrian-1-8b":[-1.097,0.123,66.03],"vita":[-1.098,0.129,58.98],"phi-3-vision-128k-instruct":[-1.1,0.183,55.7],"internlm-xcomposer2-vl-7b":[-1.119,0.093,57.03],"molmoe-1b":[-1.12,0.104,64.14],"bunny-4b":[-1.134,0.2,64.07],"xgen-mm-interleave-4b":[-1.149,0.132,63.54],"gemma-3n-e2b-it":[-1.157,0.092,48.52],"internvl-chat-v1.2":[-1.186,0.134,59.38],"internvl2.5-1b":[-1.208,0.069,50.81],"llava-1.6-7b":[-1.213,0.193,53.97],"llava-llama-3-8b":[-1.215,0.178,51.97],"llava-next-llama3":[-1.222,0.145,60.93],"internvl2-2b":[-1.237,0.069,53.03],"paddleocr-vl-1.6":[-1.255,0.275,36.7],"phi-3.5-vision-4b":[-1.261,0.143,62.03],"idefics2-8b":[-1.268,0.117,54.87],"fastvlm-0.5b":[-1.29,0.126,65.8],"mm1-30b":[-1.303,0.114,62.73],"llava-internlm2-20b-qlora":[-1.318,0.156,53.41],"reka-edge":[-1.329,0.147,44.34],"cogagent-18b":[-1.329,0.105,52.89],"llama-3-vila1.5-8b":[-1.329,0.192,51.58],"llava-next-7b":[-1.336,0.195,50.2],"mobilevlm-v2-3b":[-1.354,0.321,53.87],"smolvlm2-2.2b":[-1.357,0.075,48.7],"docowl-1.5-chat":[-1.363,0.124,55.14],"dreamllm-7b":[-1.385,0.282,42.47],"emu3-8b":[-1.387,0.141,60.33],"sphinx-v2":[-1.403,0.13,18.68],"llava-1.6-13b":[-1.412,0.122,52.79],"lfm2.5-vl-450m":[-1.417,0.142,53.7],"llava-1.6-mistral-7b":[-1.435,0.147,43.9],"kosmos2":[-1.447,0.389,17.73],"cogvlm-17b-chat":[-1.449,0.112,58.83],"vila-13b":[-1.453,0.216,50.1],"mm1.5-1b":[-1.456,0.133,57.48],"deepseek-vl-7b":[-1.512,0.103,47.86],"paligemma-mix-3b":[-1.524,0.141,55.02],"internvl2-1b":[-1.53,0.07,48.84],"yi-vl-34b":[-1.531,0.162,44.42],"minicpm-v-2.0-3b":[-1.535,0.093,56.42],"sharegpt4v-7b":[-1.574,0.125,44.42],"vila1.5-3b":[-1.636,0.155,58.25],"janus-pro-7b":[-1.642,0.135,52.45],"t5gemma-2-4b-4b":[-1.645,0.15,56.86],"monkey":[-1.649,0.143,49.61],"mini-gemini-2b":[-1.663,0.247,40.7],"gemini-nano-2":[-1.666,0.147,51.54],"emu2-chat":[-1.671,0.14,50.87],"sphinx-2k":[-1.673,0.152,59.03],"nemotron-nano-12b-v2-vl":[-1.678,0.126,34.34],"qwen-vl-chat":[-1.755,0.107,60.61],"lfm2-vl-450m":[-1.773,0.141,48.45],"minicpm-v":[-1.784,0.155,46.85],"llava-onevision-0.5b":[-1.794,0.085,42.28],"mplug-owl2":[-1.798,0.135,57.17],"deepseek-vl-1.3b":[-1.803,0.143,50.21],"yi-vl-6b":[-1.806,0.15,41.51],"internlm-xcomposer":[-1.86,0.158,41.53],"llava-1.5-13b":[-1.86,0.106,48.23],"blip-2-vicuna-13b":[-1.879,0.227,56.13],"mplug-docowl-7b":[-1.898,0.212,57.4],"janus-pro-1.5b":[-1.9,0.157,44.72],"smolvlm2-0.256b":[-1.919,0.239,23.98],"ureader":[-1.935,0.131,42.96],"lumina-dimoo":[-1.948,0.121,36.52],"alpamayo-1.5-10b":[-1.978,0.155,18.99],"smolvlm2-0.5b":[-1.982,0.122,44.76],"qwen-vl":[-2.101,0.131,60.76],"llava-1.5-7b":[-2.106,0.105,44.17],"textmonkey":[-2.139,0.138,43.79],"t5gemma-2-1b-1b":[-2.184,0.153,47.46],"idefics-80b-instruct":[-2.191,0.142,37.7],"llava-v1-7b":[-2.25,0.158,38.74],"instructblip-7b":[-2.312,0.141,44.08],"deepseek-ocr-2":[-2.55,0.183,37.59],"openflamingo-v2":[-2.776,0.153,28.24],"minigpt-4-v1-7b":[-2.893,0.161,24.91],"t5gemma-2-270m-270m":[-3.011,0.162,30.04]},"benchmarks":[{"id":"mmmu","name":"MMMU","topic":"Multimodal understanding","difficulty":-0.783,"discrimination":0.727,"n":307},{"id":"ai2d","name":"AI2D","topic":"Diagram understanding (VQA)","difficulty":-2.689,"discrimination":0.651,"n":258},{"id":"charxiv-rq","name":"CharXiv (RQ)","topic":"Chart reasoning (PDF)","difficulty":0.114,"discrimination":1.083,"n":249},{"id":"docvqa","name":"DocVQA","topic":"Document understanding (VQA)","difficulty":-2.788,"discrimination":0.931,"n":240},{"id":"ocrbench","name":"OCRBench V2","topic":"OCR (vision text extraction)","difficulty":-2.249,"discrimination":0.662,"n":239},{"id":"realworldqa","name":"RealWorldQA","topic":"Real-world visual QA","difficulty":-1.948,"discrimination":0.463,"n":228},{"id":"chartqa","name":"ChartQA","topic":"Chart understanding (VQA)","difficulty":-2.785,"discrimination":0.619,"n":219},{"id":"mathvista-mini","name":"MathVista-Mini","topic":"Math reasoning (multimodal)","difficulty":-0.912,"discrimination":0.877,"n":211},{"id":"mmbench-v1.1-en","name":"MMBench v1.1 (EN)","topic":"Multimodal understanding (English)","difficulty":-2.3,"discrimination":0.705,"n":210},{"id":"mmstar","name":"MMStar","topic":"Multimodal reasoning","difficulty":-1.107,"discrimination":0.596,"n":209},{"id":"mmmu-pro","name":"MMMU PRO","topic":"Multimodal understanding (hard)","difficulty":0.124,"discrimination":0.996,"n":201},{"id":"mathvision","name":"MathVision","topic":"Math reasoning (multimodal)","difficulty":0.235,"discrimination":1.504,"n":191},{"id":"textvqa","name":"TextVQA","topic":"Text-based VQA","difficulty":-2.859,"discrimination":0.516,"n":191},{"id":"mmbench-v1.1-cn","name":"MMBench v1.1 (CN)","topic":"Multimodal understanding (Chinese)","difficulty":-1.988,"discrimination":0.761,"n":188},{"id":"blink","name":"BLINK","topic":"Multimodal grounding","difficulty":-0.702,"discrimination":0.541,"n":167},{"id":"infovqa","name":"InfoVQA","topic":"Infographic VQA","difficulty":-1.402,"discrimination":0.892,"n":166},{"id":"hallusionbench","name":"HallusionBench","topic":"Multimodal hallucination","difficulty":-0.734,"discrimination":0.369,"n":163},{"id":"charxiv-dq","name":"CharXiv (DQ)","topic":"Chart description (PDF)","difficulty":-1.028,"discrimination":1.204,"n":157},{"id":"videomme-nosub","name":"VideoMME (w/o sub)","topic":"Video understanding","difficulty":-1.138,"discrimination":0.598,"n":120},{"id":"mvbench","name":"MVBench","topic":"Video QA","difficulty":-1.916,"discrimination":0.37,"n":118},{"id":"screenspot-pro","name":"ScreenSpot-Pro","topic":"Screen UI locators","difficulty":0.625,"discrimination":1.351,"n":111},{"id":"mathvista","name":"MathVista","topic":"Multimodal math reasoning","difficulty":-1.092,"discrimination":0.796,"n":111},{"id":"erqa","name":"ERQA","topic":"Spatial reasoning","difficulty":0.516,"discrimination":0.591,"n":110},{"id":"mmvet","name":"MMVet","topic":"Multimodal evaluation","difficulty":-1.118,"discrimination":0.739,"n":105},{"id":"mlvu","name":"MLVU","topic":"Large video understanding","difficulty":-1.195,"discrimination":0.667,"n":105},{"id":"simplevqa","name":"SimpleVQA","topic":"General VQA","difficulty":0.374,"discrimination":0.674,"n":100},{"id":"lvbench","name":"LVBench","topic":"Video understanding","difficulty":0.169,"discrimination":0.821,"n":98},{"id":"refcoco","name":"RefCOCO","topic":"Referring expressions","difficulty":-5.971,"discrimination":0.321,"n":97},{"id":"countbench","name":"CountBench","topic":"Visual counting","difficulty":-2.068,"discrimination":0.932,"n":96},{"id":"videommmu","name":"VideoMMMU","topic":"Multimodal video understanding","difficulty":-0.451,"discrimination":0.912,"n":93},{"id":"videomme-sub","name":"VideoMME (w/sub)","topic":"Video understanding","difficulty":-1.399,"discrimination":0.664,"n":92},{"id":"screenspot-v2","name":"ScreenSpot-v2","topic":"Screen UI locators","difficulty":-1.536,"discrimination":1.131,"n":82},{"id":"muirbench","name":"MUIRBENCH","topic":"Multimodal robustness","difficulty":-0.46,"discrimination":0.888,"n":80},{"id":"mmbench-v1.1-en-dev","name":"MMBench v1.1 (EN dev)","topic":"General VQA","difficulty":-2.396,"discrimination":0.651,"n":80},{"id":"osworld-g","name":"OSWorld-G","topic":"GUI agents","difficulty":0.246,"discrimination":0.938,"n":79},{"id":"vqav2","name":"VQAv2","topic":"Visual question answering","difficulty":-6.46,"discrimination":0.227,"n":79},{"id":"ocrbenchv2-en","name":"OCRBenchV2 (EN)","topic":"OCR (English)","difficulty":-0.009,"discrimination":0.448,"n":77},{"id":"seed-bench-img","name":"SEED-Bench-Img","topic":"Multimodal image understanding","difficulty":-3.428,"discrimination":0.372,"n":75},{"id":"v-star","name":"V*","topic":"Multimodal reasoning","difficulty":-1.235,"discrimination":0.852,"n":72},{"id":"refspatialbench","name":"RefSpatialBench","topic":"Spatial reasoning","difficulty":0.645,"discrimination":0.864,"n":71},{"id":"embspatialbench","name":"EmbSpatialBench","topic":"Spatial understanding","difficulty":-2.613,"discrimination":0.396,"n":71},{"id":"cv-bench","name":"CV-Bench","topic":"Computer vision QA","difficulty":-2.585,"discrimination":0.545,"n":70},{"id":"mathverse-mini","name":"MathVerse-mini","topic":"Math reasoning (multimodal)","difficulty":-0.109,"discrimination":1.125,"n":69},{"id":"mmvu","name":"MMVU","topic":"Video understanding","difficulty":-0.254,"discrimination":0.725,"n":69},{"id":"dynamath","name":"DynaMath","topic":"Math reasoning (video)","difficulty":-0.233,"discrimination":0.928,"n":68},{"id":"pixmocount","name":"PixmoCount","topic":"Visual counting","difficulty":-0.846,"discrimination":0.679,"n":67},{"id":"logicvista","name":"LogicVista","topic":"Visual logical reasoning","difficulty":-0.024,"discrimination":0.905,"n":65},{"id":"egoschema","name":"EgoSchema","topic":"Egocentric video QA","difficulty":-1.036,"discrimination":0.552,"n":62},{"id":"ocrbenchv2-cn","name":"OCRBenchV2 (CN)","topic":"OCR (Chinese)","difficulty":0.284,"discrimination":0.413,"n":61},{"id":"androidworld","name":"AndroidWorld","topic":"Mobile agents","difficulty":0.584,"discrimination":1.154,"n":57},{"id":"motionbench","name":"MotionBench","topic":"Video motion understanding","difficulty":-0.77,"discrimination":0.384,"n":55},{"id":"pope","name":"POPE","topic":"Hallucination detection","difficulty":-10.512,"discrimination":0.2,"n":54},{"id":"mmlongbench-doc","name":"MMLongBench-Doc","topic":"Long-context multimodal documents","difficulty":0.636,"discrimination":0.625,"n":52},{"id":"countbenchqa","name":"CountBenchQA","topic":"Visual counting QA","difficulty":-2.723,"discrimination":0.657,"n":50},{"id":"mmmu-pro-vision","name":"MMMU-Pro (vision)","topic":"Multimodal understanding (vision)","difficulty":0.411,"discrimination":1.063,"n":49},{"id":"robospatialhome","name":"RoboSpatialHome","topic":"Embodied spatial understanding","difficulty":-1.024,"discrimination":0.324,"n":49},{"id":"chartmuseum","name":"ChartMuseum","topic":"Chart understanding","difficulty":0.531,"discrimination":1.238,"n":48},{"id":"mme-realworld-en","name":"MME-RealWorld (en)","topic":"Real-world perception (EN)","difficulty":-0.805,"discrimination":0.457,"n":48},{"id":"chartqa-pro","name":"ChartQA-Pro","topic":"Chart understanding (VQA)","difficulty":0.468,"discrimination":0.877,"n":43},{"id":"cc-ocr","name":"CC-OCR","topic":"OCR (cross-lingual)","difficulty":-1.343,"discrimination":0.55,"n":43}]},"faix-voice":{"sd":0.615,"ext":{"gemini-3.1-pro":[1.409,0.224,81.97],"seed2.0-lite":[1.293,0.224,79.22],"gemini-3-flash":[1.285,0.224,76.85],"stepaudio-3-realtime":[1.284,0.135,80.02],"gemini-3.8-flash":[1.274,0.36,77.2],"grok-voice-3.0":[1.24,0.14,88.46],"qwen3.8-omni-flash":[1.217,0.36,75.97],"eleven-realtime-v1-max":[1.074,0.142,78.35],"qwen-audio-3.0-realtime-plus":[1.046,0.146,81.6],"gemini-3.8-live-extended-thinking-high":[1.007,0.148,79.56],"qwen3.5-omni-plus":[0.992,0.36,72.1],"grok-voice-1.0":[0.981,0.154,76.79],"grok-voice-2.0":[0.969,0.142,82.41],"gpt-live-1-medium":[0.884,0.135,82.47],"gpt-live-1-low":[0.834,0.141,82.69],"muse-spark-1.2":[0.729,0.36,63.73],"gpt-realtime-2.0-xhigh":[0.698,0.191,69.18],"eleven-realtime-v1-mini":[0.683,0.151,73.32],"gpt-realtime-2.1-high":[0.622,0.125,70.23],"qwen-audio-3.0-realtime-flash":[0.615,0.143,74.82],"gpt-realtime-2.0-high":[0.595,0.126,68.4],"gemini-3.8-live":[0.517,0.147,73.28],"longcat-flash-omni":[0.514,0.153,89.1],"gpt-realtime-2.0-medium":[0.505,0.143,73.29],"grok-voice-fast-1.0":[0.407,0.156,62.17],"gpt-realtime-1.5":[0.389,0.125,67.84],"tml-interaction-small":[0.382,0.205,71.63],"qwen3-omni-flash-thinking":[0.332,0.123,87.7],"gemini-2.5-pro":[0.326,0.123,90.38],"gpt-realtime-2.1":[0.31,0.14,73.45],"gpt-realtime-2.0":[0.302,0.128,66.52],"qwen3-omni-30b-a3b-thinking":[0.299,0.123,87.19],"gemini-3.1-flash-live-high":[0.294,0.132,59.51],"gpt-realtime":[0.292,0.138,65.43],"gpt-4o-audio":[0.25,0.123,85.23],"qwen3.5-omni-plus-realtime":[0.139,0.245,65],"gemini-2.5-flash":[0.134,0.126,81.79],"gpt-realtime-2.1-mini-high":[0.126,0.151,66.21],"qwen3-omni-30b-a3b-instruct":[0.082,0.113,76.81],"qwen3-omni-flash-instruct":[0.072,0.11,79.23],"gpt-4o-realtime-preview-2024-12-17":[0,0.143,63.92],"gpt-realtime-2.1-mini":[-0.064,0.146,63.78],"gpt-realtime-mini":[-0.076,0.149,63.91],"gemini-3.1-flash-live":[-0.088,0.134,56.06],"fun-audio-chat-8b":[-0.135,0.214,77.64],"qwen2.5-omni":[-0.235,0.123,73.34],"higgs-realtime":[-0.271,0.156,61.95],"raon-speechchat-9b":[-0.304,0.196,80.47],"deepslate-opal":[-0.468,0.162,60.07],"kimi-audio-7b-instruct":[-0.473,0.164,61.33],"personaplex-7b-v1":[-0.503,0.226,76.66],"mimo-audio-7b-instruct":[-0.53,0.234,44],"step-audio-2-mini":[-0.837,0.164,51.12],"gemini-2.5-flash-native-audio-preview-12-2025":[-0.936,0.209,32.3],"lfm2.5-audio-1.5b":[-0.948,0.279,54.33],"qwen2.5-omni-3b":[-0.975,0.266,62.9],"lfm2-audio-1.5b":[-1.034,0.231,42.28],"freeze-omni":[-1.09,0.192,53.66],"nemotronlabs-voicechat-11b":[-1.27,0.148,48.54],"flm-audio":[-1.455,0.186,52.82],"qwen2.5-omni-7b":[-1.673,0.139,31.7],"minicpm-o-2.6":[-1.812,0.15,34.94],"kanana-1.5-o-9.8b-instruct-2602":[-1.823,0.151,29.82],"moshi":[-1.967,0.167,41.52],"hyperclovax-seed-omni-8b":[-2.077,0.151,20.77],"mini-omni2":[-2.156,0.273,30.36],"gemini-2.5-flash-native-audio-preview-09-2025":[-3.202,0.242,30.34]},"benchmarks":[{"id":"big-bench-audio","name":"Big Bench Audio","topic":"Speech reasoning","difficulty":-0.627,"discrimination":2.149,"n":46},{"id":"aa-fdb-interruption","name":"AA Conversational Dynamics: Interruption","topic":"Full-duplex speech interaction","difficulty":-1.013,"discrimination":1.85,"n":37},{"id":"aa-fdb-backchannel","name":"AA Conversational Dynamics: Backchannel","topic":"Full-duplex speech interaction","difficulty":-1.781,"discrimination":1.086,"n":37},{"id":"aa-fdb-pause-handling","name":"AA Conversational Dynamics: Pause handling","topic":"Full-duplex speech interaction","difficulty":-2.943,"discrimination":0.946,"n":37},{"id":"aa-fdb-turn-taking","name":"AA Conversational Dynamics: Turn-taking","topic":"Full-duplex speech interaction","difficulty":-3.408,"discrimination":1.032,"n":37},{"id":"tau-voice-retail","name":"τ-Voice Retail","topic":"Voice agents","difficulty":0.944,"discrimination":1.379,"n":29},{"id":"tau-voice-telecom","name":"τ-Voice Telecom","topic":"Voice agents","difficulty":0.844,"discrimination":2.136,"n":29},{"id":"tau-voice-airline","name":"τ-Voice Airline","topic":"Voice agents","difficulty":0.318,"discrimination":0.7,"n":29},{"id":"voicebench-ifeval","name":"VoiceBench IFEval","topic":"VoiceBench","difficulty":-1.216,"discrimination":0.863,"n":24},{"id":"audio-multichallenge","name":"Audio MultiChallenge","topic":"Spoken multi-turn conversation","difficulty":0.85,"discrimination":1.205,"n":22},{"id":"aa-speech-agent-task-success","name":"AA Speech Agent Task Success","topic":"Voice agents","difficulty":-1.478,"discrimination":0.876,"n":22},{"id":"voicebench-mmsu-audio","name":"VoiceBench MMSU (Audio)","topic":"Audio reasoning","difficulty":-1.352,"discrimination":0.566,"n":21},{"id":"voicebench-sd-qa","name":"VoiceBench SD-QA","topic":"VoiceBench","difficulty":-0.717,"discrimination":1.508,"n":18},{"id":"voicebench-mmsu","name":"VoiceBench MMSU","topic":"VoiceBench","difficulty":-0.879,"discrimination":1.115,"n":18},{"id":"voicebench-advbench","name":"VoiceBench AdvBench","topic":"VoiceBench","difficulty":-3.347,"discrimination":1.275,"n":18},{"id":"voicebench-alpacaeval","name":"VoiceBench AlpacaEval","topic":"VoiceBench","difficulty":-0.854,"discrimination":2.878,"n":13},{"id":"voicebench-openbookqa","name":"VoiceBench OpenBookQA","topic":"VoiceBench","difficulty":-1.697,"discrimination":1.245,"n":13},{"id":"voicebench-bbh","name":"VoiceBench BBH","topic":"VoiceBench","difficulty":-2.101,"discrimination":0.763,"n":13},{"id":"fd-bench-v3-pass1","name":"FD-Bench V3 Pass@1","topic":"Full-duplex speech + tool use","difficulty":-0.085,"discrimination":0.809,"n":12},{"id":"voicebench-commoneval","name":"VoiceBench CommonEval","topic":"VoiceBench","difficulty":-0.612,"discrimination":2.541,"n":12},{"id":"fd-bench-v1.5","name":"FD-Bench V1.5","topic":"Full-duplex speech interaction","difficulty":0.287,"discrimination":0.889,"n":10},{"id":"fd-bench-v3","name":"FD-Bench V3","topic":"Full-duplex speech + tool use","difficulty":-0.649,"discrimination":1.252,"n":10},{"id":"wildspeech-bench","name":"WildSpeech-Bench","topic":"Spoken dialogue","difficulty":-0.21,"discrimination":0.805,"n":8},{"id":"voicebench-wildvoice","name":"VoiceBench WildVoice","topic":"VoiceBench","difficulty":-1.812,"discrimination":1.153,"n":8},{"id":"tau3-banking-voice","name":"τ³-Banking (Voice)","topic":"Voice agents","difficulty":1.815,"discrimination":1.331,"n":5}]}}}