{"all":{"name":"All benchmarks","n":1493,"nb":713,"acc":0.8465,"raw_acc":0.6744,"rows":[{"m":"kimi-k3.1-pro","r":1,"s":91.16,"lo":1,"hi":8,"n":12,"rr":593,"mr":2},{"m":"gpt-6-astra","r":2,"s":91.09,"lo":1,"hi":5,"n":84,"rr":140,"mr":1},{"m":"claude-opus-5.5","r":3,"s":90.83,"lo":2,"hi":7,"n":55,"rr":272,"mr":3},{"m":"gemini-4-argon","r":4,"s":90.53,"lo":1,"hi":13,"n":26,"rr":304,"mr":5},{"m":"claude-sonnet-5.5","r":5,"s":90.51,"lo":1,"hi":12,"n":21,"rr":217,"mr":4},{"m":"muse-wonder-full","r":6,"s":90.32,"lo":2,"hi":14,"n":10,"rr":704,"mr":7},{"m":"claude-fable-5.1","r":7,"s":89.99,"lo":5,"hi":11,"n":49,"rr":446,"mr":6},{"m":"claude-opus-5.5-max","r":8,"s":89.7,"lo":2,"hi":22,"n":9,"rr":130,"mr":10},{"m":"claude-opus-5","r":9,"s":89.62,"lo":7,"hi":13,"n":117,"rr":339,"mr":8},{"m":"muse-wonder","r":10,"s":89.55,"lo":6,"hi":21,"n":11,"rr":881,"mr":12},{"m":"gpt-6.1-sol","r":11,"s":89.44,"lo":3,"hi":19,"n":20,"rr":204,"mr":13},{"m":"claude-fable-5","r":12,"s":89.38,"lo":7,"hi":15,"n":110,"rr":327,"mr":9},{"m":"claude-mythos-5","r":13,"s":89.13,"lo":5,"hi":22,"n":31,"rr":74,"mr":11},{"m":"gpt-5.6-sol","r":14,"s":88.79,"lo":12,"hi":18,"n":165,"rr":286,"mr":14},{"m":"deepseek-v4.1-flash-1017","r":15,"s":88.39,"lo":12,"hi":40,"n":20,"rr":1030,"mr":15},{"m":"minimax-m3.1-flash","r":16,"s":88.29,"lo":14,"hi":35,"n":9,"rr":671,"mr":19},{"m":"mimo-v2.6-pro-rl","r":17,"s":88.27,"lo":10,"hi":29,"n":13,"rr":867,"mr":16},{"m":"muse-spark-1.3","r":18,"s":88.19,"lo":15,"hi":31,"n":15,"rr":697,"mr":17},{"m":"veriloop-e2","r":19,"s":88.17,"lo":12,"hi":33,"n":8,"rr":179,"mr":20},{"m":"grok-4.7","r":20,"s":88.14,"lo":11,"hi":33,"n":12,"rr":795,"mr":24},{"m":"claude-mythos-preview","r":21,"s":88.01,"lo":11,"hi":36,"n":27,"rr":192,"mr":23},{"m":"ling-3.1-flash","r":22,"s":88,"lo":15,"hi":32,"n":20,"rr":413,"mr":22},{"m":"gemini-3.8-flash","r":23,"s":87.98,"lo":14,"hi":32,"n":34,"rr":274,"mr":18},{"m":"qwen3.8-max","r":24,"s":87.82,"lo":18,"hi":32,"n":107,"rr":316,"mr":21},{"m":"grok-4.6","r":25,"s":87.73,"lo":17,"hi":33,"n":15,"rr":874,"mr":26},{"m":"deepseek-v4.1-flash","r":26,"s":87.65,"lo":21,"hi":34,"n":40,"rr":823,"mr":25},{"m":"glm-5.3","r":27,"s":87.5,"lo":21,"hi":36,"n":66,"rr":851,"mr":27},{"m":"atria-dawn-preview","r":28,"s":87.44,"lo":19,"hi":40,"n":18,"rr":499,"mr":29},{"m":"atria-dawn","r":29,"s":87.44,"lo":17,"hi":40,"n":21,"rr":560,"mr":28},{"m":"gpt-6-sol","r":30,"s":87.42,"lo":16,"hi":37,"n":16,"rr":778,"mr":30},{"m":"kimi-k3","r":31,"s":87.04,"lo":26,"hi":38,"n":108,"rr":465,"mr":31},{"m":"gemini-3.7-flash","r":32,"s":86.88,"lo":22,"hi":47,"n":39,"rr":682,"mr":32},{"m":"mimo-v2.6-flash-rl","r":33,"s":86.84,"lo":21,"hi":57,"n":14,"rr":1068,"mr":36},{"m":"hy4-preview","r":34,"s":86.84,"lo":29,"hi":40,"n":38,"rr":861,"mr":33},{"m":"naive-n0.5-flash","r":35,"s":86.77,"lo":21,"hi":55,"n":10,"rr":762,"mr":37},{"m":"gpt-5.6-terra","r":36,"s":86.74,"lo":27,"hi":44,"n":59,"rr":651,"mr":34},{"m":"gpt-5.5","r":37,"s":86.51,"lo":29,"hi":45,"n":178,"rr":402,"mr":35},{"m":"claude-haiku-5.5","r":38,"s":86.47,"lo":19,"hi":62,"n":20,"rr":782,"mr":40},{"m":"claude-opus-4.8","r":39,"s":86.28,"lo":35,"hi":44,"n":174,"rr":548,"mr":38},{"m":"muse-spark-open","r":40,"s":86.08,"lo":30,"hi":51,"n":17,"rr":448,"mr":41},{"m":"grok-4.5","r":41,"s":86.08,"lo":33,"hi":49,"n":20,"rr":995,"mr":39},{"m":"nex-n2.5-pro","r":42,"s":86.02,"lo":36,"hi":51,"n":14,"rr":395,"mr":42},{"m":"ornith-1.5-397b","r":43,"s":85.74,"lo":38,"hi":53,"n":16,"rr":318,"mr":43},{"m":"gpt-5.4-pro","r":44,"s":85.67,"lo":32,"hi":62,"n":12,"rr":303,"mr":46},{"m":"deepseek-v4-pro-0813","r":45,"s":85.59,"lo":39,"hi":54,"n":62,"rr":1013,"mr":44},{"m":"muse-spark-1.2","r":46,"s":85.44,"lo":37,"hi":59,"n":21,"rr":825,"mr":49},{"m":"qwen3.8-omni-flash","r":47,"s":85.31,"lo":37,"hi":58,"n":18,"rr":91,"mr":50},{"m":"fugu-ultra","r":48,"s":85.31,"lo":32,"hi":66,"n":10,"rr":169,"mr":45},{"m":"glm-5.3-flash","r":49,"s":85.31,"lo":39,"hi":62,"n":70,"rr":643,"mr":47},{"m":"muse-spark-1.1","r":50,"s":85.27,"lo":37,"hi":61,"n":19,"rr":381,"mr":51},{"m":"qwen3.8-flash-next","r":51,"s":85.23,"lo":41,"hi":57,"n":53,"rr":310,"mr":48},{"m":"deepseek-v4-flash-vision-exp","r":52,"s":84.93,"lo":45,"hi":64,"n":21,"rr":806,"mr":52},{"m":"claude-sonnet-5","r":53,"s":84.6,"lo":50,"hi":62,"n":53,"rr":999,"mr":53},{"m":"gpt-5.6-luna","r":54,"s":84.57,"lo":43,"hi":64,"n":57,"rr":583,"mr":54},{"m":"gemini-3.6-flash","r":55,"s":84.47,"lo":45,"hi":72,"n":56,"rr":466,"mr":55},{"m":"physbrain1.5-8b","r":56,"s":84.32,"lo":9,"hi":141,"n":28,"rr":174,"mr":77},{"m":"intern-s2-397b","r":57,"s":84.32,"lo":32,"hi":85,"n":18,"rr":356,"mr":59},{"m":"deepseek-v4-flash-0731","r":58,"s":84.19,"lo":52,"hi":70,"n":59,"rr":772,"mr":56},{"m":"ornith-1.5-122b","r":59,"s":83.95,"lo":50,"hi":77,"n":14,"rr":281,"mr":61},{"m":"fugu","r":60,"s":83.95,"lo":49,"hi":82,"n":10,"rr":231,"mr":57},{"m":"gpt-5.4","r":61,"s":83.9,"lo":54,"hi":68,"n":114,"rr":364,"mr":58},{"m":"seed2.1-pro","r":62,"s":83.76,"lo":54,"hi":73,"n":87,"rr":397,"mr":60},{"m":"mirothinker-h1","r":63,"s":83.66,"lo":46,"hi":112,"n":8,"rr":79,"mr":71},{"m":"sage-a1.5","r":64,"s":83.55,"lo":48,"hi":90,"n":12,"rr":634,"mr":70},{"m":"glm-5.2","r":65,"s":83.5,"lo":57,"hi":75,"n":104,"rr":848,"mr":62},{"m":"gpt-6-luna","r":66,"s":83.42,"lo":47,"hi":115,"n":16,"rr":1284,"mr":73},{"m":"dots3-note-preview","r":67,"s":83.35,"lo":56,"hi":80,"n":32,"rr":221,"mr":63},{"m":"intern-s2-preview-397b","r":68,"s":83.21,"lo":45,"hi":90,"n":19,"rr":449,"mr":69},{"m":"claude-opus-4.7","r":69,"s":83.2,"lo":59,"hi":82,"n":115,"rr":598,"mr":65},{"m":"seed2.1-turbo","r":70,"s":83.17,"lo":60,"hi":78,"n":78,"rr":416,"mr":66},{"m":"gpt-5.2-high","r":71,"s":83.15,"lo":58,"hi":82,"n":51,"rr":214,"mr":64},{"m":"gemini-3.1-pro","r":72,"s":83.11,"lo":61,"hi":83,"n":225,"rr":628,"mr":67},{"m":"beam","r":73,"s":82.99,"lo":62,"hi":83,"n":26,"rr":576,"mr":68},{"m":"gpt-5.2-pro","r":74,"s":82.75,"lo":67,"hi":88,"n":8,"rr":585,"mr":75},{"m":"gpt-5.4-thinking","r":75,"s":82.71,"lo":56,"hi":91,"n":9,"rr":488,"mr":80},{"m":"nex-n2-pro","r":76,"s":82.54,"lo":68,"hi":85,"n":17,"rr":632,"mr":74},{"m":"claude-opus-4.6","r":77,"s":82.52,"lo":68,"hi":88,"n":152,"rr":451,"mr":72},{"m":"gemini-3.5-flash","r":78,"s":82.41,"lo":64,"hi":96,"n":56,"rr":556,"mr":76},{"m":"gpt-5.2-extra-high","r":79,"s":82.36,"lo":66,"hi":106,"n":17,"rr":287,"mr":78},{"m":"gpt-5.3-codex","r":80,"s":82.35,"lo":70,"hi":93,"n":11,"rr":321,"mr":82},{"m":"gpt-6-luna-max","r":81,"s":82.32,"lo":65,"hi":115,"n":9,"rr":967,"mr":85},{"m":"qwen3.7-max","r":82,"s":82.09,"lo":71,"hi":95,"n":73,"rr":637,"mr":79},{"m":"deepseek-v4-pro-thinking-max","r":83,"s":82.05,"lo":74,"hi":91,"n":92,"rr":510,"mr":81},{"m":"kimi-k2.7-code","r":84,"s":81.89,"lo":66,"hi":98,"n":30,"rr":998,"mr":84},{"m":"ling-3.0-flash-vl","r":85,"s":81.85,"lo":66,"hi":127,"n":8,"rr":69,"mr":96},{"m":"deepseek-v4-pro","r":86,"s":81.75,"lo":77,"hi":104,"n":94,"rr":791,"mr":83},{"m":"nex-n2.5-mini","r":87,"s":81.75,"lo":74,"hi":104,"n":14,"rr":1008,"mr":88},{"m":"k2-horizon-375b-a23b","r":88,"s":81.48,"lo":77,"hi":109,"n":11,"rr":1104,"mr":91},{"m":"ornith-1.0-397b","r":89,"s":81.38,"lo":74,"hi":121,"n":19,"rr":970,"mr":87},{"m":"kimi-k2.6-thinking","r":90,"s":81.33,"lo":85,"hi":101,"n":101,"rr":301,"mr":86},{"m":"hy3","r":91,"s":81.29,"lo":80,"hi":103,"n":61,"rr":1090,"mr":90},{"m":"deepseek-v4-pro-thinking","r":92,"s":81.28,"lo":80,"hi":104,"n":20,"rr":290,"mr":89},{"m":"mercury-3","r":93,"s":81.19,"lo":63,"hi":149,"n":10,"rr":592,"mr":103},{"m":"qwen3.7-plus","r":94,"s":81.13,"lo":77,"hi":107,"n":84,"rr":462,"mr":92},{"m":"qwen3.8-27b","r":95,"s":81.04,"lo":80,"hi":120,"n":91,"rr":294,"mr":93},{"m":"kimi-k2.6","r":96,"s":80.92,"lo":78,"hi":117,"n":35,"rr":569,"mr":94},{"m":"ax-k2","r":97,"s":80.91,"lo":69,"hi":179,"n":15,"rr":393,"mr":95},{"m":"occamy-1.0","r":98,"s":80.69,"lo":75,"hi":121,"n":16,"rr":1027,"mr":104},{"m":"gpt-5.2-thinking-xhigh","r":99,"s":80.65,"lo":84,"hi":131,"n":47,"rr":270,"mr":98},{"m":"seed2.0-pro","r":100,"s":80.63,"lo":92,"hi":118,"n":86,"rr":251,"mr":97},{"m":"longcat-2.0","r":101,"s":80.61,"lo":89,"hi":132,"n":9,"rr":39,"mr":102},{"m":"claude-sonnet-4.6","r":102,"s":80.55,"lo":89,"hi":117,"n":84,"rr":641,"mr":100},{"m":"qwen3.6-max-preview","r":103,"s":80.53,"lo":89,"hi":125,"n":8,"rr":960,"mr":114},{"m":"gpt-5.2-thinking","r":104,"s":80.48,"lo":89,"hi":125,"n":33,"rr":324,"mr":99},{"m":"motif-3","r":105,"s":80.41,"lo":89,"hi":128,"n":12,"rr":606,"mr":101},{"m":"seed2.0-lite-0428","r":106,"s":80.39,"lo":85,"hi":125,"n":51,"rr":388,"mr":107},{"m":"grok-4.2","r":107,"s":80.35,"lo":80,"hi":186,"n":17,"rr":611,"mr":111},{"m":"deepseek-v4-flash","r":108,"s":80.13,"lo":92,"hi":126,"n":73,"rr":816,"mr":105},{"m":"yuan3.0-ultra","r":109,"s":80.1,"lo":1,"hi":257,"n":15,"rr":355,"mr":137},{"m":"deepseek-v4-flash-thinking-max","r":110,"s":80.02,"lo":96,"hi":130,"n":71,"rr":774,"mr":106},{"m":"muse-spark","r":111,"s":80.01,"lo":89,"hi":132,"n":29,"rr":909,"mr":112},{"m":"minimax-m3","r":112,"s":79.94,"lo":94,"hi":125,"n":50,"rr":1001,"mr":109},{"m":"gemini-3-pro","r":113,"s":79.86,"lo":103,"hi":127,"n":253,"rr":308,"mr":108},{"m":"stepaudio-3-realtime","r":114,"s":79.84,"lo":82,"hi":292,"n":11,"rr":30,"mr":138},{"m":"apodex-1.0","r":115,"s":79.82,"lo":95,"hi":165,"n":9,"rr":1149,"mr":118},{"m":"mirothinker-v1.5-235b","r":116,"s":79.71,"lo":93,"hi":137,"n":10,"rr":361,"mr":125},{"m":"gpt-5.2","r":117,"s":79.67,"lo":101,"hi":131,"n":162,"rr":544,"mr":110},{"m":"longcat-flash-thinking-2601","r":118,"s":79.59,"lo":83,"hi":155,"n":17,"rr":170,"mr":113},{"m":"glm-5v-turbo","r":119,"s":79.46,"lo":96,"hi":168,"n":13,"rr":151,"mr":129},{"m":"kat-coder-pro-v2","r":120,"s":79.34,"lo":111,"hi":150,"n":9,"rr":209,"mr":124},{"m":"grm-3.2-sky","r":121,"s":79.29,"lo":100,"hi":132,"n":11,"rr":149,"mr":115},{"m":"glm-5.1","r":122,"s":79.23,"lo":106,"hi":134,"n":107,"rr":734,"mr":116},{"m":"qwen3.6-plus","r":123,"s":79.13,"lo":108,"hi":139,"n":96,"rr":351,"mr":117},{"m":"grok-voice-3.0","r":124,"s":79.01,"lo":74,"hi":413,"n":9,"rr":1,"mr":155},{"m":"ornith-1.5-35b-a3b","r":125,"s":78.99,"lo":99,"hi":142,"n":34,"rr":1187,"mr":123},{"m":"gemini-3-flash","r":126,"s":78.97,"lo":109,"hi":145,"n":134,"rr":520,"mr":120},{"m":"inkling","r":127,"s":78.96,"lo":110,"hi":139,"n":43,"rr":965,"mr":122},{"m":"claude-opus-4.5-thinking","r":128,"s":78.91,"lo":104,"hi":154,"n":46,"rr":331,"mr":119},{"m":"mirothinker-1.7","r":129,"s":78.71,"lo":102,"hi":177,"n":8,"rr":340,"mr":136},{"m":"gemini-3-pro-preview","r":130,"s":78.66,"lo":113,"hi":150,"n":41,"rr":212,"mr":121},{"m":"ling-3.0-flash","r":131,"s":78.66,"lo":107,"hi":144,"n":22,"rr":228,"mr":126},{"m":"inkling-small","r":132,"s":78.58,"lo":112,"hi":153,"n":54,"rr":807,"mr":127},{"m":"bigbang-v1","r":133,"s":78.57,"lo":107,"hi":156,"n":23,"rr":1219,"mr":130},{"m":"qwen3.5-397b-a17b","r":134,"s":78.42,"lo":119,"hi":147,"n":157,"rr":508,"mr":128},{"m":"intern-s2-preview","r":135,"s":78.25,"lo":97,"hi":166,"n":23,"rr":883,"mr":135},{"m":"deepseek-v4-flash-thinking","r":136,"s":78.09,"lo":121,"hi":158,"n":20,"rr":614,"mr":132},{"m":"claude-opus-4.5","r":137,"s":78.08,"lo":128,"hi":152,"n":166,"rr":501,"mr":131},{"m":"openpangu-2.0-pro-thinking","r":138,"s":78.04,"lo":118,"hi":151,"n":23,"rr":432,"mr":134},{"m":"gpt-6-luna-high","r":139,"s":77.92,"lo":106,"hi":174,"n":9,"rr":1190,"mr":150},{"m":"glm-5","r":140,"s":77.82,"lo":126,"hi":163,"n":68,"rr":494,"mr":133},{"m":"mimo-v2-pro","r":141,"s":77.74,"lo":112,"hi":218,"n":14,"rr":818,"mr":148},{"m":"ring-2.6-1t-xhigh","r":142,"s":77.67,"lo":107,"hi":183,"n":26,"rr":398,"mr":139},{"m":"longcat-flash-thinking-zigzag","r":143,"s":77.57,"lo":103,"hi":180,"n":12,"rr":176,"mr":140},{"m":"nemotron-3.5-bolt-74b-a9b","r":144,"s":77.48,"lo":126,"hi":177,"n":11,"rr":1026,"mr":145},{"m":"step-3.7-flash","r":145,"s":77.21,"lo":130,"hi":180,"n":35,"rr":787,"mr":143},{"m":"muse-glimmer-30b","r":146,"s":77.21,"lo":131,"hi":172,"n":40,"rr":819,"mr":141},{"m":"solar-pro-4","r":147,"s":77.09,"lo":134,"hi":173,"n":11,"rr":492,"mr":142},{"m":"nemotron-3.5-super-vl-120b-a12b","r":148,"s":77.03,"lo":116,"hi":181,"n":48,"rr":912,"mr":144},{"m":"kimi-k2.5-thinking","r":149,"s":77,"lo":139,"hi":170,"n":95,"rr":434,"mr":146},{"m":"seed2.0-lite","r":150,"s":76.96,"lo":134,"hi":182,"n":84,"rr":411,"mr":151},{"m":"mirothinker-1.7-mini","r":151,"s":76.95,"lo":124,"hi":201,"n":9,"rr":521,"mr":170},{"m":"qwen3.6-27b","r":152,"s":76.77,"lo":138,"hi":178,"n":90,"rr":366,"mr":153},{"m":"mimo-v2.5-pro","r":153,"s":76.73,"lo":129,"hi":187,"n":24,"rr":1377,"mr":157},{"m":"step-3.5-flash-20260204","r":154,"s":76.72,"lo":140,"hi":181,"n":46,"rr":837,"mr":149},{"m":"mai-thinking-1","r":155,"s":76.72,"lo":141,"hi":194,"n":8,"rr":55,"mr":147},{"m":"intern-s2-mobius","r":156,"s":76.72,"lo":113,"hi":211,"n":11,"rr":608,"mr":163},{"m":"kimi-k2.5","r":157,"s":76.68,"lo":144,"hi":179,"n":137,"rr":495,"mr":152},{"m":"gpt-6-luna-medium","r":158,"s":76.6,"lo":97,"hi":197,"n":20,"rr":1057,"mr":167},{"m":"hy3-preview","r":159,"s":76.57,"lo":143,"hi":192,"n":32,"rr":1225,"mr":159},{"m":"ornith-1.0-35b","r":160,"s":76.53,"lo":136,"hi":220,"n":21,"rr":1222,"mr":158},{"m":"gpt-5-codex","r":161,"s":76.49,"lo":145,"hi":203,"n":8,"rr":932,"mr":168},{"m":"glm-4.7-thinking","r":162,"s":76.46,"lo":133,"hi":197,"n":14,"rr":426,"mr":156},{"m":"solar-open-2-250b","r":163,"s":76.45,"lo":123,"hi":196,"n":20,"rr":564,"mr":154},{"m":"gpt-5.4-mini","r":164,"s":76.39,"lo":147,"hi":190,"n":66,"rr":753,"mr":161},{"m":"qwen3-max-thinking","r":165,"s":76.33,"lo":141,"hi":192,"n":43,"rr":336,"mr":160},{"m":"gpt-5.1-high","r":166,"s":76.22,"lo":149,"hi":188,"n":16,"rr":892,"mr":162},{"m":"gpt-5-thinking","r":167,"s":76.1,"lo":147,"hi":202,"n":15,"rr":740,"mr":172},{"m":"mimo-v2.5","r":168,"s":76.07,"lo":150,"hi":190,"n":41,"rr":698,"mr":164},{"m":"seed1.8","r":169,"s":76.04,"lo":149,"hi":194,"n":80,"rr":298,"mr":166},{"m":"gemini-3.5-flash-lite","r":170,"s":75.89,"lo":130,"hi":249,"n":36,"rr":584,"mr":171},{"m":"trinity-large-thinking","r":171,"s":75.86,"lo":117,"hi":281,"n":9,"rr":87,"mr":165},{"m":"hy-embodied-vlm-1.0","r":172,"s":75.85,"lo":127,"hi":228,"n":30,"rr":378,"mr":203},{"m":"nemotron-3-ultra","r":173,"s":75.81,"lo":152,"hi":199,"n":58,"rr":779,"mr":169},{"m":"minimax-m2.5","r":174,"s":75.62,"lo":132,"hi":231,"n":18,"rr":980,"mr":178},{"m":"mirothinker-v1.0-72b","r":175,"s":75.52,"lo":105,"hi":236,"n":10,"rr":720,"mr":191},{"m":"gpt-5.1-thinking","r":176,"s":75.52,"lo":147,"hi":197,"n":8,"rr":1029,"mr":180},{"m":"raon-1-mini-preview","r":177,"s":75.51,"lo":145,"hi":216,"n":16,"rr":635,"mr":174},{"m":"qwen3.5-122b-a10b","r":178,"s":75.49,"lo":162,"hi":205,"n":110,"rr":483,"mr":173},{"m":"oxcoder-9b","r":179,"s":75.47,"lo":168,"hi":206,"n":10,"rr":1051,"mr":175},{"m":"mirothinker-v1.5-30b","r":180,"s":75.4,"lo":158,"hi":212,"n":10,"rr":728,"mr":190},{"m":"xing4.0-29b-a4b","r":181,"s":75.37,"lo":150,"hi":226,"n":8,"rr":259,"mr":177},{"m":"grok-voice-1.0","r":182,"s":75.3,"lo":102,"hi":1142,"n":9,"rr":71,"mr":222},{"m":"deepseek-v3.2-thinking","r":183,"s":75.04,"lo":173,"hi":210,"n":75,"rr":630,"mr":176},{"m":"nemotron-3.5-super-vl-120b-a12b-nvfp4","r":184,"s":75.04,"lo":155,"hi":214,"n":27,"rr":804,"mr":181},{"m":"qwen3.5-27b","r":185,"s":74.89,"lo":173,"hi":207,"n":125,"rr":319,"mr":179},{"m":"apodex-1.0-mini","r":186,"s":74.88,"lo":132,"hi":250,"n":15,"rr":1310,"mr":196},{"m":"gpt-5","r":187,"s":74.84,"lo":173,"hi":213,"n":150,"rr":312,"mr":182},{"m":"comet-60b-a12b-fp8","r":188,"s":74.83,"lo":159,"hi":210,"n":27,"rr":822,"mr":183},{"m":"mercury-2.5","r":189,"s":74.77,"lo":136,"hi":309,"n":9,"rr":1124,"mr":208},{"m":"ternary-bonsai-2-27b","r":190,"s":74.71,"lo":159,"hi":290,"n":13,"rr":4,"mr":185},{"m":"kimi-k2-thinking","r":191,"s":74.65,"lo":178,"hi":228,"n":55,"rr":681,"mr":184},{"m":"nex-n2-mini","r":192,"s":74.52,"lo":156,"hi":242,"n":49,"rr":1272,"mr":188},{"m":"gpt-5-high","r":193,"s":74.46,"lo":180,"hi":221,"n":122,"rr":464,"mr":186},{"m":"gpt-5-medium","r":194,"s":74.39,"lo":151,"hi":251,"n":9,"rr":588,"mr":202},{"m":"comet-60b-a12b","r":195,"s":74.35,"lo":167,"hi":222,"n":27,"rr":846,"mr":189},{"m":"claude-haiku-5.5-medium","r":196,"s":74.18,"lo":129,"hi":234,"n":17,"rr":1024,"mr":205},{"m":"qwen-audio-3.0-realtime-plus","r":197,"s":74.08,"lo":114,"hi":417,"n":9,"rr":20,"mr":240},{"m":"step3-vl-10b-pacore","r":198,"s":74.04,"lo":186,"hi":249,"n":9,"rr":6,"mr":194},{"m":"qwen3.6-35b-a3b","r":199,"s":73.97,"lo":188,"hi":220,"n":149,"rr":829,"mr":193},{"m":"kolibri-1","r":200,"s":73.96,"lo":147,"hi":270,"n":17,"rr":418,"mr":187},{"m":"skywork-r1v4","r":201,"s":73.95,"lo":160,"hi":354,"n":8,"rr":333,"mr":234},{"m":"openpangu-2.0-flash-thinking","r":202,"s":73.94,"lo":180,"hi":231,"n":24,"rr":658,"mr":192},{"m":"spark-x2.6-4b","r":203,"s":73.93,"lo":179,"hi":227,"n":21,"rr":563,"mr":200},{"m":"comet-60b-a12b-nvfp4","r":204,"s":73.86,"lo":173,"hi":234,"n":27,"rr":872,"mr":195},{"m":"grok-voice-2.0","r":205,"s":73.8,"lo":148,"hi":462,"n":9,"rr":17,"mr":241},{"m":"agents-a1","r":206,"s":73.72,"lo":153,"hi":251,"n":42,"rr":1233,"mr":206},{"m":"agents-a1-4b","r":207,"s":73.7,"lo":113,"hi":372,"n":18,"rr":884,"mr":214},{"m":"qwen3.8-27b-ud-q4-k-xl","r":208,"s":73.69,"lo":188,"hi":286,"n":13,"rr":5,"mr":198},{"m":"glm-4.7","r":209,"s":73.47,"lo":178,"hi":290,"n":40,"rr":595,"mr":197},{"m":"iquest-coder-v1-40b-thinking","r":210,"s":73.46,"lo":16,"hi":433,"n":8,"rr":3,"mr":225},{"m":"minimax-m2.7","r":211,"s":73.43,"lo":182,"hi":247,"n":86,"rr":973,"mr":201},{"m":"ernie-5.0","r":212,"s":73.41,"lo":183,"hi":253,"n":39,"rr":62,"mr":199},{"m":"gemini-3.8-live-extended-thinking-high","r":213,"s":73.4,"lo":127,"hi":626,"n":9,"rr":7,"mr":249},{"m":"mimo-v2-flash","r":214,"s":73.22,"lo":196,"hi":247,"n":30,"rr":709,"mr":204},{"m":"mai-code-1-flash","r":215,"s":73.19,"lo":164,"hi":269,"n":11,"rr":843,"mr":212},{"m":"qwen3.5-35b-a3b","r":216,"s":73.17,"lo":198,"hi":232,"n":141,"rr":784,"mr":210},{"m":"nemotron-cascade-2-30b-a3b","r":217,"s":73.14,"lo":192,"hi":270,"n":23,"rr":467,"mr":209},{"m":"gpt-5.1","r":218,"s":73.09,"lo":193,"hi":295,"n":73,"rr":926,"mr":207},{"m":"ring-2.6-1t-high","r":219,"s":72.97,"lo":145,"hi":281,"n":12,"rr":93,"mr":217},{"m":"intern-s1-pro","r":220,"s":72.92,"lo":183,"hi":249,"n":30,"rr":860,"mr":213},{"m":"physbrain1.5-2b","r":221,"s":72.92,"lo":79,"hi":362,"n":28,"rr":409,"mr":257},{"m":"k-exaone-2.0","r":222,"s":72.91,"lo":193,"hi":253,"n":21,"rr":380,"mr":211},{"m":"claude-sonnet-4.5","r":223,"s":72.81,"lo":201,"hi":242,"n":203,"rr":712,"mr":216},{"m":"grok-4","r":224,"s":72.8,"lo":201,"hi":252,"n":64,"rr":956,"mr":215},{"m":"qwen3.5-omni-plus","r":225,"s":72.77,"lo":191,"hi":247,"n":46,"rr":161,"mr":223},{"m":"snowdon-1.1-small","r":226,"s":72.75,"lo":112,"hi":276,"n":13,"rr":384,"mr":218},{"m":"nova-2-pro","r":227,"s":72.64,"lo":182,"hi":257,"n":15,"rr":141,"mr":219},{"m":"tongyi-deepresearch","r":228,"s":72.62,"lo":173,"hi":264,"n":11,"rr":750,"mr":238},{"m":"o3","r":229,"s":72.62,"lo":203,"hi":250,"n":72,"rr":730,"mr":220},{"m":"vibethinker-3b","r":230,"s":72.5,"lo":204,"hi":259,"n":10,"rr":29,"mr":221},{"m":"eleven-realtime-v1-max","r":231,"s":72.45,"lo":116,"hi":458,"n":9,"rr":47,"mr":268},{"m":"neohorse-1-9b","r":232,"s":72.3,"lo":176,"hi":321,"n":9,"rr":406,"mr":232},{"m":"deepseek-v3.2","r":233,"s":72.18,"lo":210,"hi":256,"n":86,"rr":793,"mr":224},{"m":"gpt-5-mini-high","r":234,"s":72.12,"lo":206,"hi":251,"n":87,"rr":706,"mr":227},{"m":"mimo-v2-omni","r":235,"s":72.07,"lo":163,"hi":318,"n":10,"rr":54,"mr":258},{"m":"ring-1t-preview","r":236,"s":72.01,"lo":218,"hi":262,"n":8,"rr":72,"mr":230},{"m":"nemotron-3-super-120b-a12b","r":237,"s":71.97,"lo":213,"hi":258,"n":56,"rr":834,"mr":226},{"m":"ornith-1.5-9b","r":238,"s":71.9,"lo":209,"hi":301,"n":23,"rr":1116,"mr":229},{"m":"nanbeige4.2-3b","r":239,"s":71.88,"lo":198,"hi":270,"n":25,"rr":962,"mr":231},{"m":"k2-horizon-7b","r":240,"s":71.85,"lo":210,"hi":264,"n":15,"rr":726,"mr":228},{"m":"hy-embodied-0.5-mot-2b","r":241,"s":71.7,"lo":131,"hi":411,"n":10,"rr":314,"mr":273},{"m":"ornith-1.0-9b","r":242,"s":71.63,"lo":220,"hi":265,"n":17,"rr":1363,"mr":233},{"m":"keye-vl-2.0-30b-a3b","r":243,"s":71.51,"lo":103,"hi":323,"n":10,"rr":486,"mr":244},{"m":"nova-2-omni","r":244,"s":71.45,"lo":215,"hi":293,"n":13,"rr":112,"mr":236},{"m":"grok-4-fast","r":245,"s":71.38,"lo":208,"hi":294,"n":23,"rr":578,"mr":235},{"m":"claude-4.5-sonnet-thinking","r":246,"s":71.24,"lo":217,"hi":282,"n":50,"rr":880,"mr":237},{"m":"gpt-live-1-low","r":247,"s":71.09,"lo":135,"hi":435,"n":10,"rr":15,"mr":298},{"m":"gpt-5-2025-08-07","r":248,"s":71.07,"lo":200,"hi":549,"n":10,"rr":621,"mr":248},{"m":"nemotron-labs-3-puzzle-75b-a9b","r":249,"s":71.06,"lo":215,"hi":301,"n":19,"rr":247,"mr":239},{"m":"gpt-5-low","r":250,"s":70.95,"lo":206,"hi":349,"n":8,"rr":891,"mr":256},{"m":"gemma-4-31b-it","r":251,"s":70.64,"lo":230,"hi":282,"n":113,"rr":529,"mr":243},{"m":"holo1.5-72b","r":252,"s":70.53,"lo":216,"hi":324,"n":10,"rr":9,"mr":287},{"m":"mistral-medium-3.5","r":253,"s":70.44,"lo":222,"hi":297,"n":25,"rr":951,"mr":245},{"m":"k-exaone","r":254,"s":70.43,"lo":240,"hi":286,"n":33,"rr":479,"mr":242},{"m":"longcat-flash-thinking","r":255,"s":70.35,"lo":233,"hi":300,"n":8,"rr":193,"mr":252},{"m":"gemini-3.1-flash-lite","r":256,"s":70.35,"lo":228,"hi":305,"n":40,"rr":1062,"mr":250},{"m":"o3-high","r":257,"s":70.29,"lo":235,"hi":292,"n":31,"rr":767,"mr":251},{"m":"exaone-4.5-33b-thinking","r":258,"s":70.23,"lo":240,"hi":309,"n":28,"rr":226,"mr":246},{"m":"ling-2.6-1t","r":259,"s":70.23,"lo":172,"hi":320,"n":18,"rr":770,"mr":253},{"m":"deepseek-v3.1-terminus-thinking","r":260,"s":70.19,"lo":247,"hi":294,"n":11,"rr":700,"mr":259},{"m":"gpt-live-1-medium","r":261,"s":70.15,"lo":120,"hi":527,"n":11,"rr":2,"mr":323},{"m":"gpt-oss-120b-high","r":262,"s":70.11,"lo":235,"hi":336,"n":36,"rr":502,"mr":247},{"m":"gpt-realtime-2.0-xhigh","r":263,"s":70.04,"lo":172,"hi":474,"n":9,"rr":131,"mr":305},{"m":"gemini-3-flash-preview","r":264,"s":70.01,"lo":163,"hi":399,"n":19,"rr":490,"mr":269},{"m":"glm-4.6","r":265,"s":69.91,"lo":245,"hi":311,"n":42,"rr":788,"mr":254},{"m":"ovis2.6-80b-a3b","r":266,"s":69.88,"lo":220,"hi":328,"n":27,"rr":57,"mr":285},{"m":"o3-2025-04-16","r":267,"s":69.77,"lo":184,"hi":443,"n":9,"rr":627,"mr":279},{"m":"qwen3-vl-235b-a22b-thinking","r":268,"s":69.72,"lo":245,"hi":296,"n":90,"rr":357,"mr":263},{"m":"ovis2.6-30b-a3b","r":269,"s":69.65,"lo":226,"hi":320,"n":35,"rr":35,"mr":290},{"m":"qwen3-235b-a22b-thinking-2507","r":270,"s":69.56,"lo":254,"hi":315,"n":83,"rr":549,"mr":261},{"m":"gemini-2.5-pro","r":271,"s":69.5,"lo":256,"hi":304,"n":251,"rr":600,"mr":264},{"m":"sarvam-105b","r":272,"s":69.49,"lo":253,"hi":314,"n":14,"rr":64,"mr":255},{"m":"minimax-m2.1","r":273,"s":69.48,"lo":218,"hi":332,"n":32,"rr":921,"mr":260},{"m":"o4-mini-high","r":274,"s":69.38,"lo":240,"hi":321,"n":20,"rr":942,"mr":277},{"m":"rynnbrain1.1-9b","r":275,"s":69.32,"lo":185,"hi":522,"n":28,"rr":607,"mr":331},{"m":"gpt-5-mini","r":276,"s":69.31,"lo":257,"hi":308,"n":159,"rr":586,"mr":266},{"m":"k2-horizon-3.7b","r":277,"s":69.3,"lo":252,"hi":324,"n":13,"rr":976,"mr":262},{"m":"minimax-m2","r":278,"s":69.24,"lo":235,"hi":343,"n":36,"rr":852,"mr":265},{"m":"gpt-6-luna-low","r":279,"s":69.17,"lo":99,"hi":341,"n":10,"rr":1293,"mr":300},{"m":"claude-opus-4.1","r":280,"s":69.11,"lo":242,"hi":322,"n":64,"rr":714,"mr":267},{"m":"gpt-5.4-nano","r":281,"s":69.09,"lo":239,"hi":331,"n":38,"rr":1235,"mr":271},{"m":"claude-opus-4-thinking","r":282,"s":69.03,"lo":256,"hi":318,"n":9,"rr":475,"mr":289},{"m":"nanbeige4.1-3b","r":283,"s":68.96,"lo":241,"hi":340,"n":13,"rr":724,"mr":276},{"m":"ling-2.5-1t","r":284,"s":68.92,"lo":197,"hi":330,"n":19,"rr":813,"mr":274},{"m":"pplx-decider-v1.2","r":285,"s":68.89,"lo":165,"hi":462,"n":27,"rr":96,"mr":302},{"m":"claude-sonnet-4-thinking","r":286,"s":68.73,"lo":241,"hi":440,"n":11,"rr":879,"mr":310},{"m":"zdtaichu5.0-9b","r":287,"s":68.69,"lo":270,"hi":323,"n":23,"rr":110,"mr":278},{"m":"cogito-671b-v2.1","r":288,"s":68.65,"lo":255,"hi":418,"n":8,"rr":458,"mr":272},{"m":"iquest-coder-v1-40b-instruct","r":289,"s":68.64,"lo":239,"hi":529,"n":23,"rr":354,"mr":296},{"m":"step3-vl-10b-sere","r":290,"s":68.62,"lo":274,"hi":315,"n":9,"rr":23,"mr":283},{"m":"deepseek-v3.1-terminus","r":291,"s":68.61,"lo":270,"hi":363,"n":27,"rr":1006,"mr":270},{"m":"kimi-k2-0905-preview","r":292,"s":68.46,"lo":243,"hi":448,"n":12,"rr":1355,"mr":309},{"m":"openpangu-2.0-pro","r":293,"s":68.45,"lo":234,"hi":332,"n":22,"rr":963,"mr":275},{"m":"telechat3-coder-36b-thinking","r":294,"s":68.44,"lo":254,"hi":385,"n":9,"rr":97,"mr":288},{"m":"nova-2-lite","r":295,"s":68.37,"lo":254,"hi":369,"n":17,"rr":514,"mr":280},{"m":"o4-mini","r":296,"s":68.34,"lo":262,"hi":335,"n":24,"rr":1199,"mr":291},{"m":"qwenlong-l1.5-30b-a3b","r":297,"s":68.17,"lo":236,"hi":377,"n":10,"rr":78,"mr":282},{"m":"qwen3-235b-2507","r":298,"s":68.16,"lo":252,"hi":445,"n":10,"rr":898,"mr":297},{"m":"qianfan-ocr","r":299,"s":68.12,"lo":132,"hi":591,"n":11,"rr":42,"mr":355},{"m":"gemma-4-26b-a4b-it","r":300,"s":68.11,"lo":267,"hi":339,"n":87,"rr":1066,"mr":284},{"m":"seed1.5-vl-thinking","r":301,"s":68.08,"lo":272,"hi":344,"n":57,"rr":517,"mr":330},{"m":"embodied-r1.5-8b","r":302,"s":68.05,"lo":124,"hi":526,"n":28,"rr":518,"mr":359},{"m":"dots-vlm1","r":303,"s":67.97,"lo":282,"hi":336,"n":29,"rr":137,"mr":304},{"m":"intellect-3","r":304,"s":67.84,"lo":293,"hi":342,"n":11,"rr":90,"mr":281},{"m":"minicpm-v-4.7-35b-a3b","r":305,"s":67.81,"lo":216,"hi":407,"n":28,"rr":124,"mr":321},{"m":"ring-flash-2.0","r":306,"s":67.77,"lo":289,"hi":347,"n":8,"rr":291,"mr":301},{"m":"qwen-3-235b-a22b-thinking","r":307,"s":67.68,"lo":271,"hi":404,"n":22,"rr":66,"mr":299},{"m":"golongrl-30b-a3b","r":308,"s":67.64,"lo":295,"hi":409,"n":8,"rr":101,"mr":294},{"m":"deepseek-v3.1-thinking","r":309,"s":67.63,"lo":284,"hi":341,"n":25,"rr":1023,"mr":295},{"m":"qwen3-vl-235b-a22b","r":310,"s":67.61,"lo":275,"hi":348,"n":60,"rr":573,"mr":313},{"m":"openpangu-r-72b-2512-slow-thinking","r":311,"s":67.57,"lo":263,"hi":362,"n":20,"rr":117,"mr":286},{"m":"ling-3.0-tiny","r":312,"s":67.54,"lo":245,"hi":381,"n":15,"rr":1156,"mr":307},{"m":"qwen3-next-80b-a3b-thinking","r":313,"s":67.53,"lo":296,"hi":343,"n":63,"rr":443,"mr":293},{"m":"iquest-coder-v1-40b-loop-instruct","r":314,"s":67.5,"lo":260,"hi":405,"n":18,"rr":377,"mr":311},{"m":"holo2-8b","r":315,"s":67.5,"lo":259,"hi":392,"n":8,"rr":84,"mr":352},{"m":"grok-4.1-fast","r":316,"s":67.5,"lo":274,"hi":380,"n":36,"rr":1258,"mr":303},{"m":"granite-4.2-30b","r":317,"s":67.46,"lo":291,"hi":367,"n":21,"rr":1004,"mr":292},{"m":"neohorse-1-4b","r":318,"s":67.45,"lo":253,"hi":390,"n":9,"rr":661,"mr":316},{"m":"spark-x2.5-4b","r":319,"s":67.39,"lo":273,"hi":411,"n":28,"rr":1056,"mr":306},{"m":"vllm-sr-d3","r":320,"s":67.25,"lo":211,"hi":512,"n":28,"rr":129,"mr":339},{"m":"laguna-xs-2.1","r":321,"s":67.09,"lo":243,"hi":658,"n":9,"rr":1277,"mr":325},{"m":"hy-2.0-thinking","r":322,"s":67.08,"lo":276,"hi":368,"n":14,"rr":1337,"mr":329},{"m":"command-a-plus-05-2026","r":323,"s":67.04,"lo":247,"hi":484,"n":24,"rr":937,"mr":308},{"m":"gpt-realtime-2.1-high","r":324,"s":66.98,"lo":223,"hi":545,"n":12,"rr":106,"mr":391},{"m":"claude-4.5-haiku","r":325,"s":66.97,"lo":285,"hi":371,"n":96,"rr":1196,"mr":322},{"m":"nemotron-labs-dory1.0-4b-4loop","r":326,"s":66.95,"lo":233,"hi":421,"n":9,"rr":1350,"mr":315},{"m":"seed2.0-mini","r":327,"s":66.93,"lo":278,"hi":393,"n":56,"rr":820,"mr":314},{"m":"qwen3-vl-235b-a22b-instruct","r":328,"s":66.82,"lo":263,"hi":370,"n":16,"rr":196,"mr":365},{"m":"ring-flash-linear-2.0","r":329,"s":66.74,"lo":306,"hi":374,"n":8,"rr":390,"mr":328},{"m":"deepseek-v3.2-exp","r":330,"s":66.74,"lo":296,"hi":456,"n":49,"rr":542,"mr":312},{"m":"longcat-flash-omni","r":331,"s":66.7,"lo":260,"hi":509,"n":13,"rr":12,"mr":375},{"m":"qwen3.5-9b","r":332,"s":66.67,"lo":302,"hi":359,"n":163,"rr":752,"mr":319},{"m":"gemma-4-26b-a4b","r":333,"s":66.54,"lo":259,"hi":569,"n":31,"rr":460,"mr":318},{"m":"qwen3-vl-32b-thinking","r":334,"s":66.54,"lo":292,"hi":391,"n":37,"rr":127,"mr":320},{"m":"deepseek-r1-0528","r":335,"s":66.53,"lo":311,"hi":373,"n":52,"rr":888,"mr":317},{"m":"lfm2.5-24b-a2b","r":336,"s":66.46,"lo":237,"hi":437,"n":14,"rr":882,"mr":335},{"m":"openreasoning-nemotron-32b","r":337,"s":66.42,"lo":323,"hi":369,"n":9,"rr":505,"mr":326},{"m":"clef","r":338,"s":66.38,"lo":215,"hi":520,"n":31,"rr":276,"mr":353},{"m":"gpt-oss-120b","r":339,"s":66.38,"lo":296,"hi":400,"n":91,"rr":969,"mr":327},{"m":"gpt-5-mini-medium","r":340,"s":66.37,"lo":287,"hi":427,"n":9,"rr":1165,"mr":341},{"m":"seed-oss-36b-instruct","r":341,"s":66.27,"lo":325,"hi":363,"n":9,"rr":277,"mr":333},{"m":"gemini-2.5-pro-preview-06-05","r":342,"s":66.23,"lo":248,"hi":426,"n":12,"rr":1214,"mr":349},{"m":"openpangu-2.0-flash","r":343,"s":66.23,"lo":283,"hi":408,"n":21,"rr":964,"mr":324},{"m":"gpt-oss-swallow-120b-rl-v0.1","r":344,"s":66.22,"lo":270,"hi":440,"n":10,"rr":34,"mr":332},{"m":"holo1.5-7b","r":345,"s":66.17,"lo":293,"hi":409,"n":10,"rr":19,"mr":397},{"m":"gpt-realtime-2.0-high","r":346,"s":65.98,"lo":199,"hi":603,"n":12,"rr":162,"mr":423},{"m":"longcat-flash-lite-sparse","r":347,"s":65.95,"lo":261,"hi":497,"n":22,"rr":719,"mr":343},{"m":"clef-flash","r":348,"s":65.78,"lo":208,"hi":542,"n":31,"rr":335,"mr":378},{"m":"claude-3.7-sonnet-thinking","r":349,"s":65.75,"lo":292,"hi":435,"n":23,"rr":417,"mr":379},{"m":"nemotron-labs-dory1.0-4b","r":350,"s":65.66,"lo":260,"hi":445,"n":9,"rr":1370,"mr":345},{"m":"tml-interaction-small","r":351,"s":65.64,"lo":171,"hi":638,"n":9,"rr":119,"mr":409},{"m":"glm-4.5","r":352,"s":65.64,"lo":315,"hi":396,"n":40,"rr":1021,"mr":338},{"m":"kimi-k2-instruct-0905","r":353,"s":65.63,"lo":288,"hi":422,"n":24,"rr":582,"mr":354},{"m":"qwen3-max-instruct-preview","r":354,"s":65.53,"lo":300,"hi":422,"n":12,"rr":669,"mr":358},{"m":"nemotron-3-nano-30b-a3b","r":355,"s":65.5,"lo":324,"hi":445,"n":36,"rr":708,"mr":337},{"m":"step3-vl-10b","r":356,"s":65.41,"lo":326,"hi":412,"n":33,"rr":261,"mr":347},{"m":"glm-4.5v","r":357,"s":65.39,"lo":320,"hi":421,"n":47,"rr":362,"mr":390},{"m":"glm-4.7-flash","r":358,"s":65.38,"lo":316,"hi":459,"n":38,"rr":686,"mr":336},{"m":"minicpm5-2b","r":359,"s":65.37,"lo":308,"hi":443,"n":28,"rr":954,"mr":334},{"m":"minimax-m1-80k","r":360,"s":65.34,"lo":308,"hi":396,"n":17,"rr":602,"mr":344},{"m":"zwz-8b","r":361,"s":65.29,"lo":228,"hi":437,"n":9,"rr":368,"mr":425},{"m":"qwen3-coder-480b-a35b-instruct","r":362,"s":65.23,"lo":297,"hi":482,"n":33,"rr":404,"mr":357},{"m":"molmo2-er","r":363,"s":65.19,"lo":261,"hi":518,"n":11,"rr":455,"mr":430},{"m":"nemotron-labs-3-elastic-30b-a3b","r":364,"s":65.11,"lo":300,"hi":593,"n":8,"rr":524,"mr":366},{"m":"qwen3-max","r":365,"s":65.1,"lo":282,"hi":440,"n":10,"rr":1380,"mr":388},{"m":"qwen3-next-80b-a3b","r":366,"s":65.08,"lo":303,"hi":527,"n":10,"rr":1018,"mr":346},{"m":"openreasoning-nemotron-14b","r":367,"s":65.07,"lo":350,"hi":407,"n":9,"rr":656,"mr":348},{"m":"superapriel-15b-instruct","r":368,"s":65.04,"lo":301,"hi":622,"n":9,"rr":175,"mr":342},{"m":"nemotron-cascade-14b-thinking","r":369,"s":65.03,"lo":331,"hi":439,"n":14,"rr":305,"mr":340},{"m":"claude-3.7-sonnet-20250219","r":370,"s":64.92,"lo":323,"hi":556,"n":9,"rr":876,"mr":400},{"m":"qwen3-swallow-32b-rl-v0.2","r":371,"s":64.9,"lo":334,"hi":459,"n":10,"rr":56,"mr":351},{"m":"kimi-k2-instruct","r":372,"s":64.89,"lo":337,"hi":427,"n":53,"rr":896,"mr":350},{"m":"ming-flash-omni-2.0","r":373,"s":64.83,"lo":322,"hi":411,"n":17,"rr":100,"mr":414},{"m":"qwen3-omni-flash-thinking","r":374,"s":64.8,"lo":353,"hi":434,"n":22,"rr":33,"mr":392},{"m":"qwen-drive-1.0-4b","r":375,"s":64.69,"lo":296,"hi":464,"n":16,"rr":540,"mr":442},{"m":"nemotron-32b","r":376,"s":64.68,"lo":354,"hi":434,"n":9,"rr":1016,"mr":362},{"m":"ax-k1","r":377,"s":64.61,"lo":269,"hi":516,"n":18,"rr":741,"mr":363},{"m":"gpt-5.4-none","r":378,"s":64.5,"lo":212,"hi":499,"n":19,"rr":1082,"mr":367},{"m":"marco-deepresearch-8b","r":379,"s":64.43,"lo":302,"hi":536,"n":8,"rr":1184,"mr":406},{"m":"glm-4.6v","r":380,"s":64.41,"lo":287,"hi":437,"n":52,"rr":264,"mr":393},{"m":"ernie-4.5-vl-28b-a3b-thinking","r":381,"s":64.4,"lo":291,"hi":499,"n":18,"rr":116,"mr":438},{"m":"o4-mini-2025-04-16","r":382,"s":64.34,"lo":290,"hi":515,"n":9,"rr":918,"mr":405},{"m":"glm-4.5-air","r":383,"s":64.25,"lo":353,"hi":436,"n":46,"rr":737,"mr":361},{"m":"granite-4.2-8b","r":384,"s":64.17,"lo":346,"hi":445,"n":26,"rr":1045,"mr":364},{"m":"claude-opus-4","r":385,"s":64.08,"lo":335,"hi":458,"n":52,"rr":929,"mr":373},{"m":"gpt-4o-audio","r":386,"s":64.05,"lo":361,"hi":544,"n":10,"rr":18,"mr":459},{"m":"mistral-small-4-thinking","r":387,"s":64.04,"lo":355,"hi":459,"n":22,"rr":858,"mr":356},{"m":"qwen3-vl-30b-a3b-thinking","r":388,"s":64.04,"lo":370,"hi":431,"n":28,"rr":207,"mr":376},{"m":"qwen3-30b-a3b-thinking-2507","r":389,"s":63.99,"lo":348,"hi":468,"n":73,"rr":659,"mr":369},{"m":"qwen3-omni-30b-a3b-thinking","r":390,"s":63.88,"lo":371,"hi":463,"n":35,"rr":37,"mr":418},{"m":"k2-think","r":391,"s":63.87,"lo":363,"hi":585,"n":11,"rr":901,"mr":377},{"m":"claude-sonnet-4","r":392,"s":63.85,"lo":343,"hi":455,"n":141,"rr":873,"mr":386},{"m":"minimax-m1-40k","r":393,"s":63.79,"lo":339,"hi":443,"n":17,"rr":647,"mr":370},{"m":"gemma-4-12b-it","r":394,"s":63.69,"lo":348,"hi":455,"n":68,"rr":1032,"mr":383},{"m":"seed-thinking-v1.5","r":395,"s":63.68,"lo":371,"hi":448,"n":17,"rr":756,"mr":381},{"m":"qwen3.5-4b","r":396,"s":63.68,"lo":365,"hi":453,"n":165,"rr":780,"mr":387},{"m":"o3-mini-high","r":397,"s":63.63,"lo":347,"hi":576,"n":26,"rr":1152,"mr":416},{"m":"solar-open-100b","r":398,"s":63.63,"lo":348,"hi":471,"n":29,"rr":975,"mr":371},{"m":"gemini-2.5-flash-thinking","r":399,"s":63.6,"lo":355,"hi":438,"n":53,"rr":300,"mr":389},{"m":"gpt-oss-120b-medium","r":400,"s":63.59,"lo":345,"hi":454,"n":29,"rr":307,"mr":384},{"m":"seed-1.5-vl","r":401,"s":63.59,"lo":294,"hi":480,"n":32,"rr":322,"mr":429},{"m":"sarvam-30b","r":402,"s":63.58,"lo":342,"hi":469,"n":15,"rr":197,"mr":374},{"m":"deepseek-v3.1","r":403,"s":63.55,"lo":333,"hi":524,"n":55,"rr":552,"mr":368},{"m":"qwen3-vl-32b-instruct","r":404,"s":63.55,"lo":340,"hi":464,"n":70,"rr":279,"mr":395},{"m":"qwen3-235b-a22b","r":405,"s":63.5,"lo":366,"hi":453,"n":94,"rr":733,"mr":380},{"m":"mercury-2","r":406,"s":63.5,"lo":286,"hi":529,"n":12,"rr":1070,"mr":399},{"m":"rynnbrain-30b-a3b","r":407,"s":63.46,"lo":304,"hi":530,"n":13,"rr":166,"mr":483},{"m":"eleven-realtime-v1-mini","r":408,"s":63.45,"lo":163,"hi":655,"n":9,"rr":157,"mr":500},{"m":"joyai-llm-flash","r":409,"s":63.44,"lo":344,"hi":540,"n":20,"rr":184,"mr":360},{"m":"zaya1-8b","r":410,"s":63.44,"lo":344,"hi":539,"n":11,"rr":519,"mr":385},{"m":"mirothinker-v1.0-8b","r":411,"s":63.41,"lo":333,"hi":516,"n":12,"rr":1263,"mr":439},{"m":"zwz-4b","r":412,"s":63.39,"lo":291,"hi":481,"n":9,"rr":427,"mr":481},{"m":"gpt-oss-swallow-20b-rl-v0.1","r":413,"s":63.35,"lo":361,"hi":509,"n":10,"rr":75,"mr":394},{"m":"apriel-1.6-15b-thinker","r":414,"s":63.34,"lo":347,"hi":481,"n":29,"rr":802,"mr":420},{"m":"o1","r":415,"s":63.33,"lo":354,"hi":468,"n":24,"rr":601,"mr":411},{"m":"nemotron-cascade-8b","r":416,"s":63.32,"lo":367,"hi":484,"n":14,"rr":401,"mr":372},{"m":"ling-1t","r":417,"s":63.23,"lo":289,"hi":490,"n":28,"rr":991,"mr":398},{"m":"qwen-audio-3.0-realtime-flash","r":418,"s":63.14,"lo":204,"hi":634,"n":9,"rr":115,"mr":509},{"m":"kimi-k2","r":419,"s":63.12,"lo":355,"hi":484,"n":25,"rr":1238,"mr":422},{"m":"o3-mini","r":420,"s":63.09,"lo":362,"hi":471,"n":17,"rr":738,"mr":419},{"m":"o1-preview-2024-09-12","r":421,"s":63.08,"lo":347,"hi":551,"n":12,"rr":46,"mr":444},{"m":"ui-venus-72b","r":422,"s":63.01,"lo":275,"hi":605,"n":12,"rr":167,"mr":492},{"m":"nemotron-cascade-8b-thinking","r":423,"s":62.95,"lo":373,"hi":512,"n":14,"rr":422,"mr":382},{"m":"clef-omni","r":424,"s":62.92,"lo":256,"hi":631,"n":31,"rr":399,"mr":453},{"m":"ministral-3-14b-reasoning","r":425,"s":62.92,"lo":373,"hi":516,"n":17,"rr":325,"mr":403},{"m":"gpt-realtime-2.0-medium","r":426,"s":62.85,"lo":212,"hi":622,"n":8,"rr":158,"mr":505},{"m":"grok-voice-fast-1.0","r":427,"s":62.84,"lo":333,"hi":1351,"n":8,"rr":664,"mr":498},{"m":"golongrl-4b","r":428,"s":62.81,"lo":394,"hi":570,"n":8,"rr":337,"mr":404},{"m":"mellum2.1-12b-a2.5b-thinking","r":429,"s":62.8,"lo":346,"hi":508,"n":12,"rr":288,"mr":396},{"m":"o1-2024-12-17","r":430,"s":62.69,"lo":378,"hi":480,"n":18,"rr":471,"mr":431},{"m":"qwen3-vl-8b-thinking","r":431,"s":62.68,"lo":381,"hi":494,"n":48,"rr":146,"mr":407},{"m":"motif-2-12.7b-reasoning","r":432,"s":62.67,"lo":388,"hi":525,"n":16,"rr":25,"mr":402},{"m":"grok-4-fast-thinking","r":433,"s":62.67,"lo":300,"hi":713,"n":17,"rr":1069,"mr":477},{"m":"gemini-3.8-live","r":434,"s":62.65,"lo":214,"hi":708,"n":9,"rr":160,"mr":514},{"m":"claude-opus-4.1-20250805","r":435,"s":62.63,"lo":284,"hi":686,"n":9,"rr":920,"mr":451},{"m":"qwen3-14b-thinking","r":436,"s":62.57,"lo":398,"hi":491,"n":22,"rr":206,"mr":410},{"m":"gemini-2.5-flash","r":437,"s":62.51,"lo":394,"hi":465,"n":168,"rr":765,"mr":427},{"m":"apriel-1.5-15b-thinker-self-reported","r":438,"s":62.5,"lo":382,"hi":601,"n":10,"rr":1162,"mr":434},{"m":"gpt-oss-20b-high","r":439,"s":62.43,"lo":367,"hi":511,"n":19,"rr":655,"mr":412},{"m":"gpt-oss-swallow-120b-sft-v0.1","r":440,"s":62.43,"lo":399,"hi":493,"n":10,"rr":48,"mr":421},{"m":"qwen3-30b-a3b-2507","r":441,"s":62.41,"lo":377,"hi":509,"n":19,"rr":815,"mr":440},{"m":"longcat-flash-lite","r":442,"s":62.4,"lo":348,"hi":511,"n":14,"rr":299,"mr":415},{"m":"falcon-h1r-7b","r":443,"s":62.32,"lo":400,"hi":632,"n":22,"rr":902,"mr":401},{"m":"qwen3.5-omni-flash","r":444,"s":62.31,"lo":367,"hi":500,"n":44,"rr":391,"mr":437},{"m":"openpangu-r-7b-2512-slow-thinking","r":445,"s":62.31,"lo":370,"hi":511,"n":20,"rr":435,"mr":413},{"m":"gemini-robotics-er-1.5-thinking","r":446,"s":62.24,"lo":369,"hi":567,"n":11,"rr":650,"mr":515},{"m":"magistral-medium-1.2","r":447,"s":62.22,"lo":349,"hi":536,"n":18,"rr":1050,"mr":428},{"m":"claude-3.7-sonnet","r":448,"s":62.21,"lo":367,"hi":500,"n":63,"rr":615,"mr":450},{"m":"jev-1.13","r":449,"s":62.18,"lo":281,"hi":614,"n":33,"rr":246,"mr":473},{"m":"hypernova-60b-2605","r":450,"s":62.17,"lo":331,"hi":527,"n":11,"rr":1073,"mr":441},{"m":"qwen3-32b-thinking","r":451,"s":62.12,"lo":396,"hi":493,"n":56,"rr":536,"mr":417},{"m":"telechat3-36b-thinking","r":452,"s":62.06,"lo":380,"hi":497,"n":11,"rr":77,"mr":408},{"m":"glide-no-thinking","r":453,"s":62.04,"lo":294,"hi":586,"n":27,"rr":219,"mr":472},{"m":"k2-high-70b","r":454,"s":62.01,"lo":362,"hi":579,"n":10,"rr":224,"mr":424},{"m":"o3-mini-medium","r":455,"s":61.99,"lo":404,"hi":477,"n":10,"rr":1128,"mr":458},{"m":"deepseek-r1","r":456,"s":61.94,"lo":409,"hi":483,"n":62,"rr":1046,"mr":443},{"m":"diffusiongemma-26b-a4b","r":457,"s":61.82,"lo":363,"hi":532,"n":12,"rr":1031,"mr":446},{"m":"gpt-oss-20b","r":458,"s":61.8,"lo":408,"hi":518,"n":71,"rr":957,"mr":432},{"m":"jev-1.14","r":459,"s":61.79,"lo":302,"hi":607,"n":31,"rr":284,"mr":476},{"m":"qwen3-next-80b-a3b-instruct","r":460,"s":61.79,"lo":410,"hi":497,"n":40,"rr":491,"mr":433},{"m":"rynnbrain-8b","r":461,"s":61.75,"lo":328,"hi":571,"n":13,"rr":186,"mr":520},{"m":"exaone-4.0-32b-thinking","r":462,"s":61.74,"lo":380,"hi":607,"n":23,"rr":885,"mr":445},{"m":"gemini-2.5-flash-preview-09-2025","r":463,"s":61.74,"lo":382,"hi":506,"n":19,"rr":1137,"mr":452},{"m":"ministral-3-r-8b","r":464,"s":61.71,"lo":402,"hi":753,"n":14,"rr":332,"mr":436},{"m":"nemotron-labs-dory1.0-4b-1loop","r":465,"s":61.69,"lo":350,"hi":534,"n":9,"rr":1420,"mr":447},{"m":"ling-2.6-flash","r":466,"s":61.68,"lo":360,"hi":549,"n":18,"rr":1099,"mr":455},{"m":"qwen3-32b-thinking-2504","r":467,"s":61.65,"lo":387,"hi":573,"n":8,"rr":749,"mr":465},{"m":"toolmind-web-3b","r":468,"s":61.56,"lo":367,"hi":528,"n":8,"rr":1333,"mr":491},{"m":"olmo-3.1-think-32b","r":469,"s":61.45,"lo":416,"hi":516,"n":31,"rr":194,"mr":426},{"m":"k2-think-v2","r":470,"s":61.37,"lo":347,"hi":723,"n":12,"rr":347,"mr":448},{"m":"zgcm-1-7b","r":471,"s":61.37,"lo":438,"hi":523,"n":9,"rr":535,"mr":462},{"m":"olmo-3-think-32b-dpo","r":472,"s":61.33,"lo":408,"hi":505,"n":24,"rr":154,"mr":435},{"m":"gpt-5-nano-high","r":473,"s":61.28,"lo":417,"hi":567,"n":9,"rr":1168,"mr":478},{"m":"nanbeige4-3b-thinking-2511","r":474,"s":61.17,"lo":360,"hi":577,"n":16,"rr":1077,"mr":469},{"m":"kimi-k2-0905","r":475,"s":61.16,"lo":356,"hi":538,"n":35,"rr":1246,"mr":467},{"m":"qwen3-vl-30b-a3b-instruct","r":476,"s":61.07,"lo":429,"hi":503,"n":101,"rr":555,"mr":479},{"m":"gpt-oss-20b-medium","r":477,"s":61.05,"lo":437,"hi":511,"n":14,"rr":220,"mr":457},{"m":"nvidia-nemotron-3-nano-30b-a3b-bf16","r":478,"s":61.02,"lo":377,"hi":541,"n":36,"rr":1223,"mr":454},{"m":"agentcpm-explore","r":479,"s":61.01,"lo":387,"hi":549,"n":11,"rr":1200,"mr":501},{"m":"claude-sonnet-4-20250514","r":480,"s":60.98,"lo":383,"hi":675,"n":11,"rr":1379,"mr":502},{"m":"longcat-next","r":481,"s":60.97,"lo":418,"hi":523,"n":29,"rr":474,"mr":490},{"m":"qwen3-swallow-32b-sft-v0.2","r":482,"s":60.93,"lo":436,"hi":540,"n":10,"rr":121,"mr":466},{"m":"apriel-1.5-15b-thinker","r":483,"s":60.9,"lo":429,"hi":552,"n":36,"rr":1085,"mr":470},{"m":"gemini-3.1-flash-live-high","r":484,"s":60.87,"lo":263,"hi":1181,"n":17,"rr":431,"mr":540},{"m":"gemini-2.5-flash-preview-05-20","r":485,"s":60.79,"lo":414,"hi":541,"n":12,"rr":1359,"mr":494},{"m":"minicpm-sala","r":486,"s":60.79,"lo":434,"hi":644,"n":15,"rr":98,"mr":456},{"m":"qwen3-235b-a22b-instruct-2507","r":487,"s":60.75,"lo":412,"hi":533,"n":35,"rr":972,"mr":482},{"m":"openpangu-r-72b-2512-fast-thinking","r":488,"s":60.6,"lo":343,"hi":551,"n":20,"rr":396,"mr":463},{"m":"kanana-2-30b-a3b-thinking-2601","r":489,"s":60.58,"lo":449,"hi":537,"n":9,"rr":447,"mr":449},{"m":"llada2.1-flash-q","r":490,"s":60.41,"lo":413,"hi":547,"n":33,"rr":147,"mr":471},{"m":"qwen3-omni-flash-instruct","r":491,"s":60.39,"lo":425,"hi":679,"n":26,"rr":88,"mr":510},{"m":"openreasoning-nemotron-7b","r":492,"s":60.36,"lo":457,"hi":580,"n":28,"rr":889,"mr":468},{"m":"nvidia-nemotron-nano-9b-v2","r":493,"s":60.3,"lo":437,"hi":565,"n":27,"rr":454,"mr":464},{"m":"magistral-small-1.2","r":494,"s":60.27,"lo":422,"hi":726,"n":12,"rr":1185,"mr":480},{"m":"nemotron-3.5-lightning-30b-a3b","r":495,"s":60.22,"lo":384,"hi":633,"n":36,"rr":946,"mr":461},{"m":"ui-tars-1.5-7b","r":496,"s":60.15,"lo":360,"hi":633,"n":12,"rr":139,"mr":553},{"m":"gpt-4.1-2025-04-14","r":497,"s":60.14,"lo":337,"hi":702,"n":13,"rr":988,"mr":539},{"m":"gpt-realtime-2.0","r":498,"s":60.09,"lo":203,"hi":658,"n":17,"rr":273,"mr":552},{"m":"infinity-parser2-pro","r":499,"s":60.06,"lo":403,"hi":601,"n":11,"rr":10,"mr":547},{"m":"kanana-2-30b-a3b-thinking","r":500,"s":60.05,"lo":480,"hi":556,"n":9,"rr":526,"mr":460},{"m":"gpt-oss-swallow-20b-sft-v0.1","r":501,"s":60.04,"lo":456,"hi":568,"n":10,"rr":135,"mr":487},{"m":"gpt-realtime-1.5","r":502,"s":60.01,"lo":189,"hi":620,"n":17,"rr":269,"mr":551},{"m":"llada2.0-flash","r":503,"s":59.9,"lo":448,"hi":546,"n":43,"rr":70,"mr":474},{"m":"holo1.5-3b","r":504,"s":59.89,"lo":415,"hi":587,"n":10,"rr":50,"mr":556},{"m":"qwen3-swallow-32b-cpt-v0.2","r":505,"s":59.79,"lo":479,"hi":536,"n":10,"rr":104,"mr":493},{"m":"qwen3-swallow-30b-a3b-rl-v0.2","r":506,"s":59.79,"lo":460,"hi":581,"n":10,"rr":156,"mr":495},{"m":"grok-3-mini","r":507,"s":59.76,"lo":250,"hi":579,"n":8,"rr":1079,"mr":528},{"m":"medmo-8b-next","r":508,"s":59.73,"lo":375,"hi":640,"n":9,"rr":360,"mr":557},{"m":"mimo-v2.5-pro-base","r":509,"s":59.7,"lo":390,"hi":604,"n":19,"rr":31,"mr":485},{"m":"exaone-4.0-32b","r":510,"s":59.7,"lo":413,"hi":754,"n":12,"rr":1241,"mr":526},{"m":"qwen3.5-omni-plus-realtime","r":511,"s":59.69,"lo":153,"hi":973,"n":9,"rr":237,"mr":559},{"m":"olmo-3-think-32b","r":512,"s":59.6,"lo":466,"hi":562,"n":34,"rr":248,"mr":475},{"m":"qwen2.5-vl-72b","r":513,"s":59.55,"lo":439,"hi":573,"n":37,"rr":244,"mr":550},{"m":"kolibri-origin","r":514,"s":59.54,"lo":438,"hi":676,"n":14,"rr":1161,"mr":504},{"m":"gpt-4.1","r":515,"s":59.5,"lo":435,"hi":560,"n":80,"rr":863,"mr":496},{"m":"olmo-3-think-32b-sft","r":516,"s":59.48,"lo":450,"hi":549,"n":24,"rr":208,"mr":484},{"m":"qwen3-30b-a3b-instruct-2507","r":517,"s":59.41,"lo":467,"hi":569,"n":74,"rr":293,"mr":488},{"m":"glm-4.6v-flash","r":518,"s":59.24,"lo":428,"hi":571,"n":35,"rr":701,"mr":548},{"m":"pelican-vl-72b","r":519,"s":59.23,"lo":357,"hi":660,"n":13,"rr":320,"mr":572},{"m":"motif-2-12.7b-instruct","r":520,"s":59.23,"lo":473,"hi":567,"n":16,"rr":68,"mr":489},{"m":"instella-moe-16b-a3b-think","r":521,"s":59.2,"lo":457,"hi":642,"n":12,"rr":163,"mr":503},{"m":"o1-preview","r":522,"s":59.18,"lo":400,"hi":632,"n":17,"rr":89,"mr":518},{"m":"llada2.1-flash-s","r":523,"s":59.17,"lo":461,"hi":571,"n":33,"rr":180,"mr":499},{"m":"telechat3-105b-a4.7b-thinking","r":524,"s":59.15,"lo":460,"hi":555,"n":11,"rr":164,"mr":486},{"m":"mistral-large-3","r":525,"s":59.15,"lo":436,"hi":679,"n":10,"rr":1202,"mr":522},{"m":"deepseek-v3-0324","r":526,"s":59.15,"lo":432,"hi":579,"n":48,"rr":1011,"mr":507},{"m":"deepseek-r1-0528-qwen3-8b","r":527,"s":59.07,"lo":483,"hi":633,"n":15,"rr":1130,"mr":508},{"m":"minicpm-o-4.5-thinking","r":528,"s":59.05,"lo":419,"hi":603,"n":13,"rr":41,"mr":569},{"m":"rynnbrain-4b","r":529,"s":58.94,"lo":387,"hi":622,"n":13,"rr":195,"mr":578},{"m":"vllm-sr-decision-2.0-vega-27b","r":530,"s":58.9,"lo":379,"hi":664,"n":28,"rr":375,"mr":536},{"m":"instella-moe-16b-a3b-dpo","r":531,"s":58.87,"lo":462,"hi":666,"n":12,"rr":172,"mr":511},{"m":"midm-k-2.5-pro","r":532,"s":58.84,"lo":307,"hi":863,"n":9,"rr":1404,"mr":533},{"m":"mimo-vl-7b-rl-2508","r":533,"s":58.81,"lo":443,"hi":587,"n":16,"rr":200,"mr":571},{"m":"ernie-4.5","r":534,"s":58.8,"lo":382,"hi":610,"n":24,"rr":92,"mr":497},{"m":"minicpm4.1-8b","r":535,"s":58.71,"lo":490,"hi":590,"n":14,"rr":144,"mr":512},{"m":"grok-3-beta","r":536,"s":58.63,"lo":449,"hi":622,"n":14,"rr":768,"mr":544},{"m":"abeja-qwq32b-reasoning-japanese-v1.0","r":537,"s":58.63,"lo":466,"hi":621,"n":10,"rr":128,"mr":538},{"m":"granite-4.2-3b","r":538,"s":58.6,"lo":483,"hi":600,"n":35,"rr":1255,"mr":513},{"m":"ling-flash-2.0","r":539,"s":58.55,"lo":460,"hi":588,"n":44,"rr":86,"mr":506},{"m":"r-4b-base","r":540,"s":58.52,"lo":415,"hi":706,"n":8,"rr":370,"mr":588},{"m":"ui-venus-7b","r":541,"s":58.51,"lo":429,"hi":631,"n":12,"rr":317,"mr":585},{"m":"qwen3-32b","r":542,"s":58.45,"lo":481,"hi":575,"n":78,"rr":800,"mr":516},{"m":"llama-nemotron-super-49b-v1.5","r":543,"s":58.36,"lo":407,"hi":757,"n":10,"rr":1279,"mr":517},{"m":"pplx-decider-flash-v1.2","r":544,"s":58.36,"lo":377,"hi":667,"n":27,"rr":330,"mr":546},{"m":"qwq-32b","r":545,"s":58.27,"lo":466,"hi":617,"n":24,"rr":1034,"mr":524},{"m":"lg-exaone-32b","r":546,"s":58.24,"lo":449,"hi":620,"n":10,"rr":123,"mr":521},{"m":"instella-moe-16b-a3b-sft","r":547,"s":58.17,"lo":474,"hi":710,"n":12,"rr":198,"mr":523},{"m":"gpt-realtime-2.1","r":548,"s":58.14,"lo":305,"hi":766,"n":9,"rr":150,"mr":599},{"m":"glm-4.1v","r":549,"s":58.13,"lo":473,"hi":611,"n":35,"rr":623,"mr":574},{"m":"qwen3-4b-2507","r":550,"s":58.01,"lo":486,"hi":673,"n":22,"rr":1296,"mr":530},{"m":"nemotron-research-goosereason-4b-instruct","r":551,"s":57.87,"lo":482,"hi":626,"n":10,"rr":203,"mr":531},{"m":"qwen3-8b-thinking","r":552,"s":57.87,"lo":488,"hi":627,"n":36,"rr":675,"mr":519},{"m":"phi-4-reasoning-plus","r":553,"s":57.82,"lo":509,"hi":618,"n":19,"rr":1065,"mr":529},{"m":"ace-brain-0.5-8b","r":554,"s":57.81,"lo":326,"hi":819,"n":28,"rr":827,"mr":604},{"m":"deepseek-r1-distill-qwen-32b","r":555,"s":57.72,"lo":504,"hi":620,"n":20,"rr":805,"mr":537},{"m":"vllm-sr-d3-flash","r":556,"s":57.71,"lo":395,"hi":688,"n":27,"rr":372,"mr":558},{"m":"qwen3-30b-a3b","r":557,"s":57.68,"lo":511,"hi":638,"n":74,"rr":468,"mr":525},{"m":"qwen3-4b-thinking-2507","r":558,"s":57.65,"lo":505,"hi":627,"n":37,"rr":801,"mr":535},{"m":"gpt-4.5","r":559,"s":57.56,"lo":413,"hi":621,"n":21,"rr":683,"mr":564},{"m":"hyperclovax-seed-think","r":560,"s":57.53,"lo":414,"hi":644,"n":10,"rr":1305,"mr":527},{"m":"o1-mini","r":561,"s":57.44,"lo":470,"hi":600,"n":24,"rr":365,"mr":545},{"m":"mimo-vl-7b-rl","r":562,"s":57.44,"lo":502,"hi":601,"n":46,"rr":265,"mr":579},{"m":"apriel-nemotron-15b-thinker","r":563,"s":57.43,"lo":464,"hi":619,"n":10,"rr":133,"mr":532},{"m":"qwen3-omni-30b-a3b-instruct","r":564,"s":57.42,"lo":506,"hi":613,"n":73,"rr":323,"mr":563},{"m":"deepseek-v3","r":565,"s":57.36,"lo":511,"hi":598,"n":69,"rr":596,"mr":534},{"m":"hypernova-60b-2602","r":566,"s":57.35,"lo":473,"hi":619,"n":11,"rr":1257,"mr":561},{"m":"o1-mini-2024-09-12","r":567,"s":57.33,"lo":499,"hi":618,"n":17,"rr":253,"mr":555},{"m":"gpt-realtime","r":568,"s":57.32,"lo":191,"hi":738,"n":11,"rr":485,"mr":609},{"m":"llama-3.1-tulu-3-405b","r":569,"s":57.18,"lo":428,"hi":776,"n":9,"rr":32,"mr":573},{"m":"nemotron-nano-v2-9b","r":570,"s":57.18,"lo":505,"hi":780,"n":13,"rr":263,"mr":542},{"m":"plamo-3.0-prime-thinking","r":571,"s":57.15,"lo":498,"hi":605,"n":8,"rr":1041,"mr":541},{"m":"llama-4-maverick-17b-128e-instruct","r":572,"s":57.06,"lo":413,"hi":679,"n":13,"rr":326,"mr":583},{"m":"qwen3-vl-4b-thinking","r":573,"s":56.99,"lo":537,"hi":646,"n":47,"rr":764,"mr":562},{"m":"qwen2.5-vl-72b-instruct","r":574,"s":56.95,"lo":512,"hi":631,"n":55,"rr":690,"mr":600},{"m":"mimo-7b-rl","r":575,"s":56.82,"lo":540,"hi":624,"n":14,"rr":993,"mr":549},{"m":"qwen3-coder-30b-a3b-instruct","r":576,"s":56.78,"lo":519,"hi":632,"n":23,"rr":1192,"mr":565},{"m":"olmo-3-think-7b-dpo","r":577,"s":56.76,"lo":514,"hi":651,"n":18,"rr":616,"mr":543},{"m":"joyai-vl-interaction","r":578,"s":56.74,"lo":465,"hi":725,"n":15,"rr":812,"mr":614},{"m":"zwz-7b","r":579,"s":56.7,"lo":421,"hi":723,"n":9,"rr":716,"mr":618},{"m":"autotrust-jev-27b","r":580,"s":56.44,"lo":443,"hi":720,"n":28,"rr":481,"mr":587},{"m":"molmopoint-8b","r":581,"s":56.4,"lo":491,"hi":656,"n":31,"rr":222,"mr":616},{"m":"llama-3.1-405b","r":582,"s":56.35,"lo":495,"hi":704,"n":19,"rr":254,"mr":576},{"m":"autotrust-jev-35b","r":583,"s":56.33,"lo":418,"hi":722,"n":27,"rr":343,"mr":589},{"m":"magistral-medium-2506","r":584,"s":56.32,"lo":522,"hi":639,"n":8,"rr":1230,"mr":568},{"m":"bespoke-nimble-9b-v3","r":585,"s":56.05,"lo":423,"hi":697,"n":28,"rr":363,"mr":591},{"m":"olmo-3-think-7b","r":586,"s":56.03,"lo":551,"hi":660,"n":38,"rr":516,"mr":554},{"m":"qwen3.8-27b-iq2-xxs","r":587,"s":55.98,"lo":497,"hi":731,"n":13,"rr":153,"mr":570},{"m":"qwen3-swallow-30b-a3b-cpt-v0.2","r":588,"s":55.97,"lo":557,"hi":618,"n":10,"rr":182,"mr":567},{"m":"robobrain2.5-8b","r":589,"s":55.94,"lo":341,"hi":880,"n":28,"rr":862,"mr":651},{"m":"cosmos3-nano","r":590,"s":55.94,"lo":505,"hi":672,"n":41,"rr":797,"mr":627},{"m":"kimi-linear-instruct","r":591,"s":55.93,"lo":541,"hi":670,"n":22,"rr":828,"mr":560},{"m":"step-3","r":592,"s":55.88,"lo":503,"hi":708,"n":27,"rr":817,"mr":622},{"m":"gemini-2.0-pro","r":593,"s":55.82,"lo":519,"hi":676,"n":22,"rr":374,"mr":601},{"m":"qwen3-swallow-8b-rl-v0.2","r":594,"s":55.72,"lo":557,"hi":664,"n":10,"rr":257,"mr":575},{"m":"magistral-small-2506","r":595,"s":55.58,"lo":549,"hi":655,"n":8,"rr":1312,"mr":586},{"m":"qwen3-vl-8b-instruct","r":596,"s":55.56,"lo":554,"hi":625,"n":148,"rr":654,"mr":590},{"m":"olmo-3-think-7b-sft","r":597,"s":55.54,"lo":537,"hi":691,"n":18,"rr":694,"mr":566},{"m":"qwen2.5-omni","r":598,"s":55.52,"lo":519,"hi":853,"n":10,"rr":185,"mr":632},{"m":"molmo2-8b","r":599,"s":55.52,"lo":504,"hi":682,"n":33,"rr":236,"mr":643},{"m":"medgemma-27b-it","r":600,"s":55.47,"lo":411,"hi":714,"n":8,"rr":489,"mr":641},{"m":"qwen2.5-max","r":601,"s":55.47,"lo":495,"hi":766,"n":10,"rr":80,"mr":606},{"m":"glm-4.1v-9b","r":602,"s":55.47,"lo":495,"hi":678,"n":16,"rr":122,"mr":644},{"m":"llama-3.1-tulu-3-405b-dpo","r":603,"s":55.39,"lo":370,"hi":855,"n":9,"rr":38,"mr":610},{"m":"qwen3-swallow-30b-a3b-sft-v0.2","r":604,"s":55.39,"lo":571,"hi":647,"n":10,"rr":211,"mr":582},{"m":"k2-medium-70b","r":605,"s":55.27,"lo":537,"hi":712,"n":9,"rr":349,"mr":577},{"m":"gpt-4o-2024-11-24","r":606,"s":55.25,"lo":395,"hi":794,"n":9,"rr":27,"mr":621},{"m":"qwq-bakeneko-32b","r":607,"s":55.21,"lo":556,"hi":677,"n":10,"rr":210,"mr":603},{"m":"deepseek-v4-pro-base","r":608,"s":55.16,"lo":480,"hi":734,"n":23,"rr":53,"mr":592},{"m":"gpt-5-minimal","r":609,"s":55.12,"lo":500,"hi":661,"n":38,"rr":1064,"mr":595},{"m":"tri-21b-think","r":610,"s":55.06,"lo":437,"hi":700,"n":15,"rr":849,"mr":580},{"m":"internvl3.5-30b-a3b-flash","r":611,"s":55.04,"lo":540,"hi":664,"n":18,"rr":450,"mr":642},{"m":"mimo-vl-7b-sft","r":612,"s":54.96,"lo":537,"hi":671,"n":41,"rr":242,"mr":628},{"m":"claude-3.5-sonnet-20241022","r":613,"s":54.93,"lo":505,"hi":712,"n":50,"rr":746,"mr":584},{"m":"kimi-k2-base","r":614,"s":54.87,"lo":521,"hi":693,"n":43,"rr":85,"mr":594},{"m":"openpangu-r-7b-2512-fast-thinking","r":615,"s":54.87,"lo":512,"hi":677,"n":20,"rr":911,"mr":581},{"m":"llama-3.1-nemotron-nano-8b-v1","r":616,"s":54.8,"lo":557,"hi":724,"n":11,"rr":579,"mr":608},{"m":"gpt-4.1-mini","r":617,"s":54.76,"lo":550,"hi":664,"n":20,"rr":1307,"mr":612},{"m":"autotrust-gev-26b-decide","r":618,"s":54.72,"lo":428,"hi":806,"n":27,"rr":376,"mr":619},{"m":"manzano-30b","r":619,"s":54.69,"lo":542,"hi":716,"n":12,"rr":21,"mr":665},{"m":"webexplorer-8b","r":620,"s":54.65,"lo":508,"hi":793,"n":8,"rr":1438,"mr":633},{"m":"grok-3","r":621,"s":54.61,"lo":521,"hi":652,"n":10,"rr":1002,"mr":611},{"m":"gemini-2.0-flash","r":622,"s":54.36,"lo":554,"hi":800,"n":20,"rr":1007,"mr":636},{"m":"qwen2.5-plus-1127","r":623,"s":54.36,"lo":585,"hi":664,"n":12,"rr":83,"mr":598},{"m":"qwen3-14b","r":624,"s":54.15,"lo":571,"hi":704,"n":44,"rr":899,"mr":593},{"m":"hunyuan-large-instruct","r":625,"s":54.14,"lo":532,"hi":703,"n":12,"rr":26,"mr":623},{"m":"olmo-hybrid-think-7b-sft","r":626,"s":54.13,"lo":574,"hi":705,"n":15,"rr":711,"mr":596},{"m":"gemini-2.5-flash-lite","r":627,"s":54.04,"lo":579,"hi":683,"n":82,"rr":1081,"mr":615},{"m":"nemotron-3-ultra-base","r":628,"s":54.03,"lo":510,"hi":709,"n":21,"rr":14,"mr":605},{"m":"kanana-2-30b-a3b-instruct-2601","r":629,"s":54.02,"lo":575,"hi":719,"n":14,"rr":250,"mr":597},{"m":"penguin-vl-8b","r":630,"s":53.99,"lo":509,"hi":724,"n":20,"rr":255,"mr":664},{"m":"openpangu-vl-7b","r":631,"s":53.82,"lo":539,"hi":689,"n":31,"rr":159,"mr":613},{"m":"internvl2.5-78b","r":632,"s":53.7,"lo":550,"hi":777,"n":49,"rr":252,"mr":675},{"m":"claude-3.5-sonnet-20240620","r":633,"s":53.58,"lo":578,"hi":698,"n":55,"rr":215,"mr":617},{"m":"plamo-3.0-prime-beta","r":634,"s":53.48,"lo":573,"hi":697,"n":8,"rr":1216,"mr":625},{"m":"glm-4.1v-9b-thinking","r":635,"s":53.34,"lo":548,"hi":712,"n":29,"rr":329,"mr":684},{"m":"gemini-robotics-er-1.5","r":636,"s":53.31,"lo":580,"hi":782,"n":11,"rr":894,"mr":696},{"m":"eagle2.5-8b","r":637,"s":53.25,"lo":581,"hi":724,"n":29,"rr":229,"mr":691},{"m":"keye-vl-8b","r":638,"s":53.25,"lo":552,"hi":799,"n":11,"rr":865,"mr":693},{"m":"gpt-4o-0327","r":639,"s":53.18,"lo":478,"hi":777,"n":11,"rr":439,"mr":680},{"m":"youtu-llm-2b","r":640,"s":53.15,"lo":600,"hi":764,"n":19,"rr":572,"mr":602},{"m":"medmo-8b","r":641,"s":53.04,"lo":523,"hi":731,"n":9,"rr":677,"mr":690},{"m":"olmo-3.1-instruct-32b","r":642,"s":53.01,"lo":586,"hi":776,"n":26,"rr":262,"mr":607},{"m":"claude-3.5-sonnet","r":643,"s":53,"lo":571,"hi":710,"n":49,"rr":295,"mr":647},{"m":"vllm-sr-d3-mini","r":644,"s":52.98,"lo":500,"hi":801,"n":27,"rr":515,"mr":650},{"m":"openthinker3-7b","r":645,"s":52.94,"lo":577,"hi":818,"n":16,"rr":933,"mr":626},{"m":"nemotron-3-super-120b-a12b-base","r":646,"s":52.88,"lo":585,"hi":701,"n":40,"rr":155,"mr":624},{"m":"rnj-1.5","r":647,"s":52.84,"lo":541,"hi":725,"n":10,"rr":810,"mr":635},{"m":"spark-x2.5-1.7b","r":648,"s":52.82,"lo":561,"hi":763,"n":16,"rr":1424,"mr":639},{"m":"ling-3.0-flash-base","r":649,"s":52.81,"lo":592,"hi":728,"n":17,"rr":392,"mr":640},{"m":"qwen3-swallow-8b-sft-v0.2","r":650,"s":52.8,"lo":608,"hi":759,"n":10,"rr":410,"mr":630},{"m":"mistral-medium-3.1","r":651,"s":52.76,"lo":577,"hi":711,"n":14,"rr":1251,"mr":661},{"m":"deepseek-v4.1-flash-base","r":652,"s":52.74,"lo":559,"hi":777,"n":19,"rr":190,"mr":648},{"m":"deepseek-v4-flash-base","r":653,"s":52.74,"lo":539,"hi":784,"n":27,"rr":199,"mr":629},{"m":"pixtral-large-2411","r":654,"s":52.72,"lo":487,"hi":762,"n":8,"rr":359,"mr":726},{"m":"seed1.6","r":655,"s":52.71,"lo":504,"hi":766,"n":11,"rr":345,"mr":646},{"m":"gpt-realtime-2.1-mini-high","r":656,"s":52.64,"lo":211,"hi":822,"n":8,"rr":429,"mr":719},{"m":"nemotron-h-47b-reasoning","r":657,"s":52.59,"lo":608,"hi":797,"n":13,"rr":1389,"mr":637},{"m":"kat-dev-32b","r":658,"s":52.56,"lo":563,"hi":800,"n":18,"rr":1150,"mr":649},{"m":"llama-4-scout-17b-16e","r":659,"s":52.54,"lo":573,"hi":808,"n":13,"rr":721,"mr":667},{"m":"mistral-small-4","r":660,"s":52.52,"lo":545,"hi":740,"n":17,"rr":1366,"mr":631},{"m":"qwen3-vl-4b-instruct","r":661,"s":52.49,"lo":615,"hi":694,"n":113,"rr":638,"mr":654},{"m":"ling-2.6-1t-base","r":662,"s":52.49,"lo":585,"hi":754,"n":23,"rr":440,"mr":620},{"m":"gpt-4o-0513","r":663,"s":52.41,"lo":531,"hi":789,"n":11,"rr":45,"mr":759},{"m":"llama-3.1-tulu-3-405b-sft","r":664,"s":52.37,"lo":460,"hi":899,"n":9,"rr":81,"mr":682},{"m":"ling-mini-2.0","r":665,"s":52.36,"lo":600,"hi":751,"n":37,"rr":680,"mr":638},{"m":"mimo-embodied-7b","r":666,"s":52.34,"lo":563,"hi":776,"n":46,"rr":850,"mr":705},{"m":"qwen3-4b-instruct-2507","r":667,"s":52.3,"lo":621,"hi":760,"n":36,"rr":783,"mr":634},{"m":"marco-mini-instruct","r":668,"s":52.07,"lo":587,"hi":770,"n":15,"rr":138,"mr":653},{"m":"molmo-72b","r":669,"s":51.99,"lo":488,"hi":810,"n":21,"rr":105,"mr":750},{"m":"internvl2-pro","r":670,"s":51.89,"lo":594,"hi":752,"n":11,"rr":59,"mr":755},{"m":"mistral-medium-3","r":671,"s":51.87,"lo":553,"hi":777,"n":22,"rr":574,"mr":657},{"m":"molmo2-4b","r":672,"s":51.87,"lo":570,"hi":799,"n":44,"rr":421,"mr":727},{"m":"gpt-4o-2024-08-06","r":673,"s":51.82,"lo":599,"hi":751,"n":38,"rr":705,"mr":658},{"m":"deepseek-v3.2-base","r":674,"s":51.75,"lo":560,"hi":811,"n":22,"rr":95,"mr":659},{"m":"gpt-4o","r":675,"s":51.74,"lo":645,"hi":722,"n":144,"rr":955,"mr":663},{"m":"hunyuan-4b-instruct","r":676,"s":51.65,"lo":615,"hi":777,"n":11,"rr":1217,"mr":662},{"m":"medmo-4b-next","r":677,"s":51.61,"lo":576,"hi":788,"n":9,"rr":625,"mr":729},{"m":"qwq-32b-preview","r":678,"s":51.6,"lo":620,"hi":743,"n":9,"rr":990,"mr":678},{"m":"gpt-5-nano","r":679,"s":51.58,"lo":592,"hi":771,"n":76,"rr":1164,"mr":686},{"m":"gpt-4o-2024-11-20","r":680,"s":51.56,"lo":629,"hi":746,"n":19,"rr":1275,"mr":689},{"m":"qwen3-8b","r":681,"s":51.54,"lo":627,"hi":761,"n":73,"rr":1086,"mr":645},{"m":"gemini-3.1-flash-live","r":682,"s":51.51,"lo":307,"hi":1331,"n":17,"rr":761,"mr":744},{"m":"kanana-2-30b-a3b-instruct","r":683,"s":51.48,"lo":623,"hi":793,"n":14,"rr":369,"mr":655},{"m":"mistral-large-instruct-2407","r":684,"s":51.48,"lo":621,"hi":758,"n":24,"rr":315,"mr":660},{"m":"gpt-oss-120b-low","r":685,"s":51.47,"lo":597,"hi":830,"n":13,"rr":1325,"mr":685},{"m":"hy3-preview-base","r":686,"s":51.47,"lo":611,"hi":754,"n":33,"rr":342,"mr":656},{"m":"mimo-v2-flash-base","r":687,"s":51.31,"lo":614,"hi":765,"n":31,"rr":240,"mr":652},{"m":"llama-4-maverick","r":688,"s":51.3,"lo":617,"hi":767,"n":32,"rr":1356,"mr":676},{"m":"minicpm-v-4.5-8b","r":689,"s":51.25,"lo":636,"hi":763,"n":43,"rr":414,"mr":743},{"m":"qwen2.5-vl-32b-instruct","r":690,"s":51.23,"lo":590,"hi":765,"n":12,"rr":729,"mr":745},{"m":"molmo2-o-7b","r":691,"s":51.2,"lo":571,"hi":842,"n":30,"rr":306,"mr":758},{"m":"minicpm-o-4.5","r":692,"s":51.19,"lo":609,"hi":759,"n":43,"rr":266,"mr":692},{"m":"gpt-5-mini-minimal","r":693,"s":51.16,"lo":632,"hi":778,"n":49,"rr":936,"mr":711},{"m":"qwen2-vl-72b","r":694,"s":51.12,"lo":587,"hi":884,"n":39,"rr":283,"mr":738},{"m":"qwen2-vl-72b-instruct","r":695,"s":51.03,"lo":532,"hi":970,"n":28,"rr":238,"mr":757},{"m":"medix-r1-8b","r":696,"s":50.95,"lo":572,"hi":799,"n":9,"rr":785,"mr":753},{"m":"internvl3.5-gpt-oss-20b-a4b","r":697,"s":50.89,"lo":623,"hi":795,"n":15,"rr":63,"mr":760},{"m":"granite-4.1-30b","r":698,"s":50.83,"lo":640,"hi":769,"n":24,"rr":225,"mr":668},{"m":"gpt-4o-realtime-preview-2024-12-17","r":699,"s":50.83,"lo":348,"hi":858,"n":8,"rr":561,"mr":776},{"m":"gpt-4o-2024-05-13","r":700,"s":50.8,"lo":635,"hi":768,"n":88,"rr":565,"mr":683},{"m":"ministral-3-14b-instruct","r":701,"s":50.78,"lo":611,"hi":797,"n":19,"rr":676,"mr":666},{"m":"molmopoint-o-7b","r":702,"s":50.69,"lo":462,"hi":918,"n":14,"rr":134,"mr":766},{"m":"internvl2.5-38b","r":703,"s":50.65,"lo":619,"hi":833,"n":45,"rr":373,"mr":761},{"m":"llama-3.1-tulu-3-70b-dpo","r":704,"s":50.64,"lo":600,"hi":850,"n":11,"rr":118,"mr":715},{"m":"llama-3.1-tulu-3-70b","r":705,"s":50.64,"lo":606,"hi":842,"n":11,"rr":113,"mr":700},{"m":"hermes-3-llama-3.1-405b","r":706,"s":50.5,"lo":605,"hi":916,"n":10,"rr":102,"mr":710},{"m":"nemotron-3.5-super-vl-120b-a12b-base","r":707,"s":50.49,"lo":607,"hi":794,"n":22,"rr":73,"mr":670},{"m":"robobrain-2.5-4b","r":708,"s":50.38,"lo":509,"hi":929,"n":9,"rr":916,"mr":778},{"m":"stable-diffcoder-8b-instruct","r":709,"s":50.31,"lo":600,"hi":821,"n":8,"rr":777,"mr":712},{"m":"rnj-1","r":710,"s":50.31,"lo":632,"hi":781,"n":10,"rr":1053,"mr":688},{"m":"lfm2.5-2.6b","r":711,"s":50.25,"lo":617,"hi":831,"n":32,"rr":1362,"mr":669},{"m":"mellum2-12b-a2.5b-thinking","r":712,"s":50.25,"lo":511,"hi":1106,"n":14,"rr":824,"mr":673},{"m":"keye-vl-1.5-8b","r":713,"s":50.24,"lo":635,"hi":795,"n":32,"rr":338,"mr":781},{"m":"hunyuan-large","r":714,"s":50.21,"lo":588,"hi":822,"n":19,"rr":11,"mr":695},{"m":"trinity-mini","r":715,"s":50.19,"lo":657,"hi":866,"n":11,"rr":904,"mr":677},{"m":"gpt-4-1106-preview","r":716,"s":50.19,"lo":642,"hi":805,"n":29,"rr":271,"mr":694},{"m":"qwen2.5-72b-instruct","r":717,"s":50.16,"lo":636,"hi":769,"n":72,"rr":557,"mr":672},{"m":"nemotron-3-nano-4b-thinking","r":718,"s":50.15,"lo":612,"hi":860,"n":16,"rr":1343,"mr":681},{"m":"nemotron-3-nano-4b","r":719,"s":50.11,"lo":631,"hi":904,"n":32,"rr":1398,"mr":674},{"m":"llada2.1-mini-q","r":720,"s":50.03,"lo":635,"hi":813,"n":34,"rr":594,"mr":679},{"m":"youtu-vl-4b-instruct","r":721,"s":50.02,"lo":603,"hi":799,"n":37,"rr":296,"mr":731},{"m":"kimi-dev-72b","r":722,"s":49.99,"lo":603,"hi":810,"n":18,"rr":1127,"mr":707},{"m":"qwen3-4b","r":723,"s":49.9,"lo":627,"hi":837,"n":54,"rr":667,"mr":671},{"m":"qwen2.5-math-72b-instruct","r":724,"s":49.89,"lo":623,"hi":830,"n":10,"rr":386,"mr":735},{"m":"qwen3-235b-a22b-base","r":725,"s":49.89,"lo":648,"hi":803,"n":9,"rr":148,"mr":709},{"m":"holo1-7b","r":726,"s":49.86,"lo":609,"hi":869,"n":12,"rr":348,"mr":796},{"m":"olmo-3.1-instruct-32b-dpo","r":727,"s":49.78,"lo":648,"hi":796,"n":16,"rr":832,"mr":687},{"m":"qwen2.5-turbo","r":728,"s":49.76,"lo":684,"hi":772,"n":18,"rr":67,"mr":699},{"m":"gemini-2.0-flash-001","r":729,"s":49.73,"lo":540,"hi":845,"n":8,"rr":961,"mr":751},{"m":"qwen-3-235b-a22b-nonthinking","r":730,"s":49.67,"lo":548,"hi":804,"n":11,"rr":580,"mr":739},{"m":"amazon-nova-premier","r":731,"s":49.67,"lo":615,"hi":849,"n":13,"rr":1308,"mr":723},{"m":"gpt-oss-20b-moe","r":732,"s":49.55,"lo":652,"hi":1146,"n":8,"rr":1229,"mr":722},{"m":"gemini-1.5-pro-002","r":733,"s":49.52,"lo":660,"hi":808,"n":21,"rr":856,"mr":716},{"m":"dots.mocr","r":734,"s":49.52,"lo":573,"hi":860,"n":11,"rr":94,"mr":791},{"m":"pelican-vl-7b","r":735,"s":49.47,"lo":634,"hi":852,"n":13,"rr":590,"mr":798},{"m":"gpt-4-turbo-2024-04-09","r":736,"s":49.42,"lo":648,"hi":802,"n":46,"rr":463,"mr":701},{"m":"openpangu-r-7b-diffusion","r":737,"s":49.33,"lo":688,"hi":807,"n":9,"rr":40,"mr":706},{"m":"kat-dev-72b-exp","r":738,"s":49.32,"lo":659,"hi":841,"n":16,"rr":1215,"mr":728},{"m":"cosmos-reason2-8b","r":739,"s":49.18,"lo":651,"hi":809,"n":30,"rr":748,"mr":792},{"m":"alodlm-8b","r":740,"s":49.18,"lo":671,"hi":788,"n":11,"rr":28,"mr":703},{"m":"deepseek-v3.2-exp-base","r":741,"s":49.15,"lo":640,"hi":847,"n":29,"rr":142,"mr":718},{"m":"diffusiongemma-jev","r":742,"s":49.1,"lo":625,"hi":860,"n":26,"rr":567,"mr":737},{"m":"gemma-4-e4b-it","r":743,"s":49.09,"lo":677,"hi":806,"n":109,"rr":1207,"mr":698},{"m":"exaone-4.0-1.2b","r":744,"s":49,"lo":680,"hi":879,"n":12,"rr":1151,"mr":704},{"m":"qwen2.5-32b-instruct","r":745,"s":48.99,"lo":686,"hi":793,"n":54,"rr":419,"mr":697},{"m":"gpt-4-turbo","r":746,"s":48.94,"lo":641,"hi":860,"n":16,"rr":910,"mr":768},{"m":"telechat2-115b","r":747,"s":48.92,"lo":574,"hi":852,"n":8,"rr":8,"mr":770},{"m":"yi-lightning","r":748,"s":48.82,"lo":501,"hi":808,"n":8,"rr":472,"mr":732},{"m":"deepseek-v3-base","r":749,"s":48.81,"lo":634,"hi":841,"n":39,"rr":132,"mr":734},{"m":"glm-4.5-base","r":750,"s":48.8,"lo":664,"hi":824,"n":37,"rr":205,"mr":713},{"m":"ling-1t-base","r":751,"s":48.79,"lo":685,"hi":807,"n":23,"rr":663,"mr":714},{"m":"llama-3.1-405b-instruct","r":752,"s":48.7,"lo":634,"hi":829,"n":39,"rr":617,"mr":702},{"m":"qwen-turbo-0919","r":753,"s":48.59,"lo":718,"hi":789,"n":12,"rr":268,"mr":724},{"m":"kolibri-1-base","r":754,"s":48.59,"lo":588,"hi":861,"n":10,"rr":24,"mr":749},{"m":"kimi-vl-a3b-thinking-2506","r":755,"s":48.58,"lo":655,"hi":853,"n":36,"rr":1017,"mr":801},{"m":"gpt-4o-mini","r":756,"s":48.57,"lo":712,"hi":813,"n":45,"rr":550,"mr":742},{"m":"motif-3-base","r":757,"s":48.54,"lo":642,"hi":834,"n":10,"rr":16,"mr":736},{"m":"mage-vl","r":758,"s":48.54,"lo":655,"hi":858,"n":30,"rr":684,"mr":805},{"m":"exaone-deep-2.4b","r":759,"s":48.46,"lo":680,"hi":974,"n":11,"rr":1244,"mr":767},{"m":"llama-3.3-70b-instruct","r":760,"s":48.44,"lo":649,"hi":837,"n":26,"rr":605,"mr":748},{"m":"llada2.1-mini-s","r":761,"s":48.44,"lo":662,"hi":843,"n":34,"rr":687,"mr":717},{"m":"ling-2.5-flash-base","r":762,"s":48.38,"lo":686,"hi":836,"n":17,"rr":668,"mr":740},{"m":"gemma-3-27b","r":763,"s":48.36,"lo":645,"hi":849,"n":31,"rr":202,"mr":741},{"m":"rynnbrain-2b","r":764,"s":48.35,"lo":613,"hi":909,"n":13,"rr":437,"mr":817},{"m":"k2-v2","r":765,"s":48.26,"lo":612,"hi":1058,"n":19,"rr":430,"mr":708},{"m":"gpt-4-0613","r":766,"s":48.17,"lo":686,"hi":846,"n":10,"rr":311,"mr":795},{"m":"openreasoning-nemotron-1.5b","r":767,"s":48.15,"lo":689,"hi":1011,"n":11,"rr":1382,"mr":730},{"m":"mimo-v2.5-base","r":768,"s":48.06,"lo":679,"hi":852,"n":30,"rr":400,"mr":725},{"m":"gpt-realtime-2.1-mini","r":769,"s":48.02,"lo":267,"hi":861,"n":9,"rr":570,"mr":831},{"m":"llama-3.1-405b-instruct-fp8","r":770,"s":48.01,"lo":665,"hi":822,"n":9,"rr":243,"mr":775},{"m":"claude-3.5-haiku-20241022","r":771,"s":47.99,"lo":650,"hi":929,"n":16,"rr":1345,"mr":774},{"m":"deepseek-v2.5","r":772,"s":47.98,"lo":699,"hi":815,"n":41,"rr":691,"mr":721},{"m":"videochat-flash-7b","r":773,"s":47.93,"lo":653,"hi":883,"n":13,"rr":674,"mr":827},{"m":"qwen2.5-14b-instruct","r":774,"s":47.89,"lo":724,"hi":826,"n":31,"rr":267,"mr":746},{"m":"llada2.0-mini","r":775,"s":47.84,"lo":686,"hi":846,"n":40,"rr":838,"mr":720},{"m":"minicpm-v-4.6-thinking","r":776,"s":47.81,"lo":689,"hi":850,"n":21,"rr":673,"mr":814},{"m":"plm-8b","r":777,"s":47.81,"lo":650,"hi":933,"n":29,"rr":496,"mr":826},{"m":"lfm2.5-8b-a1b","r":778,"s":47.75,"lo":684,"hi":872,"n":32,"rr":1408,"mr":733},{"m":"granite-4.1-8b","r":779,"s":47.71,"lo":710,"hi":829,"n":24,"rr":379,"mr":752},{"m":"gemini-1.5-pro","r":780,"s":47.63,"lo":695,"hi":849,"n":85,"rr":693,"mr":771},{"m":"gpt-5.4-mini-none","r":781,"s":47.61,"lo":587,"hi":894,"n":14,"rr":1357,"mr":777},{"m":"qwen3-swallow-8b-cpt-v0.2","r":782,"s":47.52,"lo":724,"hi":828,"n":10,"rr":626,"mr":756},{"m":"gpt-realtime-mini","r":783,"s":47.51,"lo":233,"hi":888,"n":9,"rr":562,"mr":838},{"m":"step-3.5-flash-base","r":784,"s":47.5,"lo":714,"hi":835,"n":33,"rr":511,"mr":754},{"m":"deepseek-coder-v2-instruct","r":785,"s":47.5,"lo":720,"hi":835,"n":41,"rr":760,"mr":747},{"m":"nemotron-3-nano-30b-a3b-base","r":786,"s":47.38,"lo":707,"hi":831,"n":22,"rr":44,"mr":763},{"m":"deepseek-v2-chat-0628","r":787,"s":47.34,"lo":721,"hi":825,"n":15,"rr":507,"mr":773},{"m":"step-3.5-flash-base-midtrain","r":788,"s":47.27,"lo":702,"hi":863,"n":20,"rr":282,"mr":772},{"m":"mistral-3.2-24b","r":789,"s":47.23,"lo":675,"hi":859,"n":13,"rr":52,"mr":764},{"m":"qwen2-math-72b-instruct","r":790,"s":47.22,"lo":653,"hi":894,"n":10,"rr":599,"mr":816},{"m":"joyai-llm-flash-base","r":791,"s":47.14,"lo":707,"hi":858,"n":8,"rr":82,"mr":765},{"m":"mistral-small-3.2-24b-instruct","r":792,"s":47.12,"lo":702,"hi":858,"n":21,"rr":533,"mr":784},{"m":"minicpm-v-4.7-1b","r":793,"s":47.09,"lo":689,"hi":861,"n":20,"rr":727,"mr":825},{"m":"qwen3.5-35b-a3b-base","r":794,"s":47.08,"lo":649,"hi":861,"n":21,"rr":232,"mr":780},{"m":"lingshu-7b","r":795,"s":47.05,"lo":654,"hi":904,"n":9,"rr":869,"mr":836},{"m":"qwen2.5-coder-32b-instruct","r":796,"s":47.04,"lo":702,"hi":871,"n":38,"rr":939,"mr":769},{"m":"deepseek-v3.1-base","r":797,"s":47.04,"lo":680,"hi":885,"n":20,"rr":249,"mr":785},{"m":"mistral-small-3.1-24b-instruct","r":798,"s":46.96,"lo":751,"hi":860,"n":17,"rr":670,"mr":800},{"m":"deepseek-coder-v2-instruct-0724","r":799,"s":46.94,"lo":727,"hi":844,"n":11,"rr":928,"mr":794},{"m":"gpt-4o-mini-2024-07-18","r":800,"s":46.89,"lo":711,"hi":869,"n":33,"rr":927,"mr":789},{"m":"claude-3-opus-20240229","r":801,"s":46.88,"lo":672,"hi":857,"n":25,"rr":868,"mr":790},{"m":"ling-2.6-flash-base","r":802,"s":46.85,"lo":739,"hi":858,"n":23,"rr":798,"mr":762},{"m":"telechat2-35b","r":803,"s":46.68,"lo":595,"hi":894,"n":8,"rr":13,"mr":809},{"m":"k2-horizon-0.9b","r":804,"s":46.64,"lo":745,"hi":927,"n":8,"rr":1302,"mr":788},{"m":"llama-3.1-tulu-3-70b-sft","r":805,"s":46.64,"lo":647,"hi":960,"n":11,"rr":223,"mr":820},{"m":"qwen3-8b-non-thinking","r":806,"s":46.63,"lo":731,"hi":832,"n":44,"rr":775,"mr":779},{"m":"seed1.5","r":807,"s":46.62,"lo":687,"hi":876,"n":8,"rr":230,"mr":803},{"m":"deepseek-vl2","r":808,"s":46.62,"lo":719,"hi":873,"n":18,"rr":43,"mr":852},{"m":"vllm-sr-decision-2.0-lux-9b","r":809,"s":46.6,"lo":668,"hi":900,"n":28,"rr":811,"mr":799},{"m":"internvl3.5-8b","r":810,"s":46.58,"lo":735,"hi":857,"n":80,"rr":731,"mr":829},{"m":"qwen3-32b-nothinking","r":811,"s":46.57,"lo":709,"hi":847,"n":29,"rr":1120,"mr":782},{"m":"manzano-3b","r":812,"s":46.46,"lo":712,"hi":910,"n":12,"rr":49,"mr":850},{"m":"mistral-large-2411","r":813,"s":46.44,"lo":710,"hi":934,"n":10,"rr":1227,"mr":823},{"m":"glm-4v-plus","r":814,"s":46.36,"lo":715,"hi":869,"n":13,"rr":120,"mr":866},{"m":"llama-3.1-70b-instruct","r":815,"s":46.3,"lo":739,"hi":850,"n":54,"rr":478,"mr":786},{"m":"k2-low-70b","r":816,"s":46.27,"lo":706,"hi":849,"n":9,"rr":952,"mr":783},{"m":"fanar-2-27b-instruct","r":817,"s":46.25,"lo":603,"hi":1020,"n":9,"rr":1208,"mr":815},{"m":"gpt-4","r":818,"s":46,"lo":739,"hi":892,"n":36,"rr":171,"mr":806},{"m":"qwen2.5-math-7b-instruct","r":819,"s":45.98,"lo":701,"hi":921,"n":10,"rr":702,"mr":834},{"m":"nemotron-3.5-lightning-30b-a3b-base","r":820,"s":45.87,"lo":713,"hi":868,"n":19,"rr":125,"mr":804},{"m":"gemma-3-27b-it","r":821,"s":45.86,"lo":753,"hi":850,"n":83,"rr":866,"mr":793},{"m":"fastvlm-7b","r":822,"s":45.84,"lo":639,"hi":977,"n":11,"rr":58,"mr":871},{"m":"llama-4-scout-17b","r":823,"s":45.8,"lo":735,"hi":879,"n":28,"rr":640,"mr":787},{"m":"mellum2-12b-a2.5b-instruct","r":824,"s":45.79,"lo":764,"hi":881,"n":11,"rr":527,"mr":797},{"m":"kimi-vl-a3b-thinking","r":825,"s":45.74,"lo":682,"hi":976,"n":12,"rr":275,"mr":858},{"m":"qwen3-8b-instruct","r":826,"s":45.53,"lo":769,"hi":866,"n":10,"rr":65,"mr":813},{"m":"kanana-1.5-32.5b-instruct","r":827,"s":45.52,"lo":769,"hi":948,"n":14,"rr":688,"mr":818},{"m":"medmo-4b","r":828,"s":45.34,"lo":706,"hi":937,"n":9,"rr":1067,"mr":855},{"m":"llama-3.1-70b","r":829,"s":45.32,"lo":682,"hi":1073,"n":25,"rr":424,"mr":812},{"m":"bagel-7b-mot","r":830,"s":45.25,"lo":733,"hi":930,"n":19,"rr":405,"mr":867},{"m":"llada2.2-mini","r":831,"s":45.22,"lo":646,"hi":923,"n":13,"rr":1204,"mr":819},{"m":"holo1-3b","r":832,"s":45.19,"lo":710,"hi":999,"n":10,"rr":522,"mr":884},{"m":"qwen2-72b-instruct","r":833,"s":45.14,"lo":790,"hi":890,"n":38,"rr":513,"mr":811},{"m":"internvl2-llama-3-76b","r":834,"s":45.14,"lo":741,"hi":956,"n":52,"rr":385,"mr":859},{"m":"mistral-large-3-base","r":835,"s":45.04,"lo":742,"hi":919,"n":24,"rr":292,"mr":807},{"m":"glm-4-0520","r":836,"s":44.99,"lo":752,"hi":907,"n":9,"rr":187,"mr":833},{"m":"qwen-2.5-72b","r":837,"s":44.9,"lo":761,"hi":888,"n":43,"rr":260,"mr":802},{"m":"hermes-3-llama-3.1-70b","r":838,"s":44.88,"lo":718,"hi":1025,"n":12,"rr":241,"mr":847},{"m":"medgemma-1.5-4b-it","r":839,"s":44.77,"lo":699,"hi":917,"n":8,"rr":915,"mr":875},{"m":"llama-3.3-70b","r":840,"s":44.74,"lo":678,"hi":930,"n":31,"rr":587,"mr":808},{"m":"autotrust-jev-9b","r":841,"s":44.72,"lo":720,"hi":950,"n":27,"rr":844,"mr":832},{"m":"kimi-vl-a3b-instruct","r":842,"s":44.68,"lo":683,"hi":957,"n":12,"rr":341,"mr":889},{"m":"minicpm-v-4.6","r":843,"s":44.64,"lo":775,"hi":890,"n":31,"rr":766,"mr":870},{"m":"llada2.0-flash-preview","r":844,"s":44.64,"lo":783,"hi":880,"n":23,"rr":497,"mr":810},{"m":"llada2.1-mini","r":845,"s":44.61,"lo":672,"hi":916,"n":11,"rr":1294,"mr":824},{"m":"nvlm-d-72b","r":846,"s":44.56,"lo":752,"hi":911,"n":12,"rr":177,"mr":916},{"m":"gemini-1.5-flash","r":847,"s":44.55,"lo":788,"hi":878,"n":35,"rr":631,"mr":828},{"m":"llava-onevision-2-8b","r":848,"s":44.45,"lo":764,"hi":934,"n":14,"rr":1118,"mr":877},{"m":"fleming-vl-8b","r":849,"s":44.31,"lo":628,"hi":1006,"n":9,"rr":913,"mr":902},{"m":"wedlm-8b-instruct","r":850,"s":44.26,"lo":805,"hi":886,"n":12,"rr":107,"mr":821},{"m":"qwen2.5-vl-7b","r":851,"s":44.21,"lo":779,"hi":920,"n":70,"rr":1003,"mr":876},{"m":"zaya1-vl-8b","r":852,"s":44.2,"lo":737,"hi":955,"n":16,"rr":145,"mr":897},{"m":"skywork-o1-open-llama-3.1-8b","r":853,"s":44.14,"lo":786,"hi":940,"n":10,"rr":717,"mr":839},{"m":"moss-vl-realtime","r":854,"s":44.13,"lo":672,"hi":1028,"n":13,"rr":1100,"mr":899},{"m":"deepseek-r1-distill-qwen-7b","r":855,"s":44.07,"lo":718,"hi":1137,"n":23,"rr":1259,"mr":841},{"m":"deepseek-vl2-small","r":856,"s":44.03,"lo":784,"hi":934,"n":18,"rr":61,"mr":919},{"m":"sdar-8b-chat","r":857,"s":43.97,"lo":791,"hi":916,"n":9,"rr":136,"mr":845},{"m":"internvl3.5-4b","r":858,"s":43.8,"lo":797,"hi":908,"n":69,"rr":710,"mr":890},{"m":"ling-flash-base-2.0","r":859,"s":43.79,"lo":816,"hi":901,"n":38,"rr":646,"mr":830},{"m":"qwen2.5-coder-14b-instruct","r":860,"s":43.76,"lo":771,"hi":953,"n":31,"rr":1159,"mr":846},{"m":"llama-3.1-nemotron-70b","r":861,"s":43.64,"lo":608,"hi":980,"n":11,"rr":201,"mr":854},{"m":"mellum2-12b-a2.5b-thinking-sft","r":862,"s":43.62,"lo":518,"hi":991,"n":9,"rr":509,"mr":844},{"m":"plm-3b","r":863,"s":43.59,"lo":739,"hi":998,"n":29,"rr":577,"mr":924},{"m":"midm-2.0-base-instruct","r":864,"s":43.5,"lo":744,"hi":970,"n":8,"rr":346,"mr":842},{"m":"internvl-8b","r":865,"s":43.43,"lo":800,"hi":924,"n":39,"rr":480,"mr":879},{"m":"minicpm5-1b","r":866,"s":43.39,"lo":779,"hi":1027,"n":21,"rr":1304,"mr":822},{"m":"llama-4-maverick-base","r":867,"s":43.3,"lo":801,"hi":921,"n":14,"rr":350,"mr":853},{"m":"nemotron-labs-twotower-30b-a3b-base","r":868,"s":43.29,"lo":831,"hi":908,"n":11,"rr":36,"mr":849},{"m":"granite-4.0-h-small","r":869,"s":43.17,"lo":807,"hi":956,"n":33,"rr":636,"mr":835},{"m":"higgs-realtime","r":870,"s":43.14,"lo":253,"hi":1063,"n":8,"rr":672,"mr":937},{"m":"qwen3-30b-a3b-base","r":871,"s":43.07,"lo":844,"hi":928,"n":25,"rr":403,"mr":851},{"m":"internvl2.5-26b","r":872,"s":43.06,"lo":770,"hi":969,"n":60,"rr":358,"mr":864},{"m":"gemma-3-12b-it","r":873,"s":42.96,"lo":813,"hi":933,"n":61,"rr":925,"mr":840},{"m":"bagel-14b","r":874,"s":42.94,"lo":727,"hi":1054,"n":11,"rr":108,"mr":938},{"m":"medgemma-4b-it","r":875,"s":42.89,"lo":755,"hi":956,"n":8,"rr":934,"mr":927},{"m":"lfm2.5-vl-3b","r":876,"s":42.88,"lo":800,"hi":941,"n":30,"rr":504,"mr":907},{"m":"bespoke-nimble-9b-v2","r":877,"s":42.85,"lo":731,"hi":1020,"n":27,"rr":906,"mr":860},{"m":"llava-onevision-72b","r":878,"s":42.79,"lo":809,"hi":932,"n":35,"rr":457,"mr":935},{"m":"olmo-3-instruct-7b","r":879,"s":42.76,"lo":797,"hi":961,"n":36,"rr":938,"mr":837},{"m":"yi-coder-9b-chat","r":880,"s":42.74,"lo":825,"hi":979,"n":13,"rr":1136,"mr":861},{"m":"gpt-4.1-nano","r":881,"s":42.71,"lo":780,"hi":975,"n":16,"rr":1372,"mr":881},{"m":"qwen2-math-7b-instruct","r":882,"s":42.67,"lo":809,"hi":968,"n":10,"rr":893,"mr":891},{"m":"smollm3-3b","r":883,"s":42.65,"lo":812,"hi":970,"n":47,"rr":1109,"mr":843},{"m":"d1-3b","r":884,"s":42.5,"lo":719,"hi":996,"n":39,"rr":633,"mr":872},{"m":"gemini-1.0-ultra","r":885,"s":42.48,"lo":708,"hi":999,"n":9,"rr":111,"mr":950},{"m":"penguin-vl-2b","r":886,"s":42.45,"lo":741,"hi":981,"n":20,"rr":665,"mr":931},{"m":"robobrain-2.0","r":887,"s":42.45,"lo":762,"hi":1032,"n":14,"rr":629,"mr":948},{"m":"gemini-1.5-flash-002","r":888,"s":42.33,"lo":822,"hi":977,"n":17,"rr":985,"mr":882},{"m":"magicoder-s-ds-6.7b","r":889,"s":42.27,"lo":841,"hi":1016,"n":10,"rr":877,"mr":893},{"m":"deepseek-v2-chat-sft","r":890,"s":42.18,"lo":826,"hi":960,"n":20,"rr":216,"mr":856},{"m":"falcon-h1-34b-instruct","r":891,"s":42.17,"lo":828,"hi":991,"n":26,"rr":1009,"mr":848},{"m":"qwen2-vl-7b-instruct","r":892,"s":42.15,"lo":801,"hi":1021,"n":27,"rr":438,"mr":947},{"m":"claude-3-sonnet-20240229","r":893,"s":42.1,"lo":823,"hi":951,"n":14,"rr":566,"mr":892},{"m":"trinity-large-base","r":894,"s":42.08,"lo":722,"hi":1070,"n":11,"rr":114,"mr":869},{"m":"kimi-audio-7b-instruct","r":895,"s":42.05,"lo":719,"hi":977,"n":9,"rr":666,"mr":944},{"m":"ministral-3-8b-instruct","r":896,"s":42.02,"lo":766,"hi":974,"n":17,"rr":622,"mr":873},{"m":"glm-4-air-0605","r":897,"s":42.01,"lo":839,"hi":951,"n":9,"rr":285,"mr":883},{"m":"minicpm4-8b","r":898,"s":42,"lo":831,"hi":972,"n":11,"rr":22,"mr":898},{"m":"infinity-parser2-flash","r":899,"s":41.96,"lo":794,"hi":1001,"n":11,"rr":109,"mr":942},{"m":"qwen3-vl-2b-thinking","r":900,"s":41.9,"lo":822,"hi":975,"n":38,"rr":1135,"mr":933},{"m":"internvl2-40b","r":901,"s":41.88,"lo":813,"hi":1063,"n":45,"rr":609,"mr":952},{"m":"codestral-22b-v0.1","r":902,"s":41.87,"lo":868,"hi":949,"n":12,"rr":953,"mr":887},{"m":"deepslate-opal","r":903,"s":41.83,"lo":555,"hi":1178,"n":8,"rr":771,"mr":978},{"m":"gemma-4-e2b-it","r":904,"s":41.82,"lo":837,"hi":980,"n":100,"rr":1306,"mr":862},{"m":"qwen2.5-32b-base","r":905,"s":41.77,"lo":806,"hi":1034,"n":26,"rr":173,"mr":863},{"m":"llama-3.2v-90b-instruct","r":906,"s":41.76,"lo":812,"hi":962,"n":16,"rr":233,"mr":980},{"m":"llava-video-7b","r":907,"s":41.68,"lo":838,"hi":999,"n":13,"rr":887,"mr":989},{"m":"llama-3-70b","r":908,"s":41.66,"lo":802,"hi":1024,"n":24,"rr":546,"mr":857},{"m":"gpt-4-0314","r":909,"s":41.63,"lo":825,"hi":963,"n":11,"rr":407,"mr":936},{"m":"qwen2.5-math-1.5b-instruct","r":910,"s":41.62,"lo":819,"hi":1032,"n":10,"rr":974,"mr":930},{"m":"olmo-3-instruct-7b-dpo","r":911,"s":41.62,"lo":849,"hi":986,"n":17,"rr":1261,"mr":865},{"m":"ling-3.0-tiny-base","r":912,"s":41.61,"lo":842,"hi":970,"n":17,"rr":989,"mr":874},{"m":"lfm2.5-1.2b-jp-202606","r":913,"s":41.61,"lo":761,"hi":1017,"n":10,"rr":1117,"mr":923},{"m":"llada2.0-mini-preview","r":914,"s":41.59,"lo":853,"hi":977,"n":9,"rr":213,"mr":878},{"m":"yi-large-preview","r":915,"s":41.56,"lo":761,"hi":955,"n":9,"rr":545,"mr":913},{"m":"claude-3-opus","r":916,"s":41.53,"lo":812,"hi":1028,"n":51,"rr":531,"mr":894},{"m":"seed-coder-8b-instruct","r":917,"s":41.53,"lo":834,"hi":981,"n":27,"rr":1270,"mr":895},{"m":"opencoder-8b-instruct","r":918,"s":41.49,"lo":820,"hi":983,"n":12,"rr":1212,"mr":914},{"m":"hy-1.8b","r":919,"s":41.38,"lo":600,"hi":1139,"n":8,"rr":383,"mr":904},{"m":"ouro-2.6b","r":920,"s":41.29,"lo":790,"hi":1018,"n":12,"rr":103,"mr":885},{"m":"phi-3.5-moe-instruct","r":921,"s":41.29,"lo":858,"hi":971,"n":12,"rr":191,"mr":905},{"m":"apertus-v1.5-70b-thinking","r":922,"s":41.24,"lo":875,"hi":987,"n":8,"rr":1121,"mr":880},{"m":"qwen2-72b","r":923,"s":41.23,"lo":834,"hi":988,"n":24,"rr":234,"mr":868},{"m":"vllm-sr-decision-2.0-nox-4b","r":924,"s":41.17,"lo":792,"hi":1028,"n":27,"rr":908,"mr":908},{"m":"internvl3-8b","r":925,"s":41.12,"lo":854,"hi":1051,"n":11,"rr":1114,"mr":968},{"m":"qwen2.5-coder-32b","r":926,"s":41.07,"lo":846,"hi":986,"n":19,"rr":453,"mr":901},{"m":"olmo-3.1-instruct-32b-sft","r":927,"s":41.03,"lo":839,"hi":993,"n":16,"rr":1228,"mr":888},{"m":"mellum2-12b-a2.5b-instruct-sft","r":928,"s":40.93,"lo":873,"hi":1005,"n":11,"rr":839,"mr":886},{"m":"motif-2-12.7b-base","r":929,"s":40.91,"lo":815,"hi":1003,"n":23,"rr":313,"mr":900},{"m":"kev-9b","r":930,"s":40.88,"lo":815,"hi":1041,"n":26,"rr":966,"mr":920},{"m":"apertus-v1.5-8b-thinking","r":931,"s":40.84,"lo":888,"hi":987,"n":8,"rr":1106,"mr":896},{"m":"llama-3.1-405b-base","r":932,"s":40.65,"lo":831,"hi":1005,"n":35,"rr":143,"mr":906},{"m":"deepseek-coder-33b-instruct","r":933,"s":40.51,"lo":890,"hi":990,"n":21,"rr":1315,"mr":932},{"m":"deepseek-v2-chat","r":934,"s":40.47,"lo":861,"hi":994,"n":37,"rr":821,"mr":903},{"m":"glm-4.5-air-base","r":935,"s":40.35,"lo":842,"hi":1001,"n":26,"rr":476,"mr":912},{"m":"internlm2_5-20b-chat","r":936,"s":40.25,"lo":863,"hi":1004,"n":17,"rr":227,"mr":910},{"m":"ling-2.5-mini-base","r":937,"s":40.23,"lo":880,"hi":979,"n":17,"rr":1044,"mr":918},{"m":"cosmos-reason1-7b","r":938,"s":40.22,"lo":857,"hi":1084,"n":16,"rr":1327,"mr":995},{"m":"llama-3-70b-instruct","r":939,"s":40.21,"lo":881,"hi":987,"n":44,"rr":897,"mr":911},{"m":"codegeex4-all-9b","r":940,"s":40.19,"lo":855,"hi":1032,"n":8,"rr":1220,"mr":959},{"m":"qwen3.5-2b","r":941,"s":40.15,"lo":875,"hi":1012,"n":133,"rr":1183,"mr":917},{"m":"qwen2.5-vl-3b","r":942,"s":40.15,"lo":881,"hi":994,"n":32,"rr":541,"mr":1001},{"m":"jina-vlm-2.4b-20251117","r":943,"s":40.13,"lo":870,"hi":982,"n":9,"rr":183,"mr":999},{"m":"qwen2.5-7b-instruct","r":944,"s":40.13,"lo":871,"hi":994,"n":53,"rr":986,"mr":915},{"m":"kimi-linear-base","r":945,"s":40.07,"lo":909,"hi":975,"n":15,"rr":699,"mr":921},{"m":"molmo-7b-d","r":946,"s":39.94,"lo":728,"hi":1078,"n":22,"rr":258,"mr":1022},{"m":"kanana-2-30b-a3b-mid-2601","r":947,"s":39.91,"lo":861,"hi":1004,"n":15,"rr":188,"mr":928},{"m":"kanana-2-30b-a3b-base","r":948,"s":39.91,"lo":860,"hi":1003,"n":15,"rr":189,"mr":929},{"m":"qwen2-vl-7b","r":949,"s":39.89,"lo":829,"hi":1035,"n":49,"rr":571,"mr":1005},{"m":"deepseek-r1-distill-llama-8b","r":950,"s":39.84,"lo":828,"hi":1122,"n":30,"rr":1108,"mr":922},{"m":"numinamath-72b-cot","r":951,"s":39.83,"lo":859,"hi":1135,"n":10,"rr":1083,"mr":963},{"m":"mixtral-8x22b-instruct-v0.1","r":952,"s":39.72,"lo":907,"hi":997,"n":32,"rr":461,"mr":909},{"m":"llada2.0-uni","r":953,"s":39.56,"lo":896,"hi":1001,"n":19,"rr":525,"mr":1003},{"m":"llama-3.1-tulu-3-8b","r":954,"s":39.52,"lo":859,"hi":1050,"n":11,"rr":624,"mr":955},{"m":"claude-3-sonnet","r":955,"s":39.4,"lo":842,"hi":1121,"n":22,"rr":537,"mr":998},{"m":"gpt-5-nano-minimal","r":956,"s":39.39,"lo":878,"hi":1085,"n":43,"rr":1360,"mr":953},{"m":"codestral-22b","r":957,"s":39.25,"lo":897,"hi":1057,"n":17,"rr":1268,"mr":982},{"m":"internvl2.5-8b","r":958,"s":39.22,"lo":879,"hi":1049,"n":63,"rr":452,"mr":967},{"m":"qwen2.5-14b","r":959,"s":39.18,"lo":896,"hi":1057,"n":18,"rr":442,"mr":925},{"m":"granite-4.1-3b","r":960,"s":39.13,"lo":899,"hi":1023,"n":24,"rr":836,"mr":934},{"m":"telechat2-7b","r":961,"s":39.11,"lo":821,"hi":1094,"n":8,"rr":99,"mr":985},{"m":"gemma-2-27b-it","r":962,"s":39,"lo":896,"hi":1035,"n":36,"rr":1038,"mr":926},{"m":"xverse-moe-a36b","r":963,"s":38.95,"lo":842,"hi":1097,"n":9,"rr":126,"mr":977},{"m":"qwen3-vl-2b-instruct","r":964,"s":38.8,"lo":886,"hi":1032,"n":88,"rr":996,"mr":988},{"m":"lfm2-24b-a2b","r":965,"s":38.79,"lo":859,"hi":1045,"n":15,"rr":722,"mr":957},{"m":"amazon-nova-pro-v1.0","r":966,"s":38.76,"lo":783,"hi":1048,"n":10,"rr":1351,"mr":946},{"m":"hy-1.8b-2bit","r":967,"s":38.74,"lo":656,"hi":1224,"n":8,"rr":604,"mr":975},{"m":"olmo-hybrid-instruct-7b-dpo","r":968,"s":38.67,"lo":866,"hi":1045,"n":15,"rr":1323,"mr":939},{"m":"qwen2.5-coder-14b","r":969,"s":38.66,"lo":910,"hi":1039,"n":19,"rr":603,"mr":951},{"m":"gpt-4v","r":970,"s":38.58,"lo":884,"hi":1032,"n":50,"rr":644,"mr":1015},{"m":"marco-nano-instruct","r":971,"s":38.55,"lo":860,"hi":1078,"n":15,"rr":743,"mr":965},{"m":"qwen3-8b-base","r":972,"s":38.49,"lo":940,"hi":1010,"n":34,"rr":581,"mr":954},{"m":"robobrain-2.0-7b","r":973,"s":38.48,"lo":837,"hi":1173,"n":13,"rr":959,"mr":1036},{"m":"hy-1.8b-int4gptq","r":974,"s":38.45,"lo":749,"hi":1174,"n":8,"rr":597,"mr":973},{"m":"intern-decision-4b","r":975,"s":38.38,"lo":865,"hi":1090,"n":28,"rr":984,"mr":964},{"m":"lfm2.5-1.2b-thinking","r":976,"s":38.32,"lo":885,"hi":1101,"n":21,"rr":1378,"mr":941},{"m":"qwen3.5-9b-base","r":977,"s":38.31,"lo":873,"hi":1056,"n":22,"rr":982,"mr":966},{"m":"tev1-4b-experimental","r":978,"s":38.31,"lo":868,"hi":1094,"n":25,"rr":981,"mr":969},{"m":"kanana-1.5-32.5b-base","r":979,"s":38.28,"lo":858,"hi":1064,"n":15,"rr":235,"mr":987},{"m":"llama-3.1-tulu-3-8b-dpo","r":980,"s":38.25,"lo":874,"hi":1071,"n":11,"rr":657,"mr":996},{"m":"deepseek-coder-v2-base","r":981,"s":38.23,"lo":881,"hi":1118,"n":16,"rr":744,"mr":979},{"m":"qwen3-1.7b","r":982,"s":38.21,"lo":916,"hi":1079,"n":72,"rr":1211,"mr":943},{"m":"llm-jp-4-vl-9b","r":983,"s":38.19,"lo":885,"hi":1117,"n":16,"rr":859,"mr":1010},{"m":"falcon-h1-7b","r":984,"s":38.19,"lo":928,"hi":1070,"n":26,"rr":1167,"mr":940},{"m":"plamo-3.0-prime","r":985,"s":38.19,"lo":882,"hi":1027,"n":8,"rr":1444,"mr":945},{"m":"qwen2-math-1.5b-instruct","r":986,"s":38.13,"lo":893,"hi":1137,"n":10,"rr":1143,"mr":1017},{"m":"vllm-sr-d3-nano","r":987,"s":38.12,"lo":847,"hi":1098,"n":27,"rr":979,"mr":970},{"m":"gemma-3-27b-vl","r":988,"s":38.11,"lo":890,"hi":1094,"n":35,"rr":1267,"mr":1040},{"m":"qwen2-57b-a14b-instruct","r":989,"s":38.1,"lo":946,"hi":1051,"n":19,"rr":803,"mr":961},{"m":"solar-pro-preview","r":990,"s":38.06,"lo":896,"hi":1141,"n":11,"rr":334,"mr":994},{"m":"claude-3-haiku-20240307","r":991,"s":37.96,"lo":940,"hi":1039,"n":16,"rr":1142,"mr":983},{"m":"qwen3-1.7b-thinking","r":992,"s":37.96,"lo":921,"hi":1078,"n":27,"rr":1291,"mr":974},{"m":"internlm2.5-7b-chat","r":993,"s":37.92,"lo":929,"hi":1049,"n":19,"rr":591,"mr":956},{"m":"kanana-1.5-o-9.8b-instruct-2602","r":994,"s":37.86,"lo":790,"hi":1156,"n":19,"rr":977,"mr":1034},{"m":"qwen1.5-110b-chat","r":995,"s":37.84,"lo":922,"hi":1044,"n":19,"rr":948,"mr":949},{"m":"qwen2.5-coder-7b-instruct","r":996,"s":37.79,"lo":905,"hi":1056,"n":38,"rr":1338,"mr":972},{"m":"qwen1.5-72b-chat","r":997,"s":37.75,"lo":944,"hi":1035,"n":37,"rr":660,"mr":958},{"m":"phi-4-reasoning-vision-15b","r":998,"s":37.74,"lo":845,"hi":1105,"n":23,"rr":678,"mr":1045},{"m":"gemini-2.5-flash-native-audio-preview-12-2025","r":999,"s":37.73,"lo":695,"hi":1468,"n":8,"rr":1446,"mr":1054},{"m":"mm1.5-30b","r":1000,"s":37.71,"lo":887,"hi":1093,"n":11,"rr":165,"mr":1065},{"m":"mobilellm-r1-950m","r":1001,"s":37.66,"lo":920,"hi":1128,"n":8,"rr":1352,"mr":962},{"m":"kanana-2-30b-a3b-base-2601","r":1002,"s":37.43,"lo":903,"hi":1068,"n":15,"rr":239,"mr":990},{"m":"deepseek-math-7b-rl","r":1003,"s":37.4,"lo":925,"hi":1119,"n":8,"rr":1095,"mr":1025},{"m":"qwen2.5-7b","r":1004,"s":37.38,"lo":970,"hi":1043,"n":41,"rr":835,"mr":960},{"m":"internlm2-math-plus-20b","r":1005,"s":37.36,"lo":931,"hi":1108,"n":10,"rr":1157,"mr":1020},{"m":"apertus-v1.5-70b","r":1006,"s":37.33,"lo":930,"hi":1051,"n":18,"rr":538,"mr":976},{"m":"gpt-3.5-turbo-1106","r":1007,"s":37.27,"lo":906,"hi":1198,"n":10,"rr":742,"mr":1039},{"m":"deepseek-v2","r":1008,"s":37.17,"lo":919,"hi":1084,"n":35,"rr":289,"mr":986},{"m":"qwen3.5-4b-base","r":1009,"s":37.15,"lo":931,"hi":1085,"n":32,"rr":551,"mr":992},{"m":"olmo-3-32b","r":1010,"s":37.1,"lo":862,"hi":1098,"n":14,"rr":302,"mr":1006},{"m":"lfm2-8b-a1b","r":1011,"s":37.05,"lo":953,"hi":1078,"n":33,"rr":1262,"mr":981},{"m":"qwen1.5-110b","r":1012,"s":37,"lo":934,"hi":1086,"n":17,"rr":477,"mr":984},{"m":"yi-1.5-34b-chat","r":1013,"s":36.91,"lo":954,"hi":1061,"n":15,"rr":1042,"mr":997},{"m":"bitcpm-cann-8b","r":1014,"s":36.9,"lo":956,"hi":1067,"n":11,"rr":51,"mr":1011},{"m":"hrm-text-1b","r":1015,"s":36.83,"lo":949,"hi":1098,"n":8,"rr":152,"mr":1013},{"m":"falcon-h1-1.5b-deep","r":1016,"s":36.83,"lo":966,"hi":1091,"n":23,"rr":1102,"mr":971},{"m":"granite-4.0-h-micro","r":1017,"s":36.82,"lo":939,"hi":1087,"n":23,"rr":905,"mr":1000},{"m":"glm-4-9b-chat","r":1018,"s":36.7,"lo":984,"hi":1053,"n":21,"rr":619,"mr":991},{"m":"glm4-9b","r":1019,"s":36.6,"lo":959,"hi":1075,"n":18,"rr":367,"mr":1004},{"m":"internvl2.5-4b","r":1020,"s":36.59,"lo":936,"hi":1153,"n":45,"rr":773,"mr":1080},{"m":"pixtral-12b","r":1021,"s":36.59,"lo":917,"hi":1123,"n":18,"rr":553,"mr":1092},{"m":"granite-3.3-8b-instruct","r":1022,"s":36.48,"lo":927,"hi":1089,"n":23,"rr":1087,"mr":1002},{"m":"mistral-large-2402","r":1023,"s":36.42,"lo":918,"hi":1104,"n":8,"rr":931,"mr":1038},{"m":"gpt-4-1106-vision-preview","r":1024,"s":36.22,"lo":947,"hi":1112,"n":21,"rr":387,"mr":1106},{"m":"llama-3.1-70b-base","r":1025,"s":36.21,"lo":889,"hi":1101,"n":13,"rr":76,"mr":1027},{"m":"amazon-nova-lite-v1.0","r":1026,"s":36.18,"lo":909,"hi":1088,"n":10,"rr":1409,"mr":1007},{"m":"internlm-xcomposer2.5","r":1027,"s":36.16,"lo":957,"hi":1097,"n":24,"rr":423,"mr":1101},{"m":"falcon-h1-3b","r":1028,"s":36.14,"lo":985,"hi":1098,"n":25,"rr":1264,"mr":993},{"m":"gemma-2-9b-it","r":1029,"s":36.11,"lo":988,"hi":1065,"n":38,"rr":1107,"mr":1009},{"m":"qwen2.5-omni-7b","r":1030,"s":35.96,"lo":932,"hi":1138,"n":37,"rr":950,"mr":1069},{"m":"minicpm3-4b","r":1031,"s":35.87,"lo":1008,"hi":1067,"n":18,"rr":944,"mr":1008},{"m":"llava-onevision-7b","r":1032,"s":35.84,"lo":950,"hi":1104,"n":35,"rr":875,"mr":1095},{"m":"internlm2-math-plus-7b","r":1033,"s":35.75,"lo":973,"hi":1161,"n":10,"rr":1224,"mr":1061},{"m":"internvl3.5-2b","r":1034,"s":35.69,"lo":974,"hi":1096,"n":41,"rr":842,"mr":1084},{"m":"kanana-2-3b-instruct","r":1035,"s":35.63,"lo":945,"hi":1111,"n":10,"rr":1153,"mr":1031},{"m":"qwen-2.5-3b-instruct","r":1036,"s":35.58,"lo":976,"hi":1137,"n":15,"rr":1265,"mr":1030},{"m":"phind-codellama-34b-v2","r":1037,"s":35.53,"lo":996,"hi":1113,"n":8,"rr":1250,"mr":1058},{"m":"granite-3.2-8b-instruct","r":1038,"s":35.5,"lo":866,"hi":1178,"n":13,"rr":735,"mr":1055},{"m":"minicpm-v-2_6","r":1039,"s":35.46,"lo":970,"hi":1104,"n":33,"rr":754,"mr":1097},{"m":"qwen2.5-coder-7b","r":1040,"s":35.43,"lo":990,"hi":1110,"n":20,"rr":853,"mr":1024},{"m":"lfm2.5-1.2b-instruct","r":1041,"s":35.43,"lo":987,"hi":1136,"n":21,"rr":1247,"mr":1018},{"m":"codellama-70b-instruct","r":1042,"s":35.43,"lo":967,"hi":1253,"n":11,"rr":1195,"mr":1050},{"m":"llama-3-70b-base","r":1043,"s":35.4,"lo":974,"hi":1108,"n":42,"rr":352,"mr":1012},{"m":"gemma-3-4b-it","r":1044,"s":35.37,"lo":974,"hi":1101,"n":56,"rr":1179,"mr":1014},{"m":"olmo-hybrid-instruct-7b-sft","r":1045,"s":35.35,"lo":977,"hi":1108,"n":15,"rr":1402,"mr":1023},{"m":"llada-o","r":1046,"s":35.33,"lo":951,"hi":1131,"n":19,"rr":736,"mr":1093},{"m":"gemma-3-12b","r":1047,"s":35.29,"lo":887,"hi":1145,"n":26,"rr":703,"mr":1042},{"m":"exaone-3.5-7.8b-instruct","r":1048,"s":35.26,"lo":939,"hi":1166,"n":8,"rr":685,"mr":1046},{"m":"mixtral-8x22b","r":1049,"s":35.19,"lo":966,"hi":1119,"n":42,"rr":528,"mr":1016},{"m":"olmo-2-32b-base","r":1050,"s":35.14,"lo":884,"hi":1146,"n":24,"rr":245,"mr":1049},{"m":"granite-4.0-micro","r":1051,"s":35.13,"lo":967,"hi":1128,"n":28,"rr":1078,"mr":1019},{"m":"mathstral-7b","r":1052,"s":35.08,"lo":979,"hi":1127,"n":12,"rr":1311,"mr":1064},{"m":"ministral-3-3b-base","r":1053,"s":35.05,"lo":979,"hi":1271,"n":9,"rr":870,"mr":1074},{"m":"molmo-7b-o","r":1054,"s":35,"lo":839,"hi":1193,"n":20,"rr":344,"mr":1121},{"m":"falcon3-10b","r":1055,"s":34.97,"lo":1001,"hi":1104,"n":21,"rr":1125,"mr":1028},{"m":"lfm2-2.6b","r":1056,"s":34.93,"lo":1012,"hi":1114,"n":17,"rr":1182,"mr":1029},{"m":"phi-3-medium-4k-instruct","r":1057,"s":34.92,"lo":906,"hi":1171,"n":15,"rr":610,"mr":1051},{"m":"deepseek-coder-v2-lite-instruct","r":1058,"s":34.91,"lo":959,"hi":1122,"n":47,"rr":1324,"mr":1032},{"m":"qwen2-7b-instruct","r":1059,"s":34.9,"lo":1007,"hi":1100,"n":40,"rr":1174,"mr":1037},{"m":"numinamath-7b-cot","r":1060,"s":34.78,"lo":986,"hi":1144,"n":8,"rr":1188,"mr":1086},{"m":"gemma-2-27b","r":1061,"s":34.72,"lo":1007,"hi":1129,"n":25,"rr":1010,"mr":1021},{"m":"granite-4.0-h-tiny","r":1062,"s":34.69,"lo":999,"hi":1121,"n":46,"rr":1276,"mr":1026},{"m":"yi-1.5-34b","r":1063,"s":34.67,"lo":989,"hi":1158,"n":22,"rr":745,"mr":1035},{"m":"internvl2-26b","r":1064,"s":34.63,"lo":985,"hi":1131,"n":61,"rr":723,"mr":1078},{"m":"internvl3-2b","r":1065,"s":34.46,"lo":1000,"hi":1117,"n":22,"rr":618,"mr":1112},{"m":"codeqwen1.5-7b-chat","r":1066,"s":34.46,"lo":903,"hi":1219,"n":14,"rr":1316,"mr":1087},{"m":"qwen2.5-coder-3b-instruct","r":1067,"s":34.42,"lo":963,"hi":1146,"n":22,"rr":1269,"mr":1053},{"m":"ministral-8b-instruct","r":1068,"s":34.41,"lo":854,"hi":1143,"n":11,"rr":847,"mr":1057},{"m":"starcoder2-15b-instruct-v0.1","r":1069,"s":34.35,"lo":1012,"hi":1132,"n":10,"rr":1175,"mr":1075},{"m":"qwen1.5-72b","r":1070,"s":34.33,"lo":1005,"hi":1131,"n":34,"rr":554,"mr":1033},{"m":"internvl2-8b","r":1071,"s":34.3,"lo":1004,"hi":1141,"n":68,"rr":707,"mr":1082},{"m":"lfm2.5-350m","r":1072,"s":34.29,"lo":944,"hi":1205,"n":9,"rr":1431,"mr":1063},{"m":"deepseek-coder-6.7b-instruct","r":1073,"s":34.28,"lo":988,"hi":1183,"n":25,"rr":1309,"mr":1052},{"m":"deepseek-llm-67b-chat","r":1074,"s":34.26,"lo":1020,"hi":1131,"n":32,"rr":503,"mr":1043},{"m":"alodlm-1.7b","r":1075,"s":34.24,"lo":1007,"hi":1124,"n":11,"rr":484,"mr":1044},{"m":"openpangu-7b-diffusion-base","r":1076,"s":34.22,"lo":987,"hi":1137,"n":9,"rr":493,"mr":1068},{"m":"lfm2-vl-3b","r":1077,"s":34.15,"lo":982,"hi":1160,"n":30,"rr":833,"mr":1102},{"m":"ouro-1.4b","r":1078,"s":34.13,"lo":980,"hi":1206,"n":15,"rr":445,"mr":1060},{"m":"glm-4-9b-chat-1m","r":1079,"s":34.1,"lo":988,"hi":1112,"n":16,"rr":498,"mr":1073},{"m":"qwen2.57b-a14b","r":1080,"s":34.06,"lo":1018,"hi":1135,"n":23,"rr":796,"mr":1047},{"m":"yi-1.5-9b-chat","r":1081,"s":33.99,"lo":1029,"hi":1128,"n":18,"rr":1122,"mr":1056},{"m":"fanar-1-9b-instruct","r":1082,"s":33.97,"lo":1005,"hi":1145,"n":9,"rr":1347,"mr":1096},{"m":"yi-34b-chat","r":1083,"s":33.96,"lo":957,"hi":1188,"n":10,"rr":412,"mr":1111},{"m":"claude-3-haiku","r":1084,"s":33.92,"lo":1003,"hi":1237,"n":28,"rr":830,"mr":1113},{"m":"deepseek-r1-distill-qwen-1.5b","r":1085,"s":33.91,"lo":908,"hi":1206,"n":23,"rr":1365,"mr":1041},{"m":"llama-3.2v-11b-instruct","r":1086,"s":33.83,"lo":958,"hi":1146,"n":15,"rr":441,"mr":1143},{"m":"command-r-plus","r":1087,"s":33.81,"lo":1037,"hi":1123,"n":19,"rr":1084,"mr":1071},{"m":"qwen1.5-32b-chat","r":1088,"s":33.67,"lo":1047,"hi":1131,"n":25,"rr":992,"mr":1059},{"m":"phi-3-mini-4k-instruct","r":1089,"s":33.65,"lo":1042,"hi":1115,"n":13,"rr":923,"mr":1072},{"m":"instella-moe-16b-a3b-base","r":1090,"s":33.57,"lo":1001,"hi":1135,"n":17,"rr":60,"mr":1076},{"m":"falcon-h1-1.5b","r":1091,"s":33.56,"lo":1037,"hi":1174,"n":21,"rr":1283,"mr":1048},{"m":"olmo-3-7b-sft","r":1092,"s":33.54,"lo":1005,"hi":1157,"n":21,"rr":1434,"mr":1067},{"m":"gpt-3.5-turbo-0125","r":1093,"s":33.52,"lo":1032,"hi":1127,"n":18,"rr":1141,"mr":1081},{"m":"apertus-v1.5-8b","r":1094,"s":33.39,"lo":1015,"hi":1137,"n":18,"rr":831,"mr":1062},{"m":"falcon3-7b","r":1095,"s":33.37,"lo":1050,"hi":1148,"n":21,"rr":1197,"mr":1066},{"m":"trinity-large-truebase","r":1096,"s":33.36,"lo":947,"hi":1172,"n":12,"rr":394,"mr":1079},{"m":"qwen-vl-max","r":1097,"s":33.32,"lo":987,"hi":1171,"n":22,"rr":559,"mr":1151},{"m":"internlm-xcomposer2-4khd-7b","r":1098,"s":33.32,"lo":1014,"hi":1148,"n":19,"rr":459,"mr":1153},{"m":"nemotron-nano-12b-v2-base","r":1099,"s":33.3,"lo":961,"hi":1198,"n":18,"rr":218,"mr":1085},{"m":"mistral-nemo-instruct-2407","r":1100,"s":33.22,"lo":1035,"hi":1150,"n":16,"rr":1282,"mr":1104},{"m":"phi-3.5-mini-instruct","r":1101,"s":33.06,"lo":1056,"hi":1151,"n":25,"rr":1186,"mr":1070},{"m":"eurollm-22b","r":1102,"s":33.05,"lo":967,"hi":1153,"n":23,"rr":799,"mr":1077},{"m":"moonlight-base","r":1103,"s":33.01,"lo":1049,"hi":1145,"n":30,"rr":935,"mr":1091},{"m":"cogvlm2-llama3-chat-19b","r":1104,"s":32.99,"lo":975,"hi":1183,"n":15,"rr":280,"mr":1149},{"m":"llama-3.1-tulu-3-8b-sft","r":1105,"s":32.85,"lo":882,"hi":1185,"n":11,"rr":900,"mr":1110},{"m":"llama-3.1-8b-instruct","r":1106,"s":32.83,"lo":1056,"hi":1148,"n":71,"rr":1313,"mr":1083},{"m":"kanana-2-1.3b-instruct","r":1107,"s":32.74,"lo":1049,"hi":1155,"n":10,"rr":1226,"mr":1088},{"m":"fast-dllm-v2-7b","r":1108,"s":32.57,"lo":998,"hi":1181,"n":12,"rr":878,"mr":1100},{"m":"glm-4v-9b","r":1109,"s":32.56,"lo":1026,"hi":1160,"n":17,"rr":470,"mr":1161},{"m":"gpt-3.5-turbo","r":1110,"s":32.49,"lo":1032,"hi":1199,"n":24,"rr":994,"mr":1117},{"m":"deepseek-coder-7b-instruct-v1.5","r":1111,"s":32.48,"lo":1017,"hi":1223,"n":12,"rr":653,"mr":1098},{"m":"qwen2-7b","r":1112,"s":32.43,"lo":1064,"hi":1160,"n":25,"rr":914,"mr":1089},{"m":"granite-3.1-8b-instruct","r":1113,"s":32.3,"lo":1005,"hi":1193,"n":14,"rr":997,"mr":1107},{"m":"mimo-7b-base","r":1114,"s":32.28,"lo":1030,"hi":1163,"n":20,"rr":639,"mr":1115},{"m":"cambrian-34b","r":1115,"s":32.25,"lo":1033,"hi":1188,"n":22,"rr":534,"mr":1157},{"m":"step-audio-2-mini","r":1116,"s":32.2,"lo":1034,"hi":1164,"n":15,"rr":1103,"mr":1130},{"m":"exaone-3.5-2.4b-instruct","r":1117,"s":32.17,"lo":1017,"hi":1233,"n":8,"rr":978,"mr":1128},{"m":"granite-4.0-tiny-preview","r":1118,"s":32.12,"lo":954,"hi":1203,"n":12,"rr":917,"mr":1114},{"m":"gemini-1.0-pro","r":1119,"s":32.1,"lo":1070,"hi":1154,"n":28,"rr":620,"mr":1139},{"m":"llama-3.1-8b","r":1120,"s":32.1,"lo":1014,"hi":1160,"n":25,"rr":1033,"mr":1094},{"m":"baichuan-omni","r":1121,"s":32.07,"lo":1068,"hi":1162,"n":19,"rr":568,"mr":1158},{"m":"olmo-2-0325-32b-instruct","r":1122,"s":32.01,"lo":1022,"hi":1183,"n":16,"rr":1392,"mr":1108},{"m":"step-1v-32k","r":1123,"s":31.97,"lo":986,"hi":1214,"n":14,"rr":523,"mr":1167},{"m":"llm-jp-4-vl-9b-beta","r":1124,"s":31.96,"lo":1030,"hi":1169,"n":16,"rr":1005,"mr":1125},{"m":"qwen1.5-32b","r":1125,"s":31.94,"lo":1057,"hi":1183,"n":22,"rr":790,"mr":1090},{"m":"internvl-chat-v1.5","r":1126,"s":31.82,"lo":1015,"hi":1259,"n":41,"rr":971,"mr":1166},{"m":"aquila-vl-2b","r":1127,"s":31.82,"lo":1070,"hi":1167,"n":14,"rr":612,"mr":1170},{"m":"internlm2-chat-20b","r":1128,"s":31.81,"lo":1076,"hi":1154,"n":24,"rr":845,"mr":1099},{"m":"gpt-3.5","r":1129,"s":31.61,"lo":1050,"hi":1176,"n":13,"rr":389,"mr":1135},{"m":"minicpm-llama3-v2.5","r":1130,"s":31.58,"lo":1087,"hi":1173,"n":19,"rr":512,"mr":1181},{"m":"gemini-pro","r":1131,"s":31.54,"lo":1035,"hi":1191,"n":25,"rr":408,"mr":1154},{"m":"llama3.0-70b","r":1132,"s":31.35,"lo":989,"hi":1242,"n":14,"rr":757,"mr":1118},{"m":"qwen2.5-coder-1.5b-instruct","r":1133,"s":31.26,"lo":1054,"hi":1282,"n":10,"rr":1344,"mr":1150},{"m":"trinity-mini-base","r":1134,"s":31.26,"lo":993,"hi":1217,"n":12,"rr":444,"mr":1116},{"m":"vllm-sr-d3-lite","r":1135,"s":31.22,"lo":1005,"hi":1228,"n":27,"rr":1111,"mr":1105},{"m":"qwen2.5-3b","r":1136,"s":31.17,"lo":1098,"hi":1188,"n":32,"rr":1178,"mr":1103},{"m":"dream-7b-base","r":1137,"s":31.12,"lo":1102,"hi":1159,"n":12,"rr":855,"mr":1123},{"m":"moonlight-instruct","r":1138,"s":31.11,"lo":1076,"hi":1187,"n":16,"rr":1330,"mr":1109},{"m":"plamo-2.2-prime","r":1139,"s":31.04,"lo":951,"hi":1226,"n":8,"rr":1462,"mr":1141},{"m":"bitcpm-cann-3b","r":1140,"s":30.95,"lo":1069,"hi":1211,"n":11,"rr":181,"mr":1131},{"m":"deepseek-vl2-tiny","r":1141,"s":30.9,"lo":1050,"hi":1214,"n":18,"rr":278,"mr":1178},{"m":"granite-3.3-2b-instruct","r":1142,"s":30.69,"lo":1023,"hi":1203,"n":15,"rr":1036,"mr":1126},{"m":"command-r","r":1143,"s":30.63,"lo":1082,"hi":1243,"n":9,"rr":1393,"mr":1144},{"m":"olmo-hybrid-7b","r":1144,"s":30.61,"lo":1056,"hi":1187,"n":20,"rr":725,"mr":1134},{"m":"minicpm-o-2.6","r":1145,"s":30.55,"lo":971,"hi":1208,"n":25,"rr":1169,"mr":1176},{"m":"gemma-3-pt-27b","r":1146,"s":30.51,"lo":1021,"hi":1226,"n":21,"rr":425,"mr":1146},{"m":"ministral-3-3b-instruct","r":1147,"s":30.41,"lo":1047,"hi":1212,"n":37,"rr":1000,"mr":1136},{"m":"deepseek-llm-67b-base","r":1148,"s":30.37,"lo":1024,"hi":1236,"n":28,"rr":415,"mr":1120},{"m":"qwen3-4b-base","r":1149,"s":30.34,"lo":1080,"hi":1239,"n":12,"rr":695,"mr":1160},{"m":"dream-7b-instruct","r":1150,"s":30.28,"lo":1110,"hi":1200,"n":19,"rr":947,"mr":1127},{"m":"deepseek-math-7b","r":1151,"s":30.27,"lo":1105,"hi":1227,"n":18,"rr":1052,"mr":1132},{"m":"llada-v","r":1152,"s":30.22,"lo":1078,"hi":1214,"n":19,"rr":903,"mr":1185},{"m":"qwen3.5-2b-base","r":1153,"s":30.14,"lo":1053,"hi":1223,"n":17,"rr":168,"mr":1147},{"m":"chatglm3-6b-base","r":1154,"s":30.11,"lo":1094,"hi":1201,"n":23,"rr":715,"mr":1119},{"m":"cambrian-1-34b","r":1155,"s":30.07,"lo":1073,"hi":1220,"n":18,"rr":382,"mr":1200},{"m":"olmo-3-7b","r":1156,"s":30.06,"lo":1086,"hi":1185,"n":37,"rr":649,"mr":1138},{"m":"qwen3-0.6b","r":1157,"s":30,"lo":1073,"hi":1254,"n":36,"rr":1464,"mr":1122},{"m":"internlm2-20b","r":1158,"s":29.92,"lo":1106,"hi":1195,"n":20,"rr":890,"mr":1129},{"m":"gemma-2-9b","r":1159,"s":29.92,"lo":1123,"hi":1203,"n":42,"rr":1093,"mr":1124},{"m":"yi-1.5-9b","r":1160,"s":29.92,"lo":1080,"hi":1213,"n":12,"rr":1035,"mr":1137},{"m":"xverse-65b","r":1161,"s":29.78,"lo":983,"hi":1274,"n":10,"rr":309,"mr":1169},{"m":"xverse-65b-2","r":1162,"s":29.74,"lo":1010,"hi":1260,"n":12,"rr":469,"mr":1168},{"m":"qwen2-vl-2b-instruct","r":1163,"s":29.72,"lo":1106,"hi":1228,"n":26,"rr":755,"mr":1207},{"m":"apertus-70b","r":1164,"s":29.68,"lo":1007,"hi":1235,"n":21,"rr":696,"mr":1142},{"m":"yi-1.5-6b-chat","r":1165,"s":29.63,"lo":1128,"hi":1217,"n":11,"rr":1320,"mr":1145},{"m":"mm1.5-7b","r":1166,"s":29.61,"lo":1077,"hi":1229,"n":9,"rr":473,"mr":1221},{"m":"internlm2-chat-20b-sft","r":1167,"s":29.54,"lo":1131,"hi":1193,"n":24,"rr":940,"mr":1140},{"m":"phi-3-vision-4b","r":1168,"s":29.5,"lo":1101,"hi":1235,"n":16,"rr":539,"mr":1219},{"m":"llama-3-8b-instruct","r":1169,"s":29.5,"lo":1135,"hi":1212,"n":45,"rr":1115,"mr":1133},{"m":"qwen2-vl-2b","r":1170,"s":29.38,"lo":1095,"hi":1229,"n":30,"rr":1012,"mr":1205},{"m":"qwen2.5-coder-3b","r":1171,"s":29.31,"lo":1124,"hi":1244,"n":19,"rr":1131,"mr":1156},{"m":"fastvlm-1.5b","r":1172,"s":29.28,"lo":1065,"hi":1268,"n":16,"rr":543,"mr":1213},{"m":"hyperclovax-seed-omni-8b","r":1173,"s":29.28,"lo":1016,"hi":1240,"n":28,"rr":1139,"mr":1197},{"m":"magpie-8b","r":1174,"s":29.22,"lo":951,"hi":1377,"n":10,"rr":1194,"mr":1192},{"m":"north-micro-vision-instruct","r":1175,"s":29.03,"lo":1085,"hi":1248,"n":20,"rr":689,"mr":1164},{"m":"molmoe-1b","r":1176,"s":28.86,"lo":887,"hi":1285,"n":19,"rr":532,"mr":1229},{"m":"dbrx-instruct-preview","r":1177,"s":28.84,"lo":1096,"hi":1242,"n":9,"rr":747,"mr":1162},{"m":"mini-gemini-hd-34b","r":1178,"s":28.78,"lo":1100,"hi":1254,"n":10,"rr":808,"mr":1226},{"m":"kanana-2-3b-base","r":1179,"s":28.61,"lo":1094,"hi":1239,"n":12,"rr":1123,"mr":1152},{"m":"qwen-14b","r":1180,"s":28.51,"lo":1087,"hi":1238,"n":35,"rr":353,"mr":1148},{"m":"qwen1.5-14b-chat","r":1181,"s":28.51,"lo":1078,"hi":1366,"n":12,"rr":642,"mr":1182},{"m":"llava-next-34b","r":1182,"s":28.44,"lo":1111,"hi":1238,"n":24,"rr":679,"mr":1236},{"m":"internvl-u","r":1183,"s":28.39,"lo":1102,"hi":1253,"n":19,"rr":930,"mr":1216},{"m":"deepseek-coder-v2-lite-base","r":1184,"s":28.29,"lo":1139,"hi":1261,"n":20,"rr":1133,"mr":1165},{"m":"internvl2-4b","r":1185,"s":28.23,"lo":1115,"hi":1283,"n":44,"rr":1047,"mr":1232},{"m":"internvl-chat-v1.2","r":1186,"s":28.23,"lo":1032,"hi":1304,"n":16,"rr":652,"mr":1258},{"m":"marin-32b-mantis","r":1187,"s":28.22,"lo":1082,"hi":1267,"n":18,"rr":371,"mr":1171},{"m":"codestral-12b-instruct","r":1188,"s":28.21,"lo":894,"hi":1326,"n":8,"rr":1421,"mr":1206},{"m":"mixtral-8x7b","r":1189,"s":28.21,"lo":1142,"hi":1243,"n":34,"rr":1055,"mr":1159},{"m":"llama-3.1-8b-base","r":1190,"s":28.1,"lo":1134,"hi":1233,"n":43,"rr":1112,"mr":1155},{"m":"gemma-3n-e2b-it","r":1191,"s":27.93,"lo":1148,"hi":1260,"n":28,"rr":1298,"mr":1202},{"m":"internlm-xcomposer2-vl-7b","r":1192,"s":27.87,"lo":1119,"hi":1269,"n":23,"rr":739,"mr":1257},{"m":"gemma-3-4b","r":1193,"s":27.87,"lo":1035,"hi":1329,"n":22,"rr":1301,"mr":1195},{"m":"llama-3.2-3b-instruct","r":1194,"s":27.76,"lo":1152,"hi":1248,"n":25,"rr":1440,"mr":1177},{"m":"codellama-34b","r":1195,"s":27.74,"lo":1111,"hi":1265,"n":14,"rr":1180,"mr":1179},{"m":"gemini-1.0-pro-vision","r":1196,"s":27.7,"lo":1126,"hi":1264,"n":8,"rr":692,"mr":1274},{"m":"tigerbot-70b-chat","r":1197,"s":27.7,"lo":1028,"hi":1310,"n":13,"rr":328,"mr":1245},{"m":"llada-moe-7b-a1b-base","r":1198,"s":27.69,"lo":1175,"hi":1224,"n":9,"rr":1020,"mr":1180},{"m":"smollm3-3b-base","r":1199,"s":27.68,"lo":1106,"hi":1242,"n":17,"rr":178,"mr":1186},{"m":"llama-3.1-swallow-8b-instruct-v0.5","r":1200,"s":27.63,"lo":1145,"hi":1264,"n":10,"rr":1376,"mr":1187},{"m":"lfm2-vl-1.6b","r":1201,"s":27.63,"lo":1117,"hi":1319,"n":9,"rr":1072,"mr":1244},{"m":"vila1.5-40b","r":1202,"s":27.59,"lo":1124,"hi":1277,"n":16,"rr":1060,"mr":1261},{"m":"telechat2-3b","r":1203,"s":27.57,"lo":1069,"hi":1257,"n":8,"rr":662,"mr":1203},{"m":"apertus-70b-instruct","r":1204,"s":27.53,"lo":1143,"hi":1269,"n":35,"rr":1437,"mr":1163},{"m":"marin-8b-instruct","r":1205,"s":27.42,"lo":1143,"hi":1256,"n":18,"rr":1206,"mr":1183},{"m":"deepseek-coder-1.3b-instruct","r":1206,"s":27.41,"lo":1144,"hi":1339,"n":13,"rr":1430,"mr":1204},{"m":"internlm2-7b","r":1207,"s":27.38,"lo":1158,"hi":1247,"n":20,"rr":1015,"mr":1174},{"m":"mixtral-8x7b-instruct-v0.1","r":1208,"s":27.37,"lo":1175,"hi":1246,"n":36,"rr":1145,"mr":1173},{"m":"trinity-nano-base","r":1209,"s":27.33,"lo":1123,"hi":1265,"n":19,"rr":428,"mr":1189},{"m":"codellama-34b-instruct","r":1210,"s":27.15,"lo":1172,"hi":1290,"n":11,"rr":1442,"mr":1198},{"m":"mm1.5-3b","r":1211,"s":27.11,"lo":1145,"hi":1289,"n":12,"rr":420,"mr":1276},{"m":"llama-3-8b","r":1212,"s":27.06,"lo":1153,"hi":1258,"n":33,"rr":1075,"mr":1172},{"m":"yi-34b","r":1213,"s":27.01,"lo":965,"hi":1329,"n":12,"rr":763,"mr":1211},{"m":"phi-4-multimodal-instruct","r":1214,"s":26.98,"lo":1127,"hi":1344,"n":26,"rr":1146,"mr":1259},{"m":"falcon-180b","r":1215,"s":26.91,"lo":1150,"hi":1250,"n":11,"rr":506,"mr":1223},{"m":"granite-4.0-1b","r":1216,"s":26.9,"lo":1169,"hi":1271,"n":20,"rr":1414,"mr":1184},{"m":"lfm2.5-vl-1.6b","r":1217,"s":26.89,"lo":1172,"hi":1271,"n":43,"rr":1113,"mr":1249},{"m":"qwen2.5-1.5b-instruct","r":1218,"s":26.83,"lo":1173,"hi":1291,"n":23,"rr":1401,"mr":1188},{"m":"qwen3-1.7b-base","r":1219,"s":26.78,"lo":1159,"hi":1303,"n":18,"rr":1140,"mr":1218},{"m":"aquila2-34b","r":1220,"s":26.78,"lo":1032,"hi":1291,"n":14,"rr":297,"mr":1239},{"m":"llama-2-70b","r":1221,"s":26.75,"lo":1143,"hi":1283,"n":39,"rr":645,"mr":1175},{"m":"yi-coder-1.5b-chat","r":1222,"s":26.71,"lo":1111,"hi":1381,"n":10,"rr":1417,"mr":1252},{"m":"falcon3-3b","r":1223,"s":26.66,"lo":1176,"hi":1298,"n":21,"rr":1386,"mr":1191},{"m":"internlm2-chat-7b","r":1224,"s":26.59,"lo":1181,"hi":1258,"n":25,"rr":1039,"mr":1193},{"m":"qwen1.5-14b","r":1225,"s":26.53,"lo":1151,"hi":1284,"n":12,"rr":758,"mr":1201},{"m":"qwen-vl-plus","r":1226,"s":26.5,"lo":1154,"hi":1295,"n":24,"rr":751,"mr":1288},{"m":"internlm2-chat-7b-sft","r":1227,"s":26.5,"lo":1184,"hi":1264,"n":24,"rr":1059,"mr":1196},{"m":"deepseek-coder-33b-base","r":1228,"s":26.48,"lo":1159,"hi":1302,"n":22,"rr":1256,"mr":1208},{"m":"granite-3.2-2b-instruct","r":1229,"s":26.42,"lo":1113,"hi":1325,"n":13,"rr":1260,"mr":1224},{"m":"marin-8b-base","r":1230,"s":26.37,"lo":1131,"hi":1304,"n":22,"rr":945,"mr":1241},{"m":"lfm2.5-230m","r":1231,"s":26.34,"lo":1143,"hi":1312,"n":9,"rr":1456,"mr":1194},{"m":"granite-4.0-h-1b","r":1232,"s":26.29,"lo":1168,"hi":1296,"n":12,"rr":1358,"mr":1210},{"m":"hy-0.5b","r":1233,"s":26.29,"lo":1093,"hi":1362,"n":8,"rr":1290,"mr":1220},{"m":"falcon-h1-0.5b-instruct","r":1234,"s":26.26,"lo":1175,"hi":1311,"n":21,"rr":1423,"mr":1190},{"m":"xverse-13b-2","r":1235,"s":26.17,"lo":1120,"hi":1278,"n":10,"rr":530,"mr":1242},{"m":"llada-8b-base","r":1236,"s":26.11,"lo":1172,"hi":1296,"n":9,"rr":1092,"mr":1237},{"m":"granite-3.1-2b-instruct","r":1237,"s":26.04,"lo":1144,"hi":1322,"n":14,"rr":1295,"mr":1230},{"m":"marin-32b-bison","r":1238,"s":25.98,"lo":1093,"hi":1325,"n":18,"rr":500,"mr":1214},{"m":"granite-3.3-8b-base","r":1239,"s":25.87,"lo":1172,"hi":1307,"n":22,"rr":1022,"mr":1228},{"m":"qwen2.5-1.5b","r":1240,"s":25.81,"lo":1200,"hi":1291,"n":31,"rr":1391,"mr":1199},{"m":"internvl2.5-2b","r":1241,"s":25.76,"lo":1196,"hi":1281,"n":61,"rr":1058,"mr":1255},{"m":"vita","r":1242,"s":25.67,"lo":1186,"hi":1298,"n":21,"rr":814,"mr":1289},{"m":"llada-8b-instruct","r":1243,"s":25.64,"lo":1185,"hi":1321,"n":15,"rr":1201,"mr":1233},{"m":"gemma-2-2b-it","r":1244,"s":25.61,"lo":1183,"hi":1312,"n":14,"rr":1412,"mr":1235},{"m":"yi-1.5-6b","r":1245,"s":25.59,"lo":1195,"hi":1284,"n":10,"rr":1129,"mr":1222},{"m":"eurollm-9b-instruct-2512","r":1246,"s":25.58,"lo":1204,"hi":1270,"n":18,"rr":1231,"mr":1212},{"m":"solar-10.7b-instruct-v1.0","r":1247,"s":25.56,"lo":1172,"hi":1278,"n":13,"rr":732,"mr":1248},{"m":"kanana-2-1.3b-base","r":1248,"s":25.49,"lo":1168,"hi":1307,"n":12,"rr":1297,"mr":1209},{"m":"llava-next-llama3","r":1249,"s":25.49,"lo":1163,"hi":1307,"n":9,"rr":547,"mr":1306},{"m":"internvl3.5-1b","r":1250,"s":25.47,"lo":1189,"hi":1333,"n":9,"rr":1158,"mr":1285},{"m":"mobilemoe-l","r":1251,"s":25.45,"lo":1177,"hi":1300,"n":20,"rr":919,"mr":1217},{"m":"tinyswallow-1.5b-instruct","r":1252,"s":25.35,"lo":1172,"hi":1343,"n":10,"rr":1453,"mr":1279},{"m":"trida-7b","r":1253,"s":25.23,"lo":1194,"hi":1285,"n":9,"rr":1119,"mr":1240},{"m":"starcoder2-15b","r":1254,"s":25.12,"lo":1193,"hi":1304,"n":22,"rr":1348,"mr":1225},{"m":"tigerbot-70b-base","r":1255,"s":25.04,"lo":1160,"hi":1334,"n":13,"rr":433,"mr":1278},{"m":"nemotronlabs-voicechat-11b","r":1256,"s":25,"lo":994,"hi":1403,"n":12,"rr":1203,"mr":1272},{"m":"orion-14b-base","r":1257,"s":24.99,"lo":1146,"hi":1365,"n":29,"rr":436,"mr":1227},{"m":"stablebeluga2-70b","r":1258,"s":24.98,"lo":1147,"hi":1326,"n":19,"rr":792,"mr":1251},{"m":"llama-3.2-3b-base","r":1259,"s":24.89,"lo":1146,"hi":1340,"n":21,"rr":1405,"mr":1234},{"m":"bunny-llama3-8b","r":1260,"s":24.85,"lo":1103,"hi":1361,"n":8,"rr":713,"mr":1319},{"m":"qwen2.5-coder-1.5b","r":1261,"s":24.82,"lo":1198,"hi":1343,"n":19,"rr":1319,"mr":1246},{"m":"cambrian-1-8b","r":1262,"s":24.77,"lo":1189,"hi":1300,"n":16,"rr":482,"mr":1310},{"m":"vllm-sr-decision-2.0-sol-2b","r":1263,"s":24.73,"lo":1142,"hi":1346,"n":27,"rr":1252,"mr":1215},{"m":"gemma-4-e4b","r":1264,"s":24.72,"lo":1008,"hi":1386,"n":17,"rr":648,"mr":1260},{"m":"qwen-14b-chat","r":1265,"s":24.66,"lo":1220,"hi":1303,"n":29,"rr":1040,"mr":1243},{"m":"internlm-20b","r":1266,"s":24.56,"lo":1203,"hi":1316,"n":33,"rr":487,"mr":1231},{"m":"meta-llama-3-8b-instruct","r":1267,"s":24.49,"lo":1149,"hi":1398,"n":8,"rr":840,"mr":1295},{"m":"llama-3-8b-base","r":1268,"s":24.37,"lo":1218,"hi":1306,"n":24,"rr":1088,"mr":1238},{"m":"qwen3.5-0.8b-thinking","r":1269,"s":24.24,"lo":1186,"hi":1324,"n":44,"rr":1397,"mr":1254},{"m":"gemma-7b","r":1270,"s":24.23,"lo":1232,"hi":1299,"n":27,"rr":1097,"mr":1247},{"m":"llama-3-8b-instruct-gradient-1048k","r":1271,"s":24.14,"lo":1014,"hi":1331,"n":15,"rr":1019,"mr":1271},{"m":"olmo-2-1124-7b-instruct","r":1272,"s":24.05,"lo":1205,"hi":1332,"n":16,"rr":1467,"mr":1263},{"m":"internvl2.5-1b","r":1273,"s":24,"lo":1218,"hi":1325,"n":44,"rr":1170,"mr":1317},{"m":"phi-3.5-vision-instruct","r":1274,"s":23.97,"lo":1210,"hi":1323,"n":36,"rr":1076,"mr":1308},{"m":"deepseek-v2-lite-chat","r":1275,"s":23.92,"lo":1228,"hi":1326,"n":25,"rr":1314,"mr":1250},{"m":"telechat-12b","r":1276,"s":23.83,"lo":1183,"hi":1333,"n":11,"rr":943,"mr":1277},{"m":"qwen1.5-7b","r":1277,"s":23.82,"lo":1232,"hi":1313,"n":20,"rr":1234,"mr":1253},{"m":"mm1-30b","r":1278,"s":23.78,"lo":1207,"hi":1323,"n":13,"rr":575,"mr":1329},{"m":"deepseek-coder-7b-base-v1.5","r":1279,"s":23.76,"lo":1246,"hi":1340,"n":11,"rr":1154,"mr":1264},{"m":"qwen3.5-0.8b","r":1280,"s":23.75,"lo":1173,"hi":1342,"n":95,"rr":1336,"mr":1273},{"m":"jamba-v0.1","r":1281,"s":23.65,"lo":1183,"hi":1321,"n":8,"rr":759,"mr":1297},{"m":"fastvlm-0.5b","r":1282,"s":23.64,"lo":1217,"hi":1355,"n":11,"rr":456,"mr":1331},{"m":"qwen1.5-moe-a2.7b","r":1283,"s":23.63,"lo":1196,"hi":1326,"n":8,"rr":1098,"mr":1280},{"m":"codellama-13b","r":1284,"s":23.6,"lo":1203,"hi":1337,"n":11,"rr":1317,"mr":1269},{"m":"llama-2-70b-chat","r":1285,"s":23.54,"lo":1168,"hi":1349,"n":18,"rr":613,"mr":1303},{"m":"minicpm-moe-8x2b","r":1286,"s":23.47,"lo":1202,"hi":1360,"n":8,"rr":1181,"mr":1294},{"m":"codellama-13b-instruct","r":1287,"s":23.35,"lo":1224,"hi":1363,"n":10,"rr":1447,"mr":1281},{"m":"qwen1.5-7b-chat","r":1288,"s":23.34,"lo":1266,"hi":1318,"n":29,"rr":1280,"mr":1265},{"m":"bitcpm-cann-1b","r":1289,"s":23.33,"lo":1235,"hi":1345,"n":11,"rr":589,"mr":1282},{"m":"strands-decider-2b","r":1290,"s":23.31,"lo":1187,"hi":1366,"n":27,"rr":1332,"mr":1256},{"m":"llama-3.2-3b","r":1291,"s":23.19,"lo":1172,"hi":1391,"n":27,"rr":1278,"mr":1267},{"m":"nemotron-nano-12b-v2-vl","r":1292,"s":23.13,"lo":944,"hi":1446,"n":12,"rr":1435,"mr":1326},{"m":"apertus-8b-instruct","r":1293,"s":23.13,"lo":1236,"hi":1325,"n":26,"rr":1422,"mr":1266},{"m":"map-neo-7b-instruct","r":1294,"s":23.11,"lo":1231,"hi":1347,"n":24,"rr":1198,"mr":1270},{"m":"yi-9b","r":1295,"s":23.09,"lo":1230,"hi":1325,"n":9,"rr":941,"mr":1283},{"m":"xverse-moe-a4.2b","r":1296,"s":23.01,"lo":1214,"hi":1328,"n":10,"rr":769,"mr":1307},{"m":"qwen3-0.6b-base","r":1297,"s":22.94,"lo":1236,"hi":1413,"n":9,"rr":1138,"mr":1316},{"m":"xgen-mm-interleave-4b","r":1298,"s":22.94,"lo":1176,"hi":1383,"n":13,"rr":718,"mr":1348},{"m":"internlm2-base-20b","r":1299,"s":22.92,"lo":1225,"hi":1337,"n":13,"rr":1163,"mr":1286},{"m":"phi-2","r":1300,"s":22.9,"lo":1240,"hi":1359,"n":19,"rr":1209,"mr":1275},{"m":"llm-jp-3.1-1.8b-instruct4","r":1301,"s":22.83,"lo":1215,"hi":1377,"n":10,"rr":1463,"mr":1328},{"m":"qwen3-0.8b","r":1302,"s":22.82,"lo":1249,"hi":1372,"n":21,"rr":1459,"mr":1262},{"m":"olmo-2-1124-7b","r":1303,"s":22.74,"lo":1222,"hi":1424,"n":20,"rr":1148,"mr":1315},{"m":"apertus-8b","r":1304,"s":22.72,"lo":1238,"hi":1353,"n":22,"rr":1080,"mr":1302},{"m":"qwen-7b","r":1305,"s":22.64,"lo":1236,"hi":1341,"n":28,"rr":857,"mr":1268},{"m":"deepseek-coder-6.7b-base","r":1306,"s":22.61,"lo":1242,"hi":1369,"n":24,"rr":1368,"mr":1284},{"m":"idefics2-8b","r":1307,"s":22.6,"lo":1196,"hi":1370,"n":12,"rr":907,"mr":1356},{"m":"gemma-1.1-7b-it","r":1308,"s":22.56,"lo":1274,"hi":1338,"n":11,"rr":1387,"mr":1298},{"m":"internlm2.5-1.8b-chat","r":1309,"s":22.56,"lo":1247,"hi":1343,"n":17,"rr":1243,"mr":1293},{"m":"sarashina2.2-1b-instruct-v0.1","r":1310,"s":22.29,"lo":1245,"hi":1364,"n":10,"rr":1477,"mr":1334},{"m":"chatglm3-6b","r":1311,"s":22.28,"lo":1250,"hi":1365,"n":27,"rr":1237,"mr":1287},{"m":"minicpm-2b-sft","r":1312,"s":22.26,"lo":1275,"hi":1338,"n":12,"rr":1132,"mr":1291},{"m":"llava-internlm2-20b-qlora","r":1313,"s":22.18,"lo":1198,"hi":1385,"n":11,"rr":864,"mr":1366},{"m":"qwen2.5-coder-0.5b-instruct","r":1314,"s":22.17,"lo":1199,"hi":1439,"n":10,"rr":1458,"mr":1333},{"m":"qwen2-1.5b-instruct","r":1315,"s":22.17,"lo":1252,"hi":1371,"n":21,"rr":1432,"mr":1299},{"m":"phi-3.5-vision-4b","r":1316,"s":22.15,"lo":1167,"hi":1382,"n":11,"rr":794,"mr":1362},{"m":"qwen2-1.5b","r":1317,"s":22.15,"lo":1275,"hi":1352,"n":21,"rr":1299,"mr":1292},{"m":"cogagent-18b","r":1318,"s":22.02,"lo":1246,"hi":1359,"n":10,"rr":1063,"mr":1355},{"m":"mobilemoe-m","r":1319,"s":21.94,"lo":1256,"hi":1357,"n":20,"rr":1094,"mr":1296},{"m":"llava-1.6-13b","r":1320,"s":21.9,"lo":1269,"hi":1357,"n":15,"rr":922,"mr":1357},{"m":"palm-540b","r":1321,"s":21.88,"lo":697,"hi":1369,"n":12,"rr":256,"mr":1320},{"m":"map-neo-7b-sft","r":1322,"s":21.87,"lo":1251,"hi":1359,"n":23,"rr":1173,"mr":1301},{"m":"gemma-2-7b","r":1323,"s":21.84,"lo":1274,"hi":1352,"n":16,"rr":949,"mr":1318},{"m":"codeqwen1.5-7b","r":1324,"s":21.8,"lo":1217,"hi":1390,"n":20,"rr":1367,"mr":1304},{"m":"deepseek-llm-7b-chat","r":1325,"s":21.79,"lo":1278,"hi":1357,"n":27,"rr":1028,"mr":1300},{"m":"intern-decision-2b","r":1326,"s":21.76,"lo":1204,"hi":1387,"n":28,"rr":1285,"mr":1290},{"m":"bluelm-7b-chat","r":1327,"s":21.72,"lo":1200,"hi":1368,"n":9,"rr":1189,"mr":1327},{"m":"x-omni","r":1328,"s":21.31,"lo":1217,"hi":1437,"n":8,"rr":1353,"mr":1337},{"m":"mistral-7b-instruct-v0.2","r":1329,"s":21.19,"lo":1288,"hi":1362,"n":40,"rr":1191,"mr":1305},{"m":"llama-1-65b","r":1330,"s":21.07,"lo":1256,"hi":1373,"n":26,"rr":871,"mr":1314},{"m":"deepseek-v2-lite","r":1331,"s":21.07,"lo":1266,"hi":1361,"n":28,"rr":924,"mr":1313},{"m":"lfm2.5-vl-450m","r":1332,"s":21,"lo":1268,"hi":1379,"n":16,"rr":1239,"mr":1336},{"m":"mistral-7b","r":1333,"s":20.9,"lo":1283,"hi":1366,"n":28,"rr":1213,"mr":1311},{"m":"mistral-7b-v0.1","r":1334,"s":20.9,"lo":1308,"hi":1365,"n":35,"rr":1221,"mr":1312},{"m":"cogvlm-17b-chat","r":1335,"s":20.87,"lo":1266,"hi":1408,"n":26,"rr":826,"mr":1389},{"m":"minicpm-2b-dpo-fp32","r":1336,"s":20.83,"lo":1280,"hi":1380,"n":12,"rr":1061,"mr":1325},{"m":"gemma-3-1b-it","r":1337,"s":20.79,"lo":1286,"hi":1396,"n":35,"rr":1460,"mr":1309},{"m":"deepseek-moe-16b-chat","r":1338,"s":20.77,"lo":1290,"hi":1388,"n":21,"rr":1089,"mr":1321},{"m":"mm1.5-1b","r":1339,"s":20.74,"lo":1276,"hi":1386,"n":9,"rr":895,"mr":1385},{"m":"codellama-7b-instruct","r":1340,"s":20.48,"lo":1304,"hi":1425,"n":12,"rr":1483,"mr":1335},{"m":"deepseek-vl-7b","r":1341,"s":20.4,"lo":1302,"hi":1399,"n":25,"rr":1054,"mr":1364},{"m":"qwen2.5-0.5b-instruct","r":1342,"s":20.35,"lo":1303,"hi":1387,"n":16,"rr":1488,"mr":1332},{"m":"baichuan2-13b-base","r":1343,"s":20.33,"lo":1302,"hi":1371,"n":39,"rr":987,"mr":1322},{"m":"tigerbot-13b-chat","r":1344,"s":20.28,"lo":1299,"hi":1371,"n":13,"rr":781,"mr":1363},{"m":"skywork-13b-base","r":1345,"s":20.24,"lo":1278,"hi":1392,"n":31,"rr":776,"mr":1323},{"m":"solar-10.7b-v1.0","r":1346,"s":20.16,"lo":1298,"hi":1402,"n":9,"rr":1126,"mr":1349},{"m":"llama-3.2-1.24b","r":1347,"s":20.16,"lo":1301,"hi":1398,"n":10,"rr":1468,"mr":1345},{"m":"internlm2-base-7b","r":1348,"s":20.13,"lo":1289,"hi":1391,"n":18,"rr":1232,"mr":1330},{"m":"yi-6b-chat","r":1349,"s":20.12,"lo":1274,"hi":1427,"n":14,"rr":1105,"mr":1343},{"m":"vllm-sr-d3-edge","r":1350,"s":20.04,"lo":1212,"hi":1395,"n":27,"rr":1321,"mr":1324},{"m":"t5gemma-2-4b-4b","r":1351,"s":19.91,"lo":1328,"hi":1375,"n":32,"rr":1071,"mr":1339},{"m":"llava-next-7b","r":1352,"s":19.87,"lo":1264,"hi":1385,"n":8,"rr":1025,"mr":1408},{"m":"minicpm-v-2.0-3b","r":1353,"s":19.83,"lo":1309,"hi":1391,"n":19,"rr":854,"mr":1406},{"m":"smolvlm2-2.2b","r":1354,"s":19.77,"lo":1308,"hi":1411,"n":39,"rr":1281,"mr":1374},{"m":"starcoderbase-16b","r":1355,"s":19.73,"lo":1282,"hi":1418,"n":8,"rr":1439,"mr":1350},{"m":"qwen-7b-chat","r":1356,"s":19.56,"lo":1326,"hi":1390,"n":27,"rr":1253,"mr":1342},{"m":"minicpm4-0.5b","r":1357,"s":19.56,"lo":1307,"hi":1411,"n":11,"rr":886,"mr":1347},{"m":"sharegpt4v-7b","r":1358,"s":19.56,"lo":1299,"hi":1417,"n":13,"rr":1166,"mr":1410},{"m":"yi-vl-34b","r":1359,"s":19.53,"lo":1251,"hi":1436,"n":13,"rr":1147,"mr":1412},{"m":"qwen1.5-4b","r":1360,"s":19.47,"lo":1282,"hi":1400,"n":8,"rr":1334,"mr":1358},{"m":"xverse-7b","r":1361,"s":19.42,"lo":1241,"hi":1453,"n":10,"rr":1049,"mr":1388},{"m":"internvl2-2b","r":1362,"s":19.3,"lo":1329,"hi":1391,"n":63,"rr":1245,"mr":1376},{"m":"granite-4-h-300m","r":1363,"s":19.24,"lo":1252,"hi":1423,"n":11,"rr":1476,"mr":1341},{"m":"internlm-chat-20b","r":1364,"s":19.23,"lo":1321,"hi":1393,"n":9,"rr":968,"mr":1387},{"m":"starcoder2-7b","r":1365,"s":19.13,"lo":1301,"hi":1418,"n":20,"rr":1428,"mr":1352},{"m":"tev1-0.8b-experimental","r":1366,"s":19.12,"lo":1289,"hi":1406,"n":25,"rr":1354,"mr":1340},{"m":"telechat-7b","r":1367,"s":19.12,"lo":1219,"hi":1403,"n":11,"rr":1266,"mr":1361},{"m":"vllm-sr-decision-2.0-eos-0.8b","r":1368,"s":19.12,"lo":1276,"hi":1412,"n":27,"rr":1388,"mr":1338},{"m":"olmoe-1b-7b-base","r":1369,"s":19.09,"lo":1294,"hi":1493,"n":17,"rr":1242,"mr":1378},{"m":"map-neo-7b","r":1370,"s":19.01,"lo":1331,"hi":1401,"n":21,"rr":1176,"mr":1351},{"m":"llama-1-33b","r":1371,"s":19.01,"lo":1305,"hi":1405,"n":24,"rr":1043,"mr":1354},{"m":"zephyr-7b-beta","r":1372,"s":18.99,"lo":1305,"hi":1410,"n":8,"rr":1384,"mr":1368},{"m":"olmoe-1b-7b","r":1373,"s":18.97,"lo":1337,"hi":1406,"n":29,"rr":1399,"mr":1346},{"m":"lfm2-350m","r":1374,"s":18.93,"lo":1231,"hi":1416,"n":14,"rr":1469,"mr":1344},{"m":"aquila2-7b","r":1375,"s":18.85,"lo":1261,"hi":1416,"n":13,"rr":809,"mr":1391},{"m":"gpt-3","r":1376,"s":18.65,"lo":1214,"hi":1417,"n":15,"rr":558,"mr":1379},{"m":"qwen2.5-0.5b","r":1377,"s":18.65,"lo":1341,"hi":1419,"n":31,"rr":1472,"mr":1353},{"m":"internlm2-chat-1.8b","r":1378,"s":18.63,"lo":1340,"hi":1401,"n":16,"rr":1349,"mr":1360},{"m":"codellama-7b","r":1379,"s":18.6,"lo":1312,"hi":1426,"n":22,"rr":1369,"mr":1373},{"m":"smollm2-1.7b-instruct","r":1380,"s":18.38,"lo":1342,"hi":1425,"n":25,"rr":1400,"mr":1359},{"m":"llama-3.2-1b-instruct","r":1381,"s":18.36,"lo":1356,"hi":1420,"n":30,"rr":1492,"mr":1370},{"m":"stablelm-zephyr-3b","r":1382,"s":18.29,"lo":1352,"hi":1417,"n":12,"rr":1271,"mr":1369},{"m":"rakutenai-2.0-mini-instruct","r":1383,"s":18.23,"lo":1331,"hi":1434,"n":10,"rr":1487,"mr":1397},{"m":"internlm-chat-7b","r":1384,"s":18.22,"lo":1261,"hi":1423,"n":13,"rr":1110,"mr":1395},{"m":"minicpm-1b-sft","r":1385,"s":18.18,"lo":1341,"hi":1409,"n":11,"rr":1273,"mr":1377},{"m":"sphinx-2k","r":1386,"s":17.92,"lo":1244,"hi":1427,"n":9,"rr":786,"mr":1433},{"m":"monkey","r":1387,"s":17.79,"lo":1294,"hi":1446,"n":12,"rr":1101,"mr":1431},{"m":"olmo-2-0425-1b-instruct","r":1388,"s":17.77,"lo":1341,"hi":1435,"n":24,"rr":1413,"mr":1372},{"m":"vllm-sr-decision-2.0-kai-0.6b","r":1389,"s":17.75,"lo":1314,"hi":1433,"n":27,"rr":1410,"mr":1365},{"m":"paligemma-mix-3b","r":1390,"s":17.74,"lo":1210,"hi":1462,"n":13,"rr":1074,"mr":1432},{"m":"baichuan2-13b-chat","r":1391,"s":17.73,"lo":1339,"hi":1415,"n":26,"rr":1288,"mr":1375},{"m":"falcon-40b","r":1392,"s":17.67,"lo":1331,"hi":1435,"n":18,"rr":1172,"mr":1381},{"m":"gemma-3-1b","r":1393,"s":17.67,"lo":1309,"hi":1436,"n":39,"rr":1449,"mr":1380},{"m":"intern-decision-0.8b","r":1394,"s":17.61,"lo":1323,"hi":1434,"n":28,"rr":1394,"mr":1367},{"m":"granite-4-300m","r":1395,"s":17.42,"lo":1313,"hi":1444,"n":11,"rr":1486,"mr":1371},{"m":"falcon3-1b","r":1396,"s":17.36,"lo":1363,"hi":1438,"n":21,"rr":1480,"mr":1383},{"m":"internvl2-1b","r":1397,"s":17.29,"lo":1342,"hi":1418,"n":47,"rr":1286,"mr":1428},{"m":"mistral-7b-instruct-v0.1","r":1398,"s":17.29,"lo":1348,"hi":1443,"n":15,"rr":1254,"mr":1382},{"m":"starcoder2-3b","r":1399,"s":17.25,"lo":1332,"hi":1447,"n":20,"rr":1441,"mr":1386},{"m":"bluelm-7b-base","r":1400,"s":17.24,"lo":1275,"hi":1432,"n":9,"rr":1342,"mr":1407},{"m":"qwen2.5-coder-0.5b","r":1401,"s":17.16,"lo":1348,"hi":1448,"n":19,"rr":1448,"mr":1392},{"m":"bitcpm-cann-0.5b","r":1402,"s":17.13,"lo":1365,"hi":1440,"n":11,"rr":1091,"mr":1390},{"m":"yi-6b","r":1403,"s":17.09,"lo":1329,"hi":1435,"n":13,"rr":1210,"mr":1400},{"m":"mobilellm-p1-base","r":1404,"s":16.9,"lo":1374,"hi":1426,"n":10,"rr":958,"mr":1393},{"m":"mobilemoe-s","r":1405,"s":16.81,"lo":1365,"hi":1433,"n":20,"rr":1339,"mr":1396},{"m":"d1-omni-600m","r":1406,"s":16.72,"lo":1346,"hi":1441,"n":32,"rr":1374,"mr":1384},{"m":"llama-2-13b","r":1407,"s":16.67,"lo":1371,"hi":1435,"n":40,"rr":1160,"mr":1394},{"m":"internlm-xcomposer","r":1408,"s":16.66,"lo":1290,"hi":1453,"n":12,"rr":1171,"mr":1442},{"m":"tigerbot-13b-base","r":1409,"s":16.61,"lo":1359,"hi":1429,"n":13,"rr":983,"mr":1424},{"m":"deepseek-coder-1.3b-base","r":1410,"s":16.6,"lo":1350,"hi":1466,"n":22,"rr":1465,"mr":1403},{"m":"qwen-vl-chat","r":1411,"s":16.46,"lo":1371,"hi":1446,"n":26,"rr":789,"mr":1445},{"m":"deepseek-llm-7b-base","r":1412,"s":16.46,"lo":1361,"hi":1440,"n":27,"rr":1144,"mr":1398},{"m":"baichuan2-7b-chat","r":1413,"s":16.45,"lo":1372,"hi":1436,"n":24,"rr":1328,"mr":1399},{"m":"gemma-2-2b","r":1414,"s":16.42,"lo":1377,"hi":1440,"n":35,"rr":1415,"mr":1401},{"m":"qwen2-0.5b-instruct","r":1415,"s":16.4,"lo":1379,"hi":1451,"n":13,"rr":1484,"mr":1416},{"m":"internlm-7b","r":1416,"s":16.27,"lo":1366,"hi":1435,"n":25,"rr":1177,"mr":1405},{"m":"janus-pro-7b","r":1417,"s":16.24,"lo":1375,"hi":1452,"n":18,"rr":1331,"mr":1429},{"m":"yi-vl-6b","r":1418,"s":16.22,"lo":1321,"hi":1461,"n":15,"rr":1193,"mr":1446},{"m":"qwen1.5-1.8b-chat","r":1419,"s":16.2,"lo":1383,"hi":1448,"n":9,"rr":1411,"mr":1425},{"m":"baichuan2-7b-base","r":1420,"s":16.19,"lo":1376,"hi":1443,"n":33,"rr":1240,"mr":1402},{"m":"llava-1.5-13b","r":1421,"s":16.09,"lo":1356,"hi":1456,"n":28,"rr":1134,"mr":1441},{"m":"emu2-chat","r":1422,"s":16.04,"lo":1349,"hi":1451,"n":15,"rr":1096,"mr":1448},{"m":"llava-onevision-0.5b","r":1423,"s":15.97,"lo":1393,"hi":1447,"n":21,"rr":1322,"mr":1444},{"m":"xverse-13b","r":1424,"s":15.9,"lo":1368,"hi":1455,"n":26,"rr":1205,"mr":1404},{"m":"baichuan-13b-base","r":1425,"s":15.9,"lo":1388,"hi":1442,"n":23,"rr":1249,"mr":1411},{"m":"lfm2-vl-450m","r":1426,"s":15.85,"lo":1367,"hi":1451,"n":15,"rr":1341,"mr":1420},{"m":"qwen2-0.5b","r":1427,"s":15.73,"lo":1394,"hi":1447,"n":20,"rr":1445,"mr":1414},{"m":"qwen1.5-1.8b","r":1428,"s":15.72,"lo":1393,"hi":1442,"n":13,"rr":1335,"mr":1418},{"m":"mpt-30b","r":1429,"s":15.67,"lo":1371,"hi":1458,"n":18,"rr":1303,"mr":1422},{"m":"llama-3.2-1.24b-base","r":1430,"s":15.58,"lo":1379,"hi":1464,"n":22,"rr":1490,"mr":1413},{"m":"deepseek-moe-16b-base","r":1431,"s":15.46,"lo":1380,"hi":1449,"n":24,"rr":1218,"mr":1419},{"m":"gemma-4-e2b","r":1432,"s":15.44,"lo":1155,"hi":1454,"n":17,"rr":1014,"mr":1417},{"m":"huginn-3.5b","r":1433,"s":15.39,"lo":1390,"hi":1461,"n":8,"rr":1364,"mr":1426},{"m":"chatglm2-6b","r":1434,"s":15.35,"lo":1396,"hi":1447,"n":28,"rr":1236,"mr":1423},{"m":"smollm2-1.7b-base","r":1435,"s":15.28,"lo":1395,"hi":1462,"n":15,"rr":1436,"mr":1409},{"m":"gemma-2b","r":1436,"s":15.08,"lo":1398,"hi":1453,"n":17,"rr":1419,"mr":1421},{"m":"mplug-owl2","r":1437,"s":15.07,"lo":1350,"hi":1461,"n":13,"rr":1048,"mr":1456},{"m":"gliner2.5-decide","r":1438,"s":15.04,"lo":1340,"hi":1461,"n":28,"rr":1450,"mr":1415},{"m":"chatglm2-6b-base","r":1439,"s":14.9,"lo":1409,"hi":1453,"n":14,"rr":1289,"mr":1436},{"m":"gemini-nano-2","r":1440,"s":14.88,"lo":1408,"hi":1453,"n":10,"rr":1287,"mr":1450},{"m":"telechat-1b","r":1441,"s":14.82,"lo":1405,"hi":1450,"n":11,"rr":1427,"mr":1437},{"m":"minicpm-v","r":1442,"s":14.68,"lo":1361,"hi":1467,"n":11,"rr":1155,"mr":1459},{"m":"mobilellm-p1","r":1443,"s":14.55,"lo":1397,"hi":1461,"n":20,"rr":1373,"mr":1427},{"m":"emu3-8b","r":1444,"s":14.4,"lo":1336,"hi":1480,"n":15,"rr":1346,"mr":1451},{"m":"janus-pro-1.5b","r":1445,"s":14.32,"lo":1346,"hi":1489,"n":10,"rr":1300,"mr":1457},{"m":"open-llama-13b","r":1446,"s":14.29,"lo":1375,"hi":1470,"n":12,"rr":1037,"mr":1449},{"m":"llama-2-13b-chat","r":1447,"s":14.29,"lo":1403,"hi":1460,"n":35,"rr":1329,"mr":1435},{"m":"llama-1-13b","r":1448,"s":14.05,"lo":1415,"hi":1457,"n":29,"rr":1274,"mr":1434},{"m":"olmo-1.7-7b","r":1449,"s":13.89,"lo":1423,"hi":1456,"n":20,"rr":1340,"mr":1438},{"m":"moshi","r":1450,"s":13.89,"lo":807,"hi":1469,"n":10,"rr":1395,"mr":1461},{"m":"qwen-vl","r":1451,"s":13.84,"lo":1383,"hi":1477,"n":17,"rr":841,"mr":1462},{"m":"qwen-1.8b","r":1452,"s":13.78,"lo":1424,"hi":1459,"n":19,"rr":1326,"mr":1439},{"m":"laya","r":1453,"s":13.32,"lo":1354,"hi":1477,"n":27,"rr":1457,"mr":1430},{"m":"llama-2-7b","r":1454,"s":13.15,"lo":1433,"hi":1461,"n":45,"rr":1361,"mr":1440},{"m":"vicuna-13b","r":1455,"s":13.09,"lo":1436,"hi":1461,"n":17,"rr":1455,"mr":1447},{"m":"lumina-dimoo","r":1456,"s":13.07,"lo":1333,"hi":1486,"n":19,"rr":1433,"mr":1460},{"m":"llama-2-7b-chat","r":1457,"s":12.97,"lo":1438,"hi":1465,"n":40,"rr":1406,"mr":1443},{"m":"llava-1.5-7b","r":1458,"s":12.85,"lo":1410,"hi":1474,"n":21,"rr":1292,"mr":1468},{"m":"alpamayo-1.5-10b","r":1459,"s":12.8,"lo":1372,"hi":1492,"n":13,"rr":1491,"mr":1452},{"m":"llama-3.2-1b","r":1460,"s":12.5,"lo":1431,"hi":1472,"n":21,"rr":1383,"mr":1453},{"m":"mpt-7b","r":1461,"s":12.04,"lo":1437,"hi":1473,"n":28,"rr":1381,"mr":1454},{"m":"chinese-alpaca-plus-13b","r":1462,"s":11.86,"lo":1443,"hi":1470,"n":14,"rr":1466,"mr":1463},{"m":"llama-1-7b","r":1463,"s":11.79,"lo":1448,"hi":1473,"n":28,"rr":1371,"mr":1455},{"m":"deepseek-vl-1.3b","r":1464,"s":11.68,"lo":1437,"hi":1480,"n":20,"rr":1248,"mr":1474},{"m":"qwen1.5-0.5b","r":1465,"s":11.57,"lo":1447,"hi":1474,"n":8,"rr":1482,"mr":1465},{"m":"t5gemma-2-1b-1b","r":1466,"s":11.54,"lo":1452,"hi":1471,"n":32,"rr":1396,"mr":1458},{"m":"smolvlm2-0.5b","r":1467,"s":11.32,"lo":1417,"hi":1484,"n":20,"rr":1403,"mr":1473},{"m":"olmo-7b-instruct","r":1468,"s":11.23,"lo":1455,"hi":1475,"n":25,"rr":1418,"mr":1464},{"m":"baichuan-7b","r":1469,"s":11.22,"lo":1447,"hi":1477,"n":17,"rr":1452,"mr":1467},{"m":"idefics-80b-instruct","r":1470,"s":10.96,"lo":1437,"hi":1486,"n":13,"rr":1375,"mr":1482},{"m":"vicuna-7b","r":1471,"s":10.96,"lo":1459,"hi":1475,"n":13,"rr":1407,"mr":1466},{"m":"falcon-7b","r":1472,"s":10.45,"lo":1452,"hi":1483,"n":25,"rr":1426,"mr":1470},{"m":"qwen1.5-0.5b-chat","r":1473,"s":10.45,"lo":1457,"hi":1477,"n":8,"rr":1478,"mr":1477},{"m":"llava-v1-7b","r":1474,"s":10.45,"lo":1419,"hi":1488,"n":12,"rr":1385,"mr":1484},{"m":"amberchat","r":1475,"s":10.35,"lo":1463,"hi":1478,"n":23,"rr":1454,"mr":1469},{"m":"instructblip-7b","r":1476,"s":10.19,"lo":1425,"hi":1488,"n":14,"rr":1318,"mr":1486},{"m":"amber-7b","r":1477,"s":9.73,"lo":1467,"hi":1484,"n":20,"rr":1451,"mr":1472},{"m":"gemma-3-270m-it","r":1478,"s":9.33,"lo":1464,"hi":1488,"n":25,"rr":1485,"mr":1471},{"m":"alpaca-7b","r":1479,"s":9.15,"lo":1469,"hi":1486,"n":10,"rr":1461,"mr":1479},{"m":"olmo-7b","r":1480,"s":9.13,"lo":1469,"hi":1486,"n":20,"rr":1443,"mr":1478},{"m":"smollm2-360m-instruct","r":1481,"s":9.1,"lo":1471,"hi":1486,"n":22,"rr":1473,"mr":1475},{"m":"pythia-6.9b","r":1482,"s":9.06,"lo":1473,"hi":1486,"n":24,"rr":1425,"mr":1480},{"m":"pythia-12b","r":1483,"s":8.99,"lo":1470,"hi":1486,"n":24,"rr":1416,"mr":1481},{"m":"smollm2-135m-instruct","r":1484,"s":8.81,"lo":1472,"hi":1490,"n":8,"rr":1489,"mr":1476},{"m":"tinyllama-1.1b","r":1485,"s":8.32,"lo":1472,"hi":1490,"n":11,"rr":1481,"mr":1483},{"m":"smollm1-1.7b-pretrained","r":1486,"s":7.93,"lo":1455,"hi":1490,"n":8,"rr":1390,"mr":1489},{"m":"gemma-3-pt-270m","r":1487,"s":7.33,"lo":1474,"hi":1492,"n":10,"rr":1429,"mr":1487},{"m":"chatglm-6b","r":1488,"s":7.28,"lo":1477,"hi":1493,"n":15,"rr":1479,"mr":1491},{"m":"smollm2-360m-base","r":1489,"s":7.03,"lo":1484,"hi":1493,"n":9,"rr":1493,"mr":1485},{"m":"t5gemma-2-270m-270m","r":1490,"s":6.89,"lo":1482,"hi":1493,"n":32,"rr":1470,"mr":1488},{"m":"minigpt-4-v1-7b","r":1491,"s":6.53,"lo":1459,"hi":1493,"n":9,"rr":1474,"mr":1492},{"m":"openflamingo-v2","r":1492,"s":6.24,"lo":1473,"hi":1493,"n":11,"rr":1475,"mr":1493},{"m":"smollm2-135m-base","r":1493,"s":6.12,"lo":1487,"hi":1493,"n":9,"rr":1471,"mr":1490}]},"core":{"name":"Fu Core (AA-style curated)","n":334,"nb":18,"acc":0.816,"raw_acc":0.6932,"rows":[{"m":"claude-sonnet-5.5","r":1,"s":79.17,"lo":1,"hi":8,"n":4,"rr":35,"mr":1},{"m":"claude-opus-5.5","r":2,"s":78.12,"lo":1,"hi":4,"n":6,"rr":95,"mr":2},{"m":"kimi-k3.1-pro","r":3,"s":77.82,"lo":2,"hi":14,"n":3,"rr":100,"mr":3},{"m":"claude-fable-5.1","r":4,"s":74.85,"lo":3,"hi":6,"n":8,"rr":52,"mr":5},{"m":"claude-opus-5","r":5,"s":74.84,"lo":1,"hi":6,"n":8,"rr":56,"mr":4},{"m":"gpt-6-astra","r":6,"s":74.41,"lo":4,"hi":12,"n":7,"rr":54,"mr":6},{"m":"claude-mythos-5","r":7,"s":72.23,"lo":4,"hi":13,"n":5,"rr":44,"mr":8},{"m":"claude-fable-5","r":8,"s":71.81,"lo":6,"hi":13,"n":12,"rr":59,"mr":7},{"m":"gpt-5.6-sol","r":9,"s":71.53,"lo":4,"hi":15,"n":11,"rr":61,"mr":9},{"m":"grok-4.7","r":10,"s":71.06,"lo":7,"hi":27,"n":3,"rr":140,"mr":10},{"m":"claude-haiku-5.5","r":11,"s":70.21,"lo":10,"hi":38,"n":4,"rr":168,"mr":11},{"m":"veriloop-e2","r":12,"s":69.67,"lo":11,"hi":44,"n":3,"rr":6,"mr":12},{"m":"deepseek-v4.1-flash-1017","r":13,"s":69.65,"lo":8,"hi":43,"n":4,"rr":232,"mr":13},{"m":"mimo-v2.6-pro-rl","r":14,"s":69.45,"lo":9,"hi":20,"n":3,"rr":55,"mr":15},{"m":"grok-4.6","r":15,"s":69.09,"lo":8,"hi":18,"n":4,"rr":69,"mr":16},{"m":"glm-5.3","r":16,"s":67.82,"lo":13,"hi":38,"n":10,"rr":108,"mr":14},{"m":"kimi-k3","r":17,"s":66.88,"lo":8,"hi":23,"n":11,"rr":58,"mr":18},{"m":"ling-3.1-flash","r":18,"s":66.46,"lo":8,"hi":41,"n":5,"rr":175,"mr":21},{"m":"claude-opus-4.8","r":19,"s":66.38,"lo":13,"hi":23,"n":12,"rr":79,"mr":22},{"m":"deepseek-v4.1-flash","r":20,"s":66.29,"lo":16,"hi":36,"n":8,"rr":89,"mr":19},{"m":"gemini-3.8-flash","r":21,"s":66.02,"lo":7,"hi":29,"n":5,"rr":78,"mr":24},{"m":"qwen3.8-max","r":22,"s":65.95,"lo":10,"hi":29,"n":9,"rr":34,"mr":17},{"m":"gpt-5.6-terra","r":23,"s":65.84,"lo":15,"hi":26,"n":8,"rr":114,"mr":23},{"m":"glm-5.3-flash","r":24,"s":65.37,"lo":18,"hi":33,"n":12,"rr":64,"mr":20},{"m":"gpt-6-sol","r":25,"s":64.5,"lo":15,"hi":54,"n":3,"rr":220,"mr":30},{"m":"gpt-5.5","r":26,"s":63.42,"lo":16,"hi":37,"n":13,"rr":31,"mr":25},{"m":"qwen3.8-flash-next","r":27,"s":63.37,"lo":21,"hi":59,"n":11,"rr":39,"mr":26},{"m":"claude-mythos-preview","r":28,"s":62.94,"lo":7,"hi":69,"n":3,"rr":2,"mr":32},{"m":"claude-sonnet-5","r":29,"s":62.89,"lo":21,"hi":39,"n":10,"rr":153,"mr":27},{"m":"grok-4.5","r":30,"s":62.79,"lo":25,"hi":42,"n":4,"rr":167,"mr":31},{"m":"hy4-preview","r":31,"s":62.47,"lo":22,"hi":39,"n":4,"rr":42,"mr":29},{"m":"gpt-5.6-luna","r":32,"s":61.99,"lo":23,"hi":41,"n":8,"rr":65,"mr":28},{"m":"deepseek-v4-pro-0813","r":33,"s":61.39,"lo":21,"hi":38,"n":6,"rr":144,"mr":33},{"m":"gpt-6-luna","r":34,"s":61.15,"lo":27,"hi":53,"n":3,"rr":275,"mr":35},{"m":"gemini-3.7-flash","r":35,"s":60.54,"lo":17,"hi":45,"n":4,"rr":195,"mr":36},{"m":"ornith-1.5-397b","r":36,"s":59.81,"lo":27,"hi":74,"n":3,"rr":4,"mr":37},{"m":"sage-a1.5","r":37,"s":59.78,"lo":23,"hi":156,"n":3,"rr":170,"mr":47},{"m":"fugu-ultra","r":38,"s":59.65,"lo":18,"hi":59,"n":5,"rr":11,"mr":34},{"m":"gpt-5.4","r":39,"s":58.84,"lo":17,"hi":53,"n":9,"rr":14,"mr":41},{"m":"muse-spark-1.2","r":40,"s":58.59,"lo":30,"hi":62,"n":3,"rr":136,"mr":43},{"m":"fugu","r":41,"s":58.52,"lo":21,"hi":54,"n":5,"rr":12,"mr":40},{"m":"gemini-3.1-pro","r":42,"s":57.81,"lo":18,"hi":58,"n":13,"rr":77,"mr":38},{"m":"glm-5.2","r":43,"s":57.02,"lo":28,"hi":57,"n":11,"rr":94,"mr":42},{"m":"beam","r":44,"s":56.9,"lo":35,"hi":56,"n":6,"rr":28,"mr":44},{"m":"deepseek-v4-flash-0731","r":45,"s":56.88,"lo":32,"hi":48,"n":12,"rr":83,"mr":39},{"m":"claude-opus-4.7","r":46,"s":56.75,"lo":28,"hi":130,"n":8,"rr":8,"mr":46},{"m":"gemini-3.6-flash","r":47,"s":56.64,"lo":34,"hi":60,"n":3,"rr":166,"mr":49},{"m":"claude-opus-4.6","r":48,"s":55.76,"lo":27,"hi":57,"n":11,"rr":47,"mr":45},{"m":"gemini-3.5-flash","r":49,"s":55.44,"lo":34,"hi":54,"n":9,"rr":41,"mr":48},{"m":"ornith-1.5-122b","r":50,"s":54,"lo":42,"hi":109,"n":3,"rr":86,"mr":53},{"m":"gpt-5.2","r":51,"s":52.76,"lo":31,"hi":70,"n":8,"rr":21,"mr":54},{"m":"gpt-5.2-extra-high","r":52,"s":52.29,"lo":45,"hi":77,"n":3,"rr":189,"mr":60},{"m":"deepseek-v4-pro","r":53,"s":51.92,"lo":31,"hi":86,"n":11,"rr":93,"mr":56},{"m":"qwen3.7-max","r":54,"s":51.64,"lo":43,"hi":72,"n":9,"rr":27,"mr":50},{"m":"muse-spark-open","r":55,"s":51.62,"lo":45,"hi":84,"n":4,"rr":23,"mr":57},{"m":"gpt-5.2-high","r":56,"s":51.43,"lo":46,"hi":80,"n":3,"rr":198,"mr":62},{"m":"deepseek-v4-pro-thinking-max","r":57,"s":51.09,"lo":48,"hi":66,"n":11,"rr":57,"mr":51},{"m":"gpt-5.2-thinking-xhigh","r":58,"s":50.8,"lo":28,"hi":90,"n":7,"rr":36,"mr":63},{"m":"gemini-3-pro","r":59,"s":50.57,"lo":47,"hi":77,"n":10,"rr":73,"mr":55},{"m":"nex-n2-pro","r":60,"s":50.49,"lo":50,"hi":85,"n":3,"rr":7,"mr":64},{"m":"kimi-k2.6-thinking","r":61,"s":50.33,"lo":52,"hi":69,"n":13,"rr":71,"mr":52},{"m":"claude-sonnet-4.6","r":62,"s":50.11,"lo":48,"hi":78,"n":10,"rr":43,"mr":58},{"m":"claude-opus-4.5-thinking","r":63,"s":49.74,"lo":45,"hi":97,"n":5,"rr":22,"mr":67},{"m":"glm-5.1","r":64,"s":49.01,"lo":40,"hi":74,"n":13,"rr":88,"mr":59},{"m":"k2-horizon-375b-a23b","r":65,"s":48.67,"lo":48,"hi":76,"n":6,"rr":107,"mr":61},{"m":"qwen3.8-omni-flash","r":66,"s":48.64,"lo":53,"hi":88,"n":3,"rr":16,"mr":70},{"m":"ornith-1.0-397b","r":67,"s":48.24,"lo":53,"hi":119,"n":3,"rr":30,"mr":66},{"m":"gemini-3-pro-preview","r":68,"s":47.33,"lo":50,"hi":140,"n":6,"rr":49,"mr":65},{"m":"qwen3.7-plus","r":69,"s":46.2,"lo":57,"hi":78,"n":7,"rr":92,"mr":68},{"m":"mimo-v2-pro","r":70,"s":45.71,"lo":59,"hi":106,"n":4,"rr":90,"mr":80},{"m":"seed2.1-pro","r":71,"s":45.32,"lo":63,"hi":104,"n":5,"rr":10,"mr":73},{"m":"hy3","r":72,"s":45.12,"lo":63,"hi":87,"n":6,"rr":74,"mr":71},{"m":"motif-3","r":73,"s":45.06,"lo":63,"hi":94,"n":7,"rr":38,"mr":69},{"m":"qwen3.8-27b","r":74,"s":44.97,"lo":47,"hi":140,"n":10,"rr":128,"mr":72},{"m":"glm-5","r":75,"s":44.23,"lo":51,"hi":106,"n":7,"rr":33,"mr":79},{"m":"claude-opus-4.5","r":76,"s":44.18,"lo":43,"hi":109,"n":10,"rr":98,"mr":77},{"m":"deepseek-v4-pro-thinking","r":77,"s":43.8,"lo":70,"hi":94,"n":3,"rr":48,"mr":83},{"m":"grok-4.2","r":78,"s":43.71,"lo":68,"hi":137,"n":5,"rr":60,"mr":85},{"m":"minimax-m3","r":79,"s":43.5,"lo":51,"hi":126,"n":10,"rr":101,"mr":76},{"m":"inkling","r":80,"s":43.32,"lo":62,"hi":92,"n":8,"rr":137,"mr":78},{"m":"deepseek-v4-flash-thinking-max","r":81,"s":43,"lo":73,"hi":92,"n":13,"rr":145,"mr":74},{"m":"muse-spark","r":82,"s":42.9,"lo":61,"hi":113,"n":6,"rr":26,"mr":81},{"m":"inkling-small","r":83,"s":42.83,"lo":58,"hi":113,"n":13,"rr":174,"mr":75},{"m":"seed2.1-turbo","r":84,"s":42.42,"lo":70,"hi":165,"n":3,"rr":40,"mr":89},{"m":"mercury-3","r":85,"s":42.08,"lo":66,"hi":106,"n":4,"rr":15,"mr":97},{"m":"mimo-v2.5-pro","r":86,"s":41.94,"lo":63,"hi":103,"n":6,"rr":219,"mr":84},{"m":"kat-coder-pro-v2","r":87,"s":40.93,"lo":78,"hi":137,"n":4,"rr":18,"mr":95},{"m":"gpt-5.4-mini","r":88,"s":40.47,"lo":80,"hi":103,"n":8,"rr":50,"mr":82},{"m":"qwen3-max-thinking","r":89,"s":40.27,"lo":75,"hi":214,"n":5,"rr":84,"mr":110},{"m":"gemini-3-flash","r":90,"s":40.04,"lo":74,"hi":155,"n":9,"rr":105,"mr":88},{"m":"qwen3.6-27b","r":91,"s":39.82,"lo":84,"hi":111,"n":9,"rr":119,"mr":92},{"m":"kimi-k2.5-thinking","r":92,"s":39.75,"lo":77,"hi":122,"n":9,"rr":66,"mr":90},{"m":"mimo-v2.5","r":93,"s":39.75,"lo":82,"hi":115,"n":9,"rr":142,"mr":86},{"m":"gpt-5.2-thinking","r":94,"s":39.68,"lo":59,"hi":155,"n":6,"rr":19,"mr":102},{"m":"deepseek-v4-flash","r":95,"s":39.36,"lo":60,"hi":164,"n":11,"rr":177,"mr":99},{"m":"gpt-5","r":96,"s":39.02,"lo":72,"hi":131,"n":8,"rr":63,"mr":91},{"m":"claude-sonnet-4.5","r":97,"s":38.97,"lo":53,"hi":183,"n":10,"rr":123,"mr":87},{"m":"deepseek-v4-flash-thinking","r":98,"s":38.84,"lo":92,"hi":117,"n":3,"rr":81,"mr":112},{"m":"deepseek-v3.2-thinking","r":99,"s":38.78,"lo":72,"hi":140,"n":8,"rr":68,"mr":98},{"m":"solar-pro-4","r":100,"s":38.64,"lo":86,"hi":122,"n":3,"rr":9,"mr":109},{"m":"kimi-k2-thinking","r":101,"s":38.49,"lo":61,"hi":142,"n":7,"rr":124,"mr":93},{"m":"occamy-1.0","r":102,"s":38.49,"lo":89,"hi":133,"n":3,"rr":224,"mr":108},{"m":"qwen3.6-plus","r":103,"s":38.17,"lo":81,"hi":130,"n":7,"rr":131,"mr":103},{"m":"qwen3.5-397b-a17b","r":104,"s":38,"lo":81,"hi":139,"n":12,"rr":169,"mr":94},{"m":"nemotron-3.5-super-vl-120b-a12b","r":105,"s":37.93,"lo":72,"hi":140,"n":13,"rr":211,"mr":100},{"m":"nova-2-pro","r":106,"s":37.93,"lo":73,"hi":167,"n":3,"rr":1,"mr":118},{"m":"glm-4.7","r":107,"s":37.6,"lo":54,"hi":176,"n":5,"rr":180,"mr":119},{"m":"hy3-preview","r":108,"s":37.59,"lo":101,"hi":124,"n":4,"rr":25,"mr":113},{"m":"ling-3.0-flash","r":109,"s":37.56,"lo":92,"hi":126,"n":5,"rr":160,"mr":104},{"m":"minimax-m2.7","r":110,"s":37.55,"lo":85,"hi":145,"n":14,"rr":143,"mr":96},{"m":"nemotron-3.5-bolt-74b-a9b","r":111,"s":37.52,"lo":99,"hi":135,"n":6,"rr":104,"mr":114},{"m":"gpt-5.1-high","r":112,"s":37.42,"lo":92,"hi":130,"n":5,"rr":225,"mr":106},{"m":"ax-k2","r":113,"s":36.7,"lo":56,"hi":166,"n":7,"rr":53,"mr":105},{"m":"ornith-1.0-35b","r":114,"s":36.67,"lo":87,"hi":182,"n":4,"rr":158,"mr":120},{"m":"kimi-k2.5","r":115,"s":36.48,"lo":102,"hi":135,"n":7,"rr":126,"mr":115},{"m":"nemotron-3-ultra","r":116,"s":36.3,"lo":83,"hi":139,"n":13,"rr":181,"mr":111},{"m":"deepseek-v3.2","r":117,"s":36.21,"lo":82,"hi":141,"n":9,"rr":111,"mr":101},{"m":"gpt-5.1","r":118,"s":36.17,"lo":57,"hi":165,"n":5,"rr":17,"mr":123},{"m":"qwen3.6-35b-a3b","r":119,"s":35.87,"lo":88,"hi":161,"n":15,"rr":194,"mr":107},{"m":"nex-n2-mini","r":120,"s":35.64,"lo":101,"hi":169,"n":6,"rr":148,"mr":124},{"m":"step-3.7-flash","r":121,"s":35.4,"lo":106,"hi":150,"n":5,"rr":182,"mr":121},{"m":"xing4.0-29b-a4b","r":122,"s":35.27,"lo":109,"hi":167,"n":3,"rr":45,"mr":131},{"m":"muse-glimmer-30b","r":123,"s":35.04,"lo":95,"hi":142,"n":10,"rr":221,"mr":117},{"m":"qwen3.5-27b","r":124,"s":34.69,"lo":42,"hi":152,"n":9,"rr":102,"mr":125},{"m":"k2-horizon-32b","r":125,"s":34.68,"lo":99,"hi":154,"n":5,"rr":151,"mr":129},{"m":"gpt-6-luna-medium","r":126,"s":34.6,"lo":79,"hi":167,"n":4,"rr":32,"mr":141},{"m":"seed1.8","r":127,"s":34.38,"lo":66,"hi":156,"n":3,"rr":91,"mr":139},{"m":"nemotron-3.5-super-vl-120b-a12b-nvfp4","r":128,"s":34.34,"lo":89,"hi":186,"n":7,"rr":121,"mr":132},{"m":"gemini-3.5-flash-lite","r":129,"s":34.25,"lo":89,"hi":212,"n":6,"rr":173,"mr":127},{"m":"gpt-5.4-nano","r":130,"s":34.23,"lo":116,"hi":167,"n":6,"rr":80,"mr":130},{"m":"qwen3.5-122b-a10b","r":131,"s":34.02,"lo":113,"hi":158,"n":14,"rr":216,"mr":122},{"m":"gpt-5-high","r":132,"s":33.9,"lo":76,"hi":158,"n":9,"rr":129,"mr":116},{"m":"solar-open-2-250b","r":133,"s":33.83,"lo":87,"hi":149,"n":6,"rr":106,"mr":128},{"m":"ornith-1.5-35b-a3b","r":134,"s":33.76,"lo":81,"hi":166,"n":7,"rr":231,"mr":126},{"m":"raon-1-mini-preview","r":135,"s":33.66,"lo":70,"hi":157,"n":5,"rr":97,"mr":143},{"m":"kolibri-1","r":136,"s":33.63,"lo":87,"hi":210,"n":4,"rr":20,"mr":151},{"m":"agnes-3.0-flash-preview","r":137,"s":33.45,"lo":116,"hi":151,"n":5,"rr":82,"mr":145},{"m":"oxcoder-9b","r":138,"s":33.45,"lo":117,"hi":155,"n":3,"rr":127,"mr":140},{"m":"trinity-large-thinking","r":139,"s":33.42,"lo":90,"hi":228,"n":3,"rr":5,"mr":159},{"m":"mimo-v2-flash","r":140,"s":33.11,"lo":112,"hi":167,"n":8,"rr":196,"mr":134},{"m":"gpt-5-codex-high","r":141,"s":32.89,"lo":116,"hi":154,"n":4,"rr":115,"mr":133},{"m":"step-3.5-flash-20260204","r":142,"s":32.79,"lo":121,"hi":176,"n":6,"rr":87,"mr":137},{"m":"qwen3.5-35b-a3b","r":143,"s":32.76,"lo":65,"hi":163,"n":8,"rr":85,"mr":135},{"m":"comet-60b-a12b-fp8","r":144,"s":32.69,"lo":99,"hi":166,"n":7,"rr":112,"mr":136},{"m":"ring-2.6-1t-xhigh","r":145,"s":32.31,"lo":95,"hi":183,"n":7,"rr":125,"mr":138},{"m":"claude-haiku-5.5-medium","r":146,"s":31.8,"lo":101,"hi":195,"n":4,"rr":46,"mr":161},{"m":"agents-a1","r":147,"s":31.75,"lo":102,"hi":178,"n":6,"rr":254,"mr":144},{"m":"comet-60b-a12b","r":148,"s":31.66,"lo":101,"hi":175,"n":7,"rr":117,"mr":142},{"m":"mercury-2.5","r":149,"s":31.13,"lo":109,"hi":188,"n":7,"rr":156,"mr":154},{"m":"k2-horizon-mova-36b-a4b","r":150,"s":31.1,"lo":119,"hi":178,"n":5,"rr":165,"mr":147},{"m":"snowdon-1.1-small","r":151,"s":30.96,"lo":43,"hi":207,"n":4,"rr":70,"mr":152},{"m":"intern-s2-preview","r":152,"s":30.87,"lo":70,"hi":178,"n":3,"rr":188,"mr":168},{"m":"comet-60b-a12b-nvfp4","r":153,"s":30.76,"lo":104,"hi":192,"n":7,"rr":132,"mr":153},{"m":"mistral-medium-3.5","r":154,"s":29.94,"lo":130,"hi":180,"n":5,"rr":134,"mr":160},{"m":"ornith-1.5-9b","r":155,"s":29.85,"lo":130,"hi":219,"n":4,"rr":172,"mr":157},{"m":"grok-4.1-fast","r":156,"s":29.34,"lo":141,"hi":173,"n":3,"rr":272,"mr":169},{"m":"minimax-m2.1","r":157,"s":29.24,"lo":140,"hi":201,"n":8,"rr":139,"mr":148},{"m":"o3","r":158,"s":29.12,"lo":121,"hi":179,"n":4,"rr":99,"mr":146},{"m":"k-exaone-2.0","r":159,"s":28.92,"lo":144,"hi":186,"n":5,"rr":76,"mr":162},{"m":"gemma-4-31b-it","r":160,"s":28.58,"lo":141,"hi":188,"n":9,"rr":203,"mr":149},{"m":"nanbeige4.2-3b","r":161,"s":28.57,"lo":131,"hi":195,"n":5,"rr":96,"mr":164},{"m":"bigbang-v1","r":162,"s":28.35,"lo":108,"hi":190,"n":3,"rr":227,"mr":166},{"m":"spark-x2.6-4b","r":163,"s":28.3,"lo":117,"hi":191,"n":5,"rr":109,"mr":172},{"m":"ornith-1.0-9b","r":164,"s":28.01,"lo":154,"hi":187,"n":3,"rr":179,"mr":171},{"m":"gemma-4-26b-a4b","r":165,"s":27.97,"lo":84,"hi":192,"n":5,"rr":113,"mr":177},{"m":"k2-horizon-7b","r":166,"s":27.96,"lo":151,"hi":201,"n":4,"rr":103,"mr":170},{"m":"north-mini-code-1.0","r":167,"s":27.89,"lo":146,"hi":186,"n":3,"rr":274,"mr":174},{"m":"minimax-m2","r":168,"s":27.85,"lo":130,"hi":192,"n":8,"rr":133,"mr":150},{"m":"claude-4.5-haiku","r":169,"s":27.15,"lo":149,"hi":213,"n":13,"rr":260,"mr":155},{"m":"gpt-5-mini-high","r":170,"s":27.15,"lo":139,"hi":190,"n":8,"rr":120,"mr":156},{"m":"claude-4.5-sonnet-thinking","r":171,"s":26.5,"lo":145,"hi":243,"n":8,"rr":164,"mr":158},{"m":"deepseek-v3.2-exp","r":172,"s":26.27,"lo":121,"hi":281,"n":5,"rr":176,"mr":175},{"m":"grok-4","r":173,"s":26,"lo":132,"hi":198,"n":9,"rr":185,"mr":163},{"m":"longcat-flash-lite-sparse","r":174,"s":25.79,"lo":88,"hi":248,"n":4,"rr":51,"mr":182},{"m":"nemotron-3-super-120b-a12b","r":175,"s":25.73,"lo":157,"hi":199,"n":12,"rr":236,"mr":165},{"m":"o3-high","r":176,"s":25.5,"lo":144,"hi":201,"n":5,"rr":209,"mr":180},{"m":"mai-code-1-flash","r":177,"s":25.34,"lo":111,"hi":204,"n":3,"rr":13,"mr":183},{"m":"claude-opus-4.1","r":178,"s":24.94,"lo":150,"hi":208,"n":8,"rr":155,"mr":167},{"m":"gpt-5-mini","r":179,"s":24.89,"lo":129,"hi":204,"n":6,"rr":72,"mr":176},{"m":"command-a-plus-05-2026","r":180,"s":24.44,"lo":160,"hi":244,"n":7,"rr":154,"mr":184},{"m":"gemini-2.5-pro","r":181,"s":24.41,"lo":153,"hi":234,"n":9,"rr":214,"mr":173},{"m":"laguna-xs-2.1","r":182,"s":24.07,"lo":165,"hi":267,"n":3,"rr":273,"mr":185},{"m":"gemini-3.1-flash-lite","r":183,"s":23.94,"lo":126,"hi":244,"n":6,"rr":212,"mr":188},{"m":"nova-2-lite","r":184,"s":23.66,"lo":132,"hi":198,"n":3,"rr":3,"mr":192},{"m":"deepseek-v3.1-terminus","r":185,"s":23.63,"lo":156,"hi":275,"n":7,"rr":184,"mr":179},{"m":"qwen3.5-omni-plus","r":186,"s":23.61,"lo":151,"hi":220,"n":3,"rr":37,"mr":201},{"m":"gemma-4-26b-a4b-it","r":187,"s":23.24,"lo":174,"hi":241,"n":12,"rr":243,"mr":181},{"m":"spark-x2.5-4b","r":188,"s":23.04,"lo":131,"hi":221,"n":5,"rr":135,"mr":194},{"m":"intern-s1-pro","r":189,"s":22.81,"lo":130,"hi":234,"n":3,"rr":228,"mr":210},{"m":"k2-horizon-3.7b","r":190,"s":22.74,"lo":170,"hi":259,"n":3,"rr":201,"mr":202},{"m":"qwen3-235b-a22b-thinking-2507","r":191,"s":22.69,"lo":150,"hi":258,"n":5,"rr":75,"mr":195},{"m":"ling-2.6-1t","r":192,"s":22.49,"lo":168,"hi":235,"n":4,"rr":190,"mr":203},{"m":"nemotron-labs-dory1.0-4b-4loop","r":193,"s":22.46,"lo":113,"hi":251,"n":7,"rr":200,"mr":193},{"m":"claude-sonnet-4","r":194,"s":22.36,"lo":162,"hi":223,"n":7,"rr":159,"mr":178},{"m":"joyai-llm-flash","r":195,"s":22.15,"lo":180,"hi":270,"n":3,"rr":67,"mr":212},{"m":"gpt-5-mini-medium","r":196,"s":22.12,"lo":134,"hi":210,"n":4,"rr":29,"mr":196},{"m":"k-exaone","r":197,"s":21.85,"lo":188,"hi":217,"n":7,"rr":130,"mr":187},{"m":"grok-4-fast","r":198,"s":21.51,"lo":142,"hi":223,"n":7,"rr":161,"mr":186},{"m":"nemotron-3.5-lightning-30b-a3b","r":199,"s":21.44,"lo":157,"hi":247,"n":9,"rr":238,"mr":189},{"m":"deepseek-v3.1-thinking","r":200,"s":21.38,"lo":176,"hi":256,"n":4,"rr":257,"mr":207},{"m":"g9v3-39a5b","r":201,"s":21.35,"lo":177,"hi":234,"n":5,"rr":222,"mr":199},{"m":"exaone-4.5-33b-thinking","r":202,"s":21.16,"lo":173,"hi":213,"n":4,"rr":24,"mr":211},{"m":"qwen3.5-9b","r":203,"s":20.7,"lo":179,"hi":256,"n":10,"rr":263,"mr":197},{"m":"gpt-oss-120b","r":204,"s":20.7,"lo":190,"hi":238,"n":10,"rr":237,"mr":191},{"m":"hy-2.0-thinking","r":205,"s":20.61,"lo":172,"hi":224,"n":3,"rr":122,"mr":217},{"m":"glm-4.6","r":206,"s":20.59,"lo":190,"hi":223,"n":7,"rr":204,"mr":190},{"m":"nemotron-labs-dory1.0-4b","r":207,"s":20.48,"lo":123,"hi":265,"n":7,"rr":205,"mr":206},{"m":"nemotron-labs-3-puzzle-75b-a9b","r":208,"s":20.47,"lo":147,"hi":231,"n":5,"rr":149,"mr":204},{"m":"ling-2.5-1t","r":209,"s":20.43,"lo":188,"hi":245,"n":3,"rr":146,"mr":218},{"m":"minicpm5-1b","r":210,"s":20.28,"lo":183,"hi":300,"n":3,"rr":152,"mr":225},{"m":"granite-4.2-8b","r":211,"s":20.2,"lo":107,"hi":250,"n":5,"rr":215,"mr":216},{"m":"glm-4.7-flash","r":212,"s":20.19,"lo":83,"hi":271,"n":6,"rr":199,"mr":205},{"m":"granite-4.2-30b","r":213,"s":20,"lo":177,"hi":259,"n":7,"rr":223,"mr":213},{"m":"ling-3.0-tiny","r":214,"s":19.87,"lo":182,"hi":256,"n":9,"rr":250,"mr":200},{"m":"gpt-oss-120b-high","r":215,"s":19.82,"lo":186,"hi":235,"n":8,"rr":234,"mr":198},{"m":"qwen3.5-4b","r":216,"s":19.15,"lo":166,"hi":285,"n":11,"rr":255,"mr":208},{"m":"nemotron-32b","r":217,"s":19.1,"lo":185,"hi":229,"n":3,"rr":229,"mr":230},{"m":"gemma-4-12b-it","r":218,"s":18.83,"lo":192,"hi":278,"n":10,"rr":264,"mr":209},{"m":"gpt-5.4-none","r":219,"s":18.76,"lo":170,"hi":241,"n":5,"rr":163,"mr":222},{"m":"kimi-k2-0905","r":220,"s":18.76,"lo":199,"hi":281,"n":7,"rr":210,"mr":214},{"m":"kimi-k2-instruct","r":221,"s":18.75,"lo":203,"hi":281,"n":5,"rr":246,"mr":215},{"m":"deepseek-v3.1","r":222,"s":18.5,"lo":181,"hi":272,"n":4,"rr":202,"mr":229},{"m":"minicpm5-2b","r":223,"s":18.43,"lo":69,"hi":289,"n":6,"rr":141,"mr":224},{"m":"devstral-small-2","r":224,"s":18.25,"lo":205,"hi":243,"n":3,"rr":319,"mr":228},{"m":"ax-k1","r":225,"s":18.07,"lo":165,"hi":321,"n":6,"rr":192,"mr":241},{"m":"apriel-1.6-15b-thinker","r":226,"s":18.06,"lo":201,"hi":246,"n":6,"rr":197,"mr":220},{"m":"nemotron-cascade-2-30b-a3b","r":227,"s":18.04,"lo":153,"hi":255,"n":5,"rr":147,"mr":231},{"m":"glm-4.5","r":228,"s":17.28,"lo":180,"hi":299,"n":7,"rr":247,"mr":221},{"m":"hypernova-60b-2605","r":229,"s":17.03,"lo":194,"hi":255,"n":6,"rr":171,"mr":232},{"m":"lfm2.5-24b-a2b","r":230,"s":16.91,"lo":137,"hi":270,"n":4,"rr":183,"mr":239},{"m":"qwen3-235b-a22b","r":231,"s":16.75,"lo":187,"hi":283,"n":6,"rr":187,"mr":227},{"m":"qwen3-235b-2507","r":232,"s":16.64,"lo":180,"hi":255,"n":7,"rr":193,"mr":223},{"m":"k2-think","r":233,"s":16.58,"lo":175,"hi":253,"n":3,"rr":239,"mr":246},{"m":"deepseek-r1","r":234,"s":16.28,"lo":212,"hi":265,"n":4,"rr":302,"mr":244},{"m":"deepseek-r1-0528","r":235,"s":16.25,"lo":190,"hi":277,"n":7,"rr":235,"mr":219},{"m":"mercury-2","r":236,"s":16.25,"lo":175,"hi":263,"n":8,"rr":213,"mr":237},{"m":"nemotron-labs-dory1.0-4b-1loop","r":237,"s":16.12,"lo":167,"hi":280,"n":7,"rr":249,"mr":234},{"m":"claude-opus-4","r":238,"s":16.05,"lo":218,"hi":254,"n":4,"rr":261,"mr":240},{"m":"gemini-2.5-flash","r":239,"s":16.02,"lo":210,"hi":264,"n":9,"rr":266,"mr":226},{"m":"apriel-1.5-15b-thinker","r":240,"s":15.95,"lo":218,"hi":275,"n":8,"rr":276,"mr":235},{"m":"qwen3-235b-a22b-2507","r":241,"s":15.59,"lo":205,"hi":257,"n":4,"rr":284,"mr":243},{"m":"gpt-5-minimal","r":242,"s":15.38,"lo":226,"hi":290,"n":8,"rr":283,"mr":238},{"m":"phi-4-reasoning-plus","r":243,"s":15.34,"lo":174,"hi":287,"n":4,"rr":218,"mr":255},{"m":"qwen3.5-omni-flash","r":244,"s":15.3,"lo":206,"hi":275,"n":3,"rr":118,"mr":253},{"m":"glm-4.5-air","r":245,"s":15.28,"lo":218,"hi":264,"n":7,"rr":248,"mr":236},{"m":"qwq-32b","r":246,"s":15.17,"lo":186,"hi":265,"n":3,"rr":256,"mr":254},{"m":"mistral-small-4-thinking","r":247,"s":14.88,"lo":179,"hi":271,"n":5,"rr":138,"mr":245},{"m":"gemini-2.5-flash-preview-09-2025","r":248,"s":14.83,"lo":195,"hi":283,"n":7,"rr":230,"mr":233},{"m":"magistral-medium-1.2","r":249,"s":14.76,"lo":200,"hi":264,"n":7,"rr":207,"mr":242},{"m":"claude-4.5-haiku-thinking","r":250,"s":14.66,"lo":187,"hi":262,"n":4,"rr":110,"mr":252},{"m":"qwen3-vl-235b-a22b-thinking","r":251,"s":14.55,"lo":185,"hi":268,"n":4,"rr":62,"mr":251},{"m":"k2-think-v2","r":252,"s":14.42,"lo":198,"hi":277,"n":3,"rr":178,"mr":262},{"m":"gpt-oss-20b-high","r":253,"s":14.27,"lo":230,"hi":277,"n":6,"rr":226,"mr":247},{"m":"midm-k-2.5-pro","r":254,"s":14.07,"lo":170,"hi":312,"n":8,"rr":291,"mr":256},{"m":"mistral-small-4","r":255,"s":13.93,"lo":232,"hi":289,"n":4,"rr":240,"mr":257},{"m":"qwen3-coder-30b-a3b-instruct","r":256,"s":13.74,"lo":116,"hi":304,"n":3,"rr":308,"mr":263},{"m":"hypernova-60b-2602","r":257,"s":13.69,"lo":234,"hi":290,"n":6,"rr":208,"mr":250},{"m":"qwen3-next-80b-a3b","r":258,"s":13.67,"lo":204,"hi":273,"n":7,"rr":217,"mr":248},{"m":"gpt-oss-20b","r":259,"s":13.28,"lo":227,"hi":305,"n":11,"rr":287,"mr":249},{"m":"nemotron-3-nano-30b-a3b","r":260,"s":13.22,"lo":223,"hi":285,"n":6,"rr":233,"mr":259},{"m":"apriel-1.5-15b-thinker-self-reported","r":261,"s":13.06,"lo":236,"hi":290,"n":7,"rr":252,"mr":258},{"m":"gpt-oss-120b-medium","r":262,"s":12.93,"lo":229,"hi":279,"n":5,"rr":186,"mr":260},{"m":"gpt-4o","r":263,"s":12.53,"lo":232,"hi":323,"n":3,"rr":325,"mr":276},{"m":"qwen3-next-80b-a3b-thinking","r":264,"s":12.5,"lo":132,"hi":290,"n":5,"rr":116,"mr":261},{"m":"solar-open-100b","r":265,"s":12.42,"lo":241,"hi":309,"n":6,"rr":251,"mr":264},{"m":"tri-21b-think","r":266,"s":12.35,"lo":182,"hi":313,"n":6,"rr":241,"mr":265},{"m":"qwen3-next-80b-a3b-instruct","r":267,"s":12.11,"lo":170,"hi":321,"n":3,"rr":162,"mr":274},{"m":"qwen3-4b-thinking-2507","r":268,"s":12.09,"lo":215,"hi":293,"n":3,"rr":157,"mr":271},{"m":"mistral-large-3","r":269,"s":12.06,"lo":239,"hi":306,"n":4,"rr":313,"mr":275},{"m":"hyperclovax-seed-think","r":270,"s":11.51,"lo":166,"hi":308,"n":7,"rr":277,"mr":268},{"m":"gemini-2.5-flash-thinking","r":271,"s":10.94,"lo":167,"hi":286,"n":4,"rr":150,"mr":272},{"m":"o3-mini-high","r":272,"s":10.84,"lo":198,"hi":293,"n":6,"rr":245,"mr":266},{"m":"ling-1t","r":273,"s":10.48,"lo":217,"hi":299,"n":3,"rr":244,"mr":278},{"m":"granite-4.2-3b","r":274,"s":10.42,"lo":259,"hi":303,"n":7,"rr":279,"mr":269},{"m":"nvidia-nemotron-3-nano-30b-a3b-bf16","r":275,"s":10.41,"lo":247,"hi":311,"n":11,"rr":304,"mr":267},{"m":"olmo-3-think-32b","r":276,"s":10.28,"lo":226,"hi":296,"n":3,"rr":253,"mr":285},{"m":"qwen3.5-0.8b-thinking","r":277,"s":10.27,"lo":236,"hi":321,"n":3,"rr":267,"mr":279},{"m":"gpt-4.1","r":278,"s":10.17,"lo":251,"hi":318,"n":4,"rr":242,"mr":277},{"m":"gemini-2.5-flash-lite-thinking","r":279,"s":10.03,"lo":217,"hi":291,"n":4,"rr":191,"mr":280},{"m":"nvidia-nemotron-nano-9b-v2","r":280,"s":9.98,"lo":244,"hi":296,"n":3,"rr":268,"mr":286},{"m":"lfm2.5-8b-a1b","r":281,"s":9.82,"lo":152,"hi":330,"n":8,"rr":278,"mr":282},{"m":"qwen3-30b-a3b-thinking-2507","r":282,"s":9.51,"lo":235,"hi":300,"n":9,"rr":289,"mr":270},{"m":"amazon-nova-premier","r":283,"s":9.27,"lo":246,"hi":297,"n":3,"rr":206,"mr":289},{"m":"qwen3-8b-thinking","r":284,"s":9.16,"lo":224,"hi":303,"n":3,"rr":265,"mr":296},{"m":"openreasoning-nemotron-7b","r":285,"s":9.16,"lo":256,"hi":309,"n":4,"rr":299,"mr":293},{"m":"falcon-h1r-7b","r":286,"s":9.15,"lo":245,"hi":301,"n":5,"rr":270,"mr":290},{"m":"deepseek-v3-0324","r":287,"s":9.06,"lo":260,"hi":303,"n":3,"rr":271,"mr":288},{"m":"llama-4-maverick","r":288,"s":9.03,"lo":262,"hi":312,"n":8,"rr":306,"mr":273},{"m":"qwen3-30b-a3b","r":289,"s":8.92,"lo":249,"hi":298,"n":5,"rr":269,"mr":283},{"m":"qwen3-32b","r":290,"s":8.8,"lo":264,"hi":300,"n":6,"rr":295,"mr":281},{"m":"lfm2.5-2.6b","r":291,"s":8.65,"lo":139,"hi":323,"n":6,"rr":262,"mr":284},{"m":"exaone-4.0-32b","r":292,"s":8.26,"lo":256,"hi":308,"n":7,"rr":303,"mr":291},{"m":"llama-nemotron-super-49b-v1.5","r":293,"s":8.16,"lo":262,"hi":304,"n":7,"rr":294,"mr":287},{"m":"command-a-reasoning-08-2025","r":294,"s":8.07,"lo":262,"hi":320,"n":4,"rr":312,"mr":299},{"m":"gemini-2.5-flash-lite","r":295,"s":8.03,"lo":255,"hi":310,"n":3,"rr":285,"mr":297},{"m":"qwen3-32b-thinking","r":296,"s":7.96,"lo":244,"hi":304,"n":4,"rr":259,"mr":298},{"m":"deepseek-r1-0528-qwen3-8b","r":297,"s":7.85,"lo":266,"hi":315,"n":4,"rr":301,"mr":300},{"m":"magistral-small-1.2","r":298,"s":7.75,"lo":272,"hi":310,"n":7,"rr":297,"mr":292},{"m":"qwen3-4b-instruct-2507","r":299,"s":7.69,"lo":250,"hi":316,"n":3,"rr":290,"mr":303},{"m":"qwen3-4b","r":300,"s":7.56,"lo":248,"hi":314,"n":3,"rr":296,"mr":304},{"m":"qwen3-4b-2507","r":301,"s":7.44,"lo":278,"hi":320,"n":7,"rr":298,"mr":294},{"m":"exaone-4.0-32b-thinking","r":302,"s":7.16,"lo":232,"hi":312,"n":4,"rr":258,"mr":305},{"m":"spark-x2.5-1.7b","r":303,"s":6.97,"lo":213,"hi":322,"n":5,"rr":292,"mr":306},{"m":"g9v3-3b","r":304,"s":6.87,"lo":240,"hi":321,"n":3,"rr":320,"mr":307},{"m":"nemotron-3-nano-4b-thinking","r":305,"s":6.78,"lo":261,"hi":327,"n":4,"rr":315,"mr":301},{"m":"gemma-4-e4b-it","r":306,"s":6.75,"lo":282,"hi":328,"n":11,"rr":314,"mr":295},{"m":"gpt-5-nano-minimal","r":307,"s":6.71,"lo":240,"hi":313,"n":4,"rr":286,"mr":309},{"m":"gpt-4-turbo","r":308,"s":6.65,"lo":211,"hi":325,"n":3,"rr":305,"mr":312},{"m":"qwen3-14b","r":309,"s":6.61,"lo":252,"hi":324,"n":3,"rr":282,"mr":310},{"m":"nemotron-3-nano-4b","r":310,"s":6.46,"lo":284,"hi":327,"n":6,"rr":307,"mr":302},{"m":"qwen3-8b","r":311,"s":6.39,"lo":287,"hi":327,"n":6,"rr":309,"mr":308},{"m":"lfm2.5-1.2b-thinking","r":312,"s":6.06,"lo":237,"hi":318,"n":3,"rr":280,"mr":315},{"m":"lfm2.5-350m","r":313,"s":5.79,"lo":244,"hi":319,"n":3,"rr":300,"mr":314},{"m":"gemma-3-4b","r":314,"s":5.76,"lo":241,"hi":326,"n":3,"rr":322,"mr":318},{"m":"qwen3-0.6b","r":315,"s":5.7,"lo":261,"hi":323,"n":4,"rr":323,"mr":313},{"m":"qwen3-1.7b","r":316,"s":5.48,"lo":240,"hi":322,"n":3,"rr":317,"mr":320},{"m":"amazon-nova-lite-v1.0","r":317,"s":5.48,"lo":241,"hi":320,"n":3,"rr":293,"mr":319},{"m":"amazon-nova-pro-v1.0","r":318,"s":5.32,"lo":245,"hi":323,"n":3,"rr":281,"mr":321},{"m":"nemotron-h-47b-reasoning","r":319,"s":5.04,"lo":290,"hi":326,"n":5,"rr":310,"mr":317},{"m":"qwen3.5-2b","r":320,"s":4.92,"lo":230,"hi":332,"n":8,"rr":311,"mr":311},{"m":"gemma-4-e2b-it","r":321,"s":4.75,"lo":307,"hi":332,"n":9,"rr":326,"mr":316},{"m":"qwen3-30b-a3b-instruct-2507","r":322,"s":4.74,"lo":233,"hi":333,"n":4,"rr":288,"mr":322},{"m":"gemma-3-270m-it","r":323,"s":4.57,"lo":235,"hi":334,"n":3,"rr":334,"mr":324},{"m":"granite-4.0-h-tiny","r":324,"s":4.25,"lo":299,"hi":330,"n":5,"rr":332,"mr":323},{"m":"granite-4-h-300m","r":325,"s":4.2,"lo":227,"hi":333,"n":3,"rr":328,"mr":325},{"m":"qwen3-1.7b-thinking","r":326,"s":4.12,"lo":238,"hi":330,"n":3,"rr":316,"mr":330},{"m":"lfm2-8b-a1b","r":327,"s":3.97,"lo":304,"hi":329,"n":5,"rr":329,"mr":326},{"m":"deepseek-r1-distill-qwen-1.5b","r":328,"s":3.93,"lo":237,"hi":332,"n":3,"rr":331,"mr":329},{"m":"apertus-70b-instruct","r":329,"s":3.78,"lo":234,"hi":330,"n":3,"rr":321,"mr":327},{"m":"lfm2-350m","r":330,"s":3.6,"lo":233,"hi":331,"n":3,"rr":324,"mr":331},{"m":"qwen3.5-0.8b","r":331,"s":3.59,"lo":274,"hi":334,"n":4,"rr":330,"mr":328},{"m":"gemma-3-1b","r":332,"s":3.34,"lo":229,"hi":332,"n":3,"rr":327,"mr":332},{"m":"lfm2.5-230m","r":333,"s":2.89,"lo":242,"hi":333,"n":3,"rr":318,"mr":333},{"m":"granite-4-300m","r":334,"s":1.86,"lo":230,"hi":334,"n":3,"rr":333,"mr":334}]},"decision":{"name":"Decision","n":51,"nb":34,"acc":0.833,"raw_acc":0.8092,"rows":[{"m":"d1-ultra","r":1,"s":86.54,"lo":1,"hi":15,"n":6,"rr":22,"mr":5},{"m":"pplx-decider-v1.2","r":2,"s":86.26,"lo":1,"hi":7,"n":27,"rr":6,"mr":1},{"m":"vllm-sr-d3","r":3,"s":86.09,"lo":1,"hi":7,"n":28,"rr":7,"mr":2},{"m":"clef-flash","r":4,"s":85.19,"lo":1,"hi":20,"n":31,"rr":13,"mr":3},{"m":"clef","r":5,"s":84.97,"lo":3,"hi":12,"n":31,"rr":10,"mr":4},{"m":"clef-omni","r":6,"s":83.79,"lo":2,"hi":22,"n":31,"rr":19,"mr":6},{"m":"glide","r":7,"s":83.7,"lo":4,"hi":21,"n":6,"rr":35,"mr":10},{"m":"pplx-decider-v1.1-27b","r":8,"s":83.45,"lo":3,"hi":23,"n":6,"rr":33,"mr":14},{"m":"glide-no-thinking","r":9,"s":82.22,"lo":5,"hi":16,"n":27,"rr":8,"mr":7},{"m":"jev-1.14","r":10,"s":81.85,"lo":6,"hi":16,"n":31,"rr":11,"mr":8},{"m":"jev-1.13","r":11,"s":81.4,"lo":7,"hi":16,"n":34,"rr":9,"mr":11},{"m":"vllm-sr-d3-flash","r":12,"s":81.12,"lo":7,"hi":18,"n":27,"rr":16,"mr":9},{"m":"mercury-decide","r":13,"s":80.97,"lo":3,"hi":33,"n":6,"rr":34,"mr":20},{"m":"autotrust-jev-35b","r":14,"s":80.79,"lo":6,"hi":22,"n":27,"rr":14,"mr":13},{"m":"vllm-sr-decision-2.0-vega-27b","r":15,"s":80.77,"lo":11,"hi":20,"n":28,"rr":17,"mr":12},{"m":"celeris-1-decision","r":16,"s":80.42,"lo":8,"hi":40,"n":6,"rr":39,"mr":21},{"m":"pplx-decider-flash-v1.2","r":17,"s":80.41,"lo":8,"hi":21,"n":27,"rr":12,"mr":15},{"m":"microsoft-decision-1","r":18,"s":79.6,"lo":2,"hi":29,"n":6,"rr":37,"mr":22},{"m":"autotrust-gev-26b-decide","r":19,"s":79.41,"lo":11,"hi":25,"n":27,"rr":18,"mr":16},{"m":"autotrust-jev-27b","r":20,"s":79.19,"lo":14,"hi":24,"n":28,"rr":20,"mr":17},{"m":"d1","r":21,"s":78.95,"lo":12,"hi":38,"n":6,"rr":40,"mr":23},{"m":"bespoke-nimble-9b-v3","r":22,"s":78.79,"lo":11,"hi":25,"n":28,"rr":15,"mr":18},{"m":"vllm-sr-d3-mini","r":23,"s":78.18,"lo":15,"hi":26,"n":27,"rr":21,"mr":19},{"m":"gpt-6-luna-decisions","r":24,"s":76.63,"lo":7,"hi":36,"n":6,"rr":43,"mr":26},{"m":"h2o-lightning-4b-nemotron-nano","r":25,"s":75.58,"lo":21,"hi":34,"n":3,"rr":2,"mr":28},{"m":"h2o-lightning-4b","r":26,"s":75.39,"lo":15,"hi":33,"n":4,"rr":4,"mr":30},{"m":"pplx-decider-v1-27b","r":27,"s":75.36,"lo":11,"hi":31,"n":3,"rr":5,"mr":29},{"m":"semif","r":28,"s":75.14,"lo":20,"hi":39,"n":3,"rr":3,"mr":31},{"m":"diffusiongemma-jev","r":29,"s":74.67,"lo":20,"hi":30,"n":26,"rr":23,"mr":24},{"m":"vllm-sr-decision-2.0-lux-9b","r":30,"s":72.94,"lo":22,"hi":31,"n":28,"rr":24,"mr":25},{"m":"jevk5","r":31,"s":71.7,"lo":26,"hi":34,"n":3,"rr":1,"mr":36},{"m":"autotrust-jev-9b","r":32,"s":71.36,"lo":26,"hi":33,"n":27,"rr":25,"mr":27},{"m":"bespoke-nimble-9b-v2","r":33,"s":70.19,"lo":28,"hi":36,"n":27,"rr":28,"mr":32},{"m":"d1-3b","r":34,"s":69.26,"lo":24,"hi":38,"n":28,"rr":26,"mr":33},{"m":"vllm-sr-decision-2.0-nox-4b","r":35,"s":68.78,"lo":30,"hi":36,"n":27,"rr":29,"mr":34},{"m":"kev-9b","r":36,"s":68.61,"lo":30,"hi":38,"n":26,"rr":30,"mr":35},{"m":"vllm-sr-d3-nano","r":37,"s":66.96,"lo":31,"hi":39,"n":27,"rr":31,"mr":37},{"m":"intern-decision-4b","r":38,"s":66.44,"lo":35,"hi":39,"n":30,"rr":27,"mr":38},{"m":"tev1-4b-experimental","r":39,"s":66.18,"lo":34,"hi":39,"n":25,"rr":32,"mr":39},{"m":"vllm-sr-d3-lite","r":40,"s":60.09,"lo":37,"hi":40,"n":27,"rr":36,"mr":40},{"m":"vllm-sr-decision-2.0-sol-2b","r":41,"s":52.52,"lo":38,"hi":43,"n":27,"rr":42,"mr":41},{"m":"strands-decider-2b","r":42,"s":50.98,"lo":40,"hi":43,"n":30,"rr":41,"mr":42},{"m":"intern-decision-2b","r":43,"s":48.61,"lo":40,"hi":44,"n":30,"rr":38,"mr":43},{"m":"vllm-sr-d3-edge","r":44,"s":46.12,"lo":41,"hi":45,"n":27,"rr":44,"mr":44},{"m":"tev1-0.8b-experimental","r":45,"s":43.98,"lo":42,"hi":47,"n":25,"rr":46,"mr":45},{"m":"vllm-sr-decision-2.0-eos-0.8b","r":46,"s":43.58,"lo":44,"hi":47,"n":27,"rr":47,"mr":46},{"m":"vllm-sr-decision-2.0-kai-0.6b","r":47,"s":42.32,"lo":45,"hi":49,"n":27,"rr":48,"mr":47},{"m":"intern-decision-0.8b","r":48,"s":41.95,"lo":43,"hi":49,"n":30,"rr":45,"mr":48},{"m":"d1-omni-600m","r":49,"s":40.45,"lo":46,"hi":50,"n":28,"rr":49,"mr":49},{"m":"gliner2.5-decide","r":50,"s":36.82,"lo":47,"hi":51,"n":28,"rr":51,"mr":50},{"m":"laya","r":51,"s":34.45,"lo":48,"hi":51,"n":29,"rr":50,"mr":51}]},"faix-agent":{"name":"Agent","n":217,"nb":24,"acc":0.7748,"raw_acc":0.7191,"rows":[{"m":"claude-fable-5","r":1,"s":84.96,"lo":1,"hi":56,"n":3,"rr":3,"mr":1},{"m":"longcat-flash-thinking-2601","r":2,"s":82.37,"lo":1,"hi":68,"n":3,"rr":1,"mr":3},{"m":"glm-5.2","r":3,"s":82.23,"lo":1,"hi":66,"n":5,"rr":28,"mr":2},{"m":"qwen3.8-max","r":4,"s":81.88,"lo":2,"hi":57,"n":4,"rr":9,"mr":5},{"m":"gpt-5.5","r":5,"s":81.61,"lo":1,"hi":14,"n":8,"rr":18,"mr":7},{"m":"claude-opus-4.6","r":6,"s":81.07,"lo":2,"hi":16,"n":11,"rr":42,"mr":6},{"m":"claude-opus-4.8","r":7,"s":81.06,"lo":2,"hi":70,"n":5,"rr":23,"mr":9},{"m":"gemini-3.1-pro","r":8,"s":80.71,"lo":1,"hi":20,"n":11,"rr":46,"mr":8},{"m":"gpt-5.4","r":9,"s":80.67,"lo":3,"hi":21,"n":10,"rr":41,"mr":4},{"m":"kimi-k2.6","r":10,"s":80.12,"lo":5,"hi":116,"n":3,"rr":5,"mr":12},{"m":"glm-5.3-flash","r":11,"s":79.27,"lo":8,"hi":83,"n":7,"rr":27,"mr":10},{"m":"glm-5.1","r":12,"s":79.07,"lo":4,"hi":24,"n":8,"rr":29,"mr":11},{"m":"claude-opus-4.5-thinking","r":13,"s":78.89,"lo":7,"hi":63,"n":3,"rr":7,"mr":15},{"m":"claude-opus-4.7","r":14,"s":78.8,"lo":4,"hi":67,"n":7,"rr":16,"mr":13},{"m":"gpt-5.6-sol","r":15,"s":78.2,"lo":6,"hi":46,"n":5,"rr":20,"mr":18},{"m":"qwen3.7-plus","r":16,"s":77.54,"lo":11,"hi":26,"n":5,"rr":51,"mr":14},{"m":"gpt-5.2","r":17,"s":77.43,"lo":8,"hi":42,"n":8,"rr":49,"mr":19},{"m":"claude-opus-4.5","r":18,"s":77.42,"lo":8,"hi":31,"n":10,"rr":55,"mr":16},{"m":"gpt-5.6-luna","r":19,"s":77.26,"lo":7,"hi":90,"n":4,"rr":57,"mr":23},{"m":"deepseek-v4-flash-0731","r":20,"s":77.26,"lo":12,"hi":67,"n":6,"rr":24,"mr":17},{"m":"deepseek-v4-pro-thinking-max","r":21,"s":76.68,"lo":9,"hi":27,"n":6,"rr":26,"mr":20},{"m":"qwen3.8-flash-next","r":22,"s":76.51,"lo":6,"hi":59,"n":7,"rr":21,"mr":22},{"m":"claude-sonnet-4.6","r":23,"s":76.33,"lo":12,"hi":40,"n":7,"rr":47,"mr":24},{"m":"longcat-flash-thinking-zigzag","r":24,"s":76.31,"lo":15,"hi":68,"n":3,"rr":2,"mr":28},{"m":"qwen3.7-max","r":25,"s":76.02,"lo":12,"hi":35,"n":5,"rr":33,"mr":21},{"m":"kimi-k3","r":26,"s":75.78,"lo":5,"hi":81,"n":4,"rr":17,"mr":30},{"m":"glm-5","r":27,"s":75.51,"lo":15,"hi":44,"n":7,"rr":73,"mr":27},{"m":"kimi-k2.6-thinking","r":28,"s":75.34,"lo":16,"hi":34,"n":6,"rr":39,"mr":25},{"m":"gpt-5.2-thinking-xhigh","r":29,"s":74.83,"lo":8,"hi":69,"n":4,"rr":35,"mr":36},{"m":"inkling","r":30,"s":74.63,"lo":19,"hi":74,"n":3,"rr":85,"mr":29},{"m":"gemini-3-pro","r":31,"s":74.34,"lo":16,"hi":60,"n":12,"rr":82,"mr":26},{"m":"deepseek-v4-pro-thinking","r":32,"s":73.89,"lo":24,"hi":50,"n":3,"rr":68,"mr":32},{"m":"ring-2.6-1t-high","r":33,"s":73.63,"lo":23,"hi":92,"n":3,"rr":6,"mr":34},{"m":"qwen3.6-plus","r":34,"s":73.61,"lo":24,"hi":42,"n":5,"rr":79,"mr":31},{"m":"qwen3.5-397b-a17b","r":35,"s":73.04,"lo":24,"hi":44,"n":7,"rr":53,"mr":33},{"m":"deepseek-v4-pro","r":36,"s":72.82,"lo":28,"hi":59,"n":5,"rr":63,"mr":35},{"m":"mimo-v2.5","r":37,"s":72.51,"lo":25,"hi":57,"n":4,"rr":104,"mr":38},{"m":"claude-sonnet-4.5","r":38,"s":72.46,"lo":12,"hi":70,"n":13,"rr":74,"mr":37},{"m":"gemini-3.5-flash","r":39,"s":72.26,"lo":8,"hi":195,"n":3,"rr":110,"mr":45},{"m":"deepseek-v4-flash-thinking-max","r":40,"s":71.36,"lo":32,"hi":46,"n":5,"rr":80,"mr":41},{"m":"minimax-m3","r":41,"s":71.23,"lo":21,"hi":68,"n":4,"rr":52,"mr":39},{"m":"qwen3.8-27b","r":42,"s":70.86,"lo":21,"hi":99,"n":8,"rr":56,"mr":40},{"m":"qwen3.5-27b","r":43,"s":70.57,"lo":6,"hi":71,"n":8,"rr":67,"mr":43},{"m":"deepseek-v4-flash-thinking","r":44,"s":70.47,"lo":36,"hi":57,"n":3,"rr":97,"mr":47},{"m":"qwen3.6-27b","r":45,"s":70.42,"lo":37,"hi":57,"n":4,"rr":81,"mr":49},{"m":"qwen3.6-35b-a3b","r":46,"s":70.14,"lo":23,"hi":62,"n":10,"rr":95,"mr":42},{"m":"ring-2.6-1t-xhigh","r":47,"s":70.14,"lo":36,"hi":69,"n":4,"rr":13,"mr":50},{"m":"glm-4.7-flash","r":48,"s":70.02,"lo":30,"hi":157,"n":3,"rr":22,"mr":56},{"m":"kimi-k2.5-thinking","r":49,"s":69.83,"lo":28,"hi":68,"n":9,"rr":94,"mr":46},{"m":"muse-spark","r":50,"s":69.71,"lo":7,"hi":65,"n":3,"rr":15,"mr":52},{"m":"gpt-5","r":51,"s":69.64,"lo":26,"hi":81,"n":13,"rr":102,"mr":44},{"m":"deepseek-v3.2-thinking","r":52,"s":69.62,"lo":30,"hi":65,"n":10,"rr":96,"mr":48},{"m":"nex-n2-mini","r":53,"s":69.27,"lo":21,"hi":131,"n":3,"rr":71,"mr":61},{"m":"kolibri-1","r":54,"s":68.91,"lo":38,"hi":125,"n":3,"rr":10,"mr":54},{"m":"seed1.8","r":55,"s":68.8,"lo":12,"hi":75,"n":4,"rr":58,"mr":65},{"m":"gpt-5.4-mini","r":56,"s":68.74,"lo":40,"hi":67,"n":5,"rr":61,"mr":51},{"m":"kimi-k2.5","r":57,"s":67.41,"lo":44,"hi":71,"n":5,"rr":108,"mr":57},{"m":"qwen3.5-122b-a10b","r":58,"s":67.33,"lo":41,"hi":81,"n":8,"rr":83,"mr":60},{"m":"deepseek-v4-flash","r":59,"s":67.04,"lo":50,"hi":76,"n":5,"rr":99,"mr":59},{"m":"inkling-small","r":60,"s":66.85,"lo":17,"hi":93,"n":5,"rr":36,"mr":63},{"m":"areal-sea-235b-a22b","r":61,"s":66.81,"lo":47,"hi":89,"n":3,"rr":8,"mr":66},{"m":"qwen3.5-35b-a3b","r":62,"s":66.78,"lo":22,"hi":82,"n":10,"rr":72,"mr":55},{"m":"gpt-5.4-nano","r":63,"s":66.72,"lo":52,"hi":74,"n":4,"rr":77,"mr":62},{"m":"glm-4.7","r":64,"s":66.72,"lo":15,"hi":99,"n":3,"rr":129,"mr":75},{"m":"nemotron-3-ultra","r":65,"s":66.59,"lo":38,"hi":84,"n":6,"rr":62,"mr":53},{"m":"holo2-235b-a22b","r":66,"s":66.49,"lo":40,"hi":98,"n":3,"rr":4,"mr":77},{"m":"minimax-m2.7","r":67,"s":66.31,"lo":40,"hi":77,"n":6,"rr":76,"mr":58},{"m":"qwen3-max-thinking","r":68,"s":66.21,"lo":34,"hi":138,"n":5,"rr":88,"mr":69},{"m":"gemini-3-pro-preview","r":69,"s":65.96,"lo":11,"hi":79,"n":5,"rr":69,"mr":68},{"m":"kimi-k2-thinking","r":70,"s":65.91,"lo":30,"hi":91,"n":6,"rr":126,"mr":70},{"m":"gemma-4-31b-it","r":71,"s":65.54,"lo":37,"hi":85,"n":4,"rr":146,"mr":71},{"m":"gpt-5-codex","r":72,"s":65.17,"lo":45,"hi":81,"n":3,"rr":145,"mr":72},{"m":"mimo-v2-flash","r":73,"s":65.13,"lo":47,"hi":98,"n":3,"rr":112,"mr":74},{"m":"deepseek-v3.2","r":74,"s":65.09,"lo":31,"hi":84,"n":7,"rr":107,"mr":67},{"m":"nemotron-3.5-super-vl-120b-a12b","r":75,"s":64.96,"lo":41,"hi":98,"n":5,"rr":43,"mr":64},{"m":"gpt-5-thinking","r":76,"s":64.21,"lo":43,"hi":95,"n":3,"rr":60,"mr":80},{"m":"gemini-3-flash","r":77,"s":64,"lo":45,"hi":93,"n":6,"rr":84,"mr":73},{"m":"gpt-5-high","r":78,"s":63.69,"lo":32,"hi":90,"n":7,"rr":103,"mr":76},{"m":"gpt-5.1","r":79,"s":63.6,"lo":12,"hi":94,"n":4,"rr":37,"mr":79},{"m":"holo2-30b-a3b","r":80,"s":63.6,"lo":45,"hi":130,"n":4,"rr":12,"mr":84},{"m":"longcat-flash-lite-sparse","r":81,"s":63,"lo":35,"hi":110,"n":3,"rr":101,"mr":78},{"m":"comet-60b-a12b-fp8","r":82,"s":62,"lo":48,"hi":88,"n":4,"rr":30,"mr":82},{"m":"holo1.5-72b","r":83,"s":61.2,"lo":66,"hi":119,"n":3,"rr":11,"mr":94},{"m":"mai-code-1-flash","r":84,"s":60.68,"lo":51,"hi":126,"n":3,"rr":91,"mr":92},{"m":"comet-60b-a12b","r":85,"s":60.6,"lo":41,"hi":98,"n":4,"rr":31,"mr":87},{"m":"comet-60b-a12b-nvfp4","r":86,"s":59.54,"lo":45,"hi":112,"n":4,"rr":38,"mr":95},{"m":"qwen3-vl-30b-a3b-instruct","r":87,"s":59.44,"lo":52,"hi":115,"n":3,"rr":93,"mr":98},{"m":"minimax-m2","r":88,"s":58.89,"lo":68,"hi":107,"n":8,"rr":133,"mr":85},{"m":"north-mini-code-1.0","r":89,"s":58.83,"lo":78,"hi":108,"n":3,"rr":178,"mr":90},{"m":"gpt-5-mini-high","r":90,"s":58.1,"lo":76,"hi":102,"n":9,"rr":120,"mr":81},{"m":"grok-4","r":91,"s":57.66,"lo":49,"hi":115,"n":9,"rr":125,"mr":91},{"m":"o3","r":92,"s":57.61,"lo":72,"hi":107,"n":11,"rr":115,"mr":89},{"m":"holo2-8b","r":93,"s":57.59,"lo":75,"hi":142,"n":4,"rr":32,"mr":103},{"m":"claude-4.5-haiku","r":94,"s":57.38,"lo":77,"hi":107,"n":11,"rr":138,"mr":88},{"m":"nemotron-3.5-super-vl-120b-a12b-nvfp4","r":95,"s":57.15,"lo":50,"hi":113,"n":4,"rr":40,"mr":97},{"m":"qwen3.5-4b","r":96,"s":56.99,"lo":60,"hi":131,"n":7,"rr":117,"mr":93},{"m":"claude-opus-4.1","r":97,"s":56.69,"lo":66,"hi":110,"n":12,"rr":137,"mr":86},{"m":"holo2-4b","r":98,"s":56.61,"lo":77,"hi":143,"n":3,"rr":14,"mr":108},{"m":"claude-4.5-sonnet-thinking","r":99,"s":56.43,"lo":65,"hi":153,"n":8,"rr":116,"mr":83},{"m":"ui-venus-72b","r":100,"s":56.41,"lo":68,"hi":185,"n":4,"rr":34,"mr":105},{"m":"holo1.5-7b","r":101,"s":56.37,"lo":82,"hi":141,"n":3,"rr":19,"mr":107},{"m":"qwen3.5-9b","r":102,"s":56.24,"lo":82,"hi":132,"n":7,"rr":171,"mr":96},{"m":"kimi-k2-0905-preview","r":103,"s":55.52,"lo":86,"hi":111,"n":4,"rr":140,"mr":100},{"m":"qwen3-vl-30b-a3b-thinking","r":104,"s":55.35,"lo":86,"hi":146,"n":3,"rr":25,"mr":115},{"m":"seed-1.5-vl","r":105,"s":55.18,"lo":81,"hi":122,"n":3,"rr":113,"mr":117},{"m":"command-a-plus-05-2026","r":106,"s":54.88,"lo":78,"hi":154,"n":3,"rr":147,"mr":101},{"m":"claude-sonnet-4","r":107,"s":54.26,"lo":76,"hi":137,"n":19,"rr":118,"mr":99},{"m":"kimi-k2-instruct-0905","r":108,"s":53.65,"lo":30,"hi":128,"n":4,"rr":122,"mr":104},{"m":"qwen3-vl-32b-instruct","r":109,"s":53.17,"lo":88,"hi":137,"n":3,"rr":123,"mr":124},{"m":"nemotron-3-super-120b-a12b","r":110,"s":52.9,"lo":81,"hi":132,"n":6,"rr":119,"mr":102},{"m":"joyai-llm-flash","r":111,"s":52.72,"lo":91,"hi":151,"n":3,"rr":54,"mr":112},{"m":"claude-sonnet-4-thinking","r":112,"s":52.61,"lo":80,"hi":138,"n":5,"rr":142,"mr":113},{"m":"kimi-k2-0905","r":113,"s":52.46,"lo":87,"hi":122,"n":3,"rr":139,"mr":106},{"m":"qwen3-coder-480b-a35b-instruct","r":114,"s":52.21,"lo":34,"hi":158,"n":5,"rr":149,"mr":119},{"m":"deepseek-v3.1","r":115,"s":51.74,"lo":85,"hi":140,"n":5,"rr":155,"mr":114},{"m":"grok-code-fast-1","r":116,"s":51.41,"lo":103,"hi":144,"n":4,"rr":177,"mr":111},{"m":"k-exaone","r":117,"s":51.33,"lo":99,"hi":130,"n":4,"rr":87,"mr":116},{"m":"glm-4.6","r":118,"s":51.22,"lo":87,"hi":135,"n":7,"rr":143,"mr":110},{"m":"exaone-4.5-33b-thinking","r":119,"s":50.94,"lo":93,"hi":128,"n":3,"rr":48,"mr":120},{"m":"qwen3-vl-235b-a22b-thinking","r":120,"s":50.52,"lo":86,"hi":160,"n":8,"rr":75,"mr":125},{"m":"longcat-flash-lite","r":121,"s":50.12,"lo":108,"hi":132,"n":4,"rr":90,"mr":122},{"m":"grok-4-fast","r":122,"s":49.82,"lo":103,"hi":145,"n":5,"rr":182,"mr":118},{"m":"kimi-k2-0711-preview","r":123,"s":49.8,"lo":107,"hi":149,"n":3,"rr":165,"mr":133},{"m":"qwen2.5-vl-72b","r":124,"s":49.64,"lo":98,"hi":194,"n":3,"rr":70,"mr":144},{"m":"nova-2-lite","r":125,"s":49.34,"lo":98,"hi":168,"n":3,"rr":151,"mr":127},{"m":"qwen3-vl-4b-thinking","r":126,"s":49.26,"lo":113,"hi":165,"n":3,"rr":45,"mr":143},{"m":"ui-venus-7b","r":127,"s":49.14,"lo":110,"hi":170,"n":4,"rr":65,"mr":141},{"m":"qwen3-vl-8b-thinking","r":128,"s":48.82,"lo":113,"hi":167,"n":3,"rr":50,"mr":146},{"m":"qwen3-vl-8b-instruct","r":129,"s":48.75,"lo":110,"hi":152,"n":3,"rr":144,"mr":145},{"m":"qwen3-max-instruct-preview","r":130,"s":48.73,"lo":107,"hi":153,"n":3,"rr":205,"mr":134},{"m":"devstral-small-2","r":131,"s":48.44,"lo":90,"hi":167,"n":3,"rr":202,"mr":135},{"m":"claude-opus-4","r":132,"s":48.3,"lo":75,"hi":151,"n":7,"rr":106,"mr":128},{"m":"gpt-5-mini","r":133,"s":48.25,"lo":107,"hi":164,"n":7,"rr":175,"mr":126},{"m":"holo1.5-3b","r":134,"s":48.08,"lo":102,"hi":179,"n":3,"rr":44,"mr":149},{"m":"gemma-4-26b-a4b-it","r":135,"s":47.99,"lo":95,"hi":167,"n":8,"rr":162,"mr":109},{"m":"o4-mini","r":136,"s":47.89,"lo":110,"hi":159,"n":7,"rr":161,"mr":131},{"m":"kimi-k2-instruct-0711","r":137,"s":47.76,"lo":101,"hi":158,"n":3,"rr":181,"mr":138},{"m":"gemma-4-12b-it","r":138,"s":47.73,"lo":113,"hi":160,"n":4,"rr":204,"mr":123},{"m":"kimi-k2-instruct","r":139,"s":47.72,"lo":119,"hi":158,"n":8,"rr":167,"mr":121},{"m":"gpt-oss-120b-high","r":140,"s":46.44,"lo":113,"hi":169,"n":5,"rr":131,"mr":132},{"m":"kolibri-origin","r":141,"s":46.4,"lo":121,"hi":171,"n":3,"rr":78,"mr":137},{"m":"ui-tars-1.5-7b","r":142,"s":46.38,"lo":104,"hi":177,"n":4,"rr":89,"mr":153},{"m":"holotron-12b","r":143,"s":46.28,"lo":127,"hi":178,"n":3,"rr":59,"mr":154},{"m":"glm-4.5","r":144,"s":46.02,"lo":101,"hi":191,"n":9,"rr":166,"mr":129},{"m":"holo1-7b","r":145,"s":45.6,"lo":130,"hi":180,"n":3,"rr":64,"mr":155},{"m":"nemotron-labs-3-puzzle-75b-a9b","r":146,"s":45.38,"lo":126,"hi":155,"n":4,"rr":124,"mr":142},{"m":"qwen3-vl-4b-instruct","r":147,"s":45.35,"lo":115,"hi":174,"n":3,"rr":154,"mr":157},{"m":"gemini-2.5-pro","r":148,"s":45.25,"lo":111,"hi":175,"n":19,"rr":164,"mr":130},{"m":"deepseek-v3.2-exp","r":149,"s":45.21,"lo":92,"hi":183,"n":6,"rr":157,"mr":139},{"m":"deepseek-v3.1-terminus","r":150,"s":44.72,"lo":108,"hi":179,"n":5,"rr":198,"mr":136},{"m":"apriel-1.6-15b-thinker","r":151,"s":44.58,"lo":121,"hi":178,"n":5,"rr":127,"mr":140},{"m":"longcat-next","r":152,"s":44.36,"lo":122,"hi":166,"n":5,"rr":114,"mr":151},{"m":"glm-4.5-air","r":153,"s":43.79,"lo":127,"hi":164,"n":8,"rr":150,"mr":147},{"m":"kimi-k2","r":154,"s":42.37,"lo":120,"hi":203,"n":5,"rr":156,"mr":150},{"m":"qwen3-vl-2b-instruct","r":155,"s":42.36,"lo":119,"hi":182,"n":3,"rr":169,"mr":165},{"m":"gpt-4.1","r":156,"s":42.26,"lo":108,"hi":172,"n":11,"rr":153,"mr":148},{"m":"openpangu-r-72b-2512-slow-thinking","r":157,"s":42.13,"lo":91,"hi":166,"n":5,"rr":66,"mr":158},{"m":"solar-open-100b","r":158,"s":41.93,"lo":125,"hi":181,"n":5,"rr":163,"mr":156},{"m":"gpt-4.1-2025-04-14","r":159,"s":41.9,"lo":107,"hi":188,"n":3,"rr":179,"mr":164},{"m":"claude-3.7-sonnet","r":160,"s":41.89,"lo":97,"hi":167,"n":6,"rr":176,"mr":160},{"m":"qwen3-235b-a22b-instruct-2507","r":161,"s":41.86,"lo":83,"hi":191,"n":5,"rr":183,"mr":162},{"m":"glm-4.6v-flash","r":162,"s":41.57,"lo":127,"hi":184,"n":3,"rr":168,"mr":170},{"m":"holo1-3b","r":163,"s":41.03,"lo":145,"hi":191,"n":3,"rr":86,"mr":174},{"m":"gpt-oss-120b-medium","r":164,"s":39.37,"lo":130,"hi":171,"n":3,"rr":105,"mr":163},{"m":"qwen3-235b-a22b-thinking-2507","r":165,"s":39.33,"lo":125,"hi":181,"n":10,"rr":141,"mr":161},{"m":"qwen3.5-2b","r":166,"s":39.17,"lo":126,"hi":214,"n":3,"rr":195,"mr":166},{"m":"apriel-1.5-15b-thinker","r":167,"s":38.95,"lo":127,"hi":199,"n":5,"rr":160,"mr":168},{"m":"openpangu-r-72b-2512-fast-thinking","r":168,"s":38.88,"lo":133,"hi":175,"n":5,"rr":98,"mr":167},{"m":"openpangu-r-7b-2512-slow-thinking","r":169,"s":38.45,"lo":125,"hi":176,"n":5,"rr":100,"mr":171},{"m":"qwen3-next-80b-a3b-thinking","r":170,"s":38.45,"lo":130,"hi":179,"n":5,"rr":92,"mr":172},{"m":"nemotron-3-nano-30b-a3b","r":171,"s":38.44,"lo":143,"hi":175,"n":3,"rr":111,"mr":169},{"m":"qwen2.5-vl-72b-instruct","r":172,"s":38.31,"lo":114,"hi":198,"n":3,"rr":199,"mr":182},{"m":"gemini-2.5-flash","r":173,"s":37.53,"lo":155,"hi":191,"n":15,"rr":189,"mr":159},{"m":"deepseek-r1","r":174,"s":37.07,"lo":112,"hi":193,"n":3,"rr":172,"mr":180},{"m":"gpt-oss-120b","r":175,"s":36.85,"lo":122,"hi":200,"n":11,"rr":186,"mr":152},{"m":"gpt-5-mini-minimal","r":176,"s":36.52,"lo":135,"hi":194,"n":3,"rr":187,"mr":186},{"m":"deepseek-r1-0528","r":177,"s":36.4,"lo":157,"hi":187,"n":8,"rr":159,"mr":173},{"m":"openpangu-r-7b-2512-fast-thinking","r":178,"s":35.7,"lo":149,"hi":187,"n":5,"rr":109,"mr":175},{"m":"mistral-small-4-thinking","r":179,"s":35.3,"lo":150,"hi":185,"n":3,"rr":134,"mr":178},{"m":"qwen2.5-vl-7b","r":180,"s":35.22,"lo":162,"hi":199,"n":4,"rr":132,"mr":188},{"m":"gemini-2.5-flash-thinking","r":181,"s":34.82,"lo":147,"hi":188,"n":6,"rr":128,"mr":176},{"m":"deepseek-v3-0324","r":182,"s":34.19,"lo":122,"hi":191,"n":5,"rr":130,"mr":181},{"m":"qwen2.5-vl-3b","r":183,"s":34.01,"lo":162,"hi":204,"n":3,"rr":121,"mr":194},{"m":"gemini-2.5-flash-preview-09-2025","r":184,"s":33.94,"lo":158,"hi":191,"n":5,"rr":158,"mr":177},{"m":"gpt-4.1-mini","r":185,"s":33.49,"lo":165,"hi":203,"n":4,"rr":207,"mr":185},{"m":"gpt-oss-20b","r":186,"s":33.34,"lo":144,"hi":211,"n":6,"rr":192,"mr":179},{"m":"nemotron-labs-3-elastic-30b-a3b","r":187,"s":32.46,"lo":162,"hi":192,"n":3,"rr":148,"mr":187},{"m":"qwen3-235b-a22b","r":188,"s":32.23,"lo":167,"hi":200,"n":10,"rr":174,"mr":183},{"m":"nvidia-nemotron-3-nano-30b-a3b-bf16","r":189,"s":31.75,"lo":175,"hi":203,"n":5,"rr":188,"mr":184},{"m":"qwen3-30b-a3b-thinking-2507","r":190,"s":30.96,"lo":159,"hi":200,"n":6,"rr":152,"mr":189},{"m":"o3-mini-high","r":191,"s":30.76,"lo":127,"hi":205,"n":5,"rr":170,"mr":195},{"m":"exaone-4.0-32b-thinking","r":192,"s":30.41,"lo":136,"hi":199,"n":3,"rr":135,"mr":191},{"m":"qwen3-30b-a3b","r":193,"s":30.32,"lo":170,"hi":198,"n":5,"rr":136,"mr":192},{"m":"nemotron-3-nano-4b-thinking","r":194,"s":30.14,"lo":168,"hi":206,"n":3,"rr":180,"mr":193},{"m":"deepseek-v3","r":195,"s":29.03,"lo":120,"hi":207,"n":3,"rr":200,"mr":196},{"m":"gpt-4o-2024-11-20","r":196,"s":28.73,"lo":132,"hi":206,"n":3,"rr":190,"mr":197},{"m":"gemma-4-e4b-it","r":197,"s":28.21,"lo":176,"hi":207,"n":5,"rr":211,"mr":190},{"m":"nemotron-3-nano-4b","r":198,"s":28.16,"lo":165,"hi":209,"n":3,"rr":193,"mr":198},{"m":"qwen2.5-coder-32b-instruct","r":199,"s":27.38,"lo":139,"hi":212,"n":3,"rr":201,"mr":205},{"m":"gpt-4o","r":200,"s":27.06,"lo":175,"hi":210,"n":8,"rr":197,"mr":202},{"m":"qwen3-32b-thinking","r":201,"s":26.82,"lo":186,"hi":208,"n":9,"rr":184,"mr":199},{"m":"gemini-2.5-flash-lite","r":202,"s":26.37,"lo":163,"hi":207,"n":4,"rr":196,"mr":200},{"m":"gemma-4-e2b-it","r":203,"s":25.22,"lo":183,"hi":213,"n":4,"rr":215,"mr":203},{"m":"qwen3-next-80b-a3b-instruct","r":204,"s":25.14,"lo":176,"hi":210,"n":7,"rr":173,"mr":201},{"m":"seed-coder-8b-instruct","r":205,"s":24.61,"lo":138,"hi":215,"n":3,"rr":206,"mr":208},{"m":"kimi-linear-instruct","r":206,"s":24.57,"lo":162,"hi":210,"n":4,"rr":203,"mr":204},{"m":"llama-4-maverick","r":207,"s":22.71,"lo":177,"hi":213,"n":4,"rr":217,"mr":207},{"m":"qwen3-8b-thinking","r":208,"s":21.08,"lo":142,"hi":212,"n":3,"rr":208,"mr":211},{"m":"qwen3-32b-nothinking","r":209,"s":20.77,"lo":184,"hi":213,"n":5,"rr":191,"mr":210},{"m":"apertus-70b-instruct","r":210,"s":20.58,"lo":165,"hi":213,"n":3,"rr":210,"mr":209},{"m":"qwen3-14b","r":211,"s":19.99,"lo":162,"hi":213,"n":3,"rr":209,"mr":212},{"m":"qwen3-32b","r":212,"s":18.93,"lo":186,"hi":215,"n":9,"rr":212,"mr":206},{"m":"qwen2.5-coder-7b-instruct","r":213,"s":17.14,"lo":137,"hi":217,"n":3,"rr":214,"mr":215},{"m":"qwen3-30b-a3b-instruct-2507","r":214,"s":15.64,"lo":172,"hi":216,"n":3,"rr":194,"mr":213},{"m":"qwen3-omni-30b-a3b-instruct","r":215,"s":15.59,"lo":123,"hi":216,"n":4,"rr":185,"mr":214},{"m":"qwen3-8b","r":216,"s":12.55,"lo":194,"hi":217,"n":6,"rr":216,"mr":216},{"m":"nemotron-nano-12b-v2-vl","r":217,"s":12.15,"lo":185,"hi":217,"n":4,"rr":213,"mr":217}]},"faix-code":{"name":"Code","n":756,"nb":38,"acc":0.8538,"raw_acc":0.6958,"rows":[{"m":"claude-fable-5","r":1,"s":93.58,"lo":1,"hi":7,"n":5,"rr":17,"mr":1},{"m":"kimi-k3","r":2,"s":91.21,"lo":1,"hi":281,"n":3,"rr":14,"mr":3},{"m":"claude-mythos-preview","r":3,"s":91.01,"lo":2,"hi":85,"n":3,"rr":3,"mr":2},{"m":"claude-opus-4.8","r":4,"s":90.67,"lo":2,"hi":7,"n":7,"rr":19,"mr":4},{"m":"gpt-5.5","r":5,"s":90.44,"lo":1,"hi":10,"n":9,"rr":36,"mr":5},{"m":"claude-opus-4.7","r":6,"s":88.68,"lo":4,"hi":24,"n":8,"rr":108,"mr":6},{"m":"fugu-ultra","r":7,"s":88.25,"lo":5,"hi":272,"n":3,"rr":40,"mr":7},{"m":"gpt-5.6-luna","r":8,"s":87.89,"lo":4,"hi":273,"n":3,"rr":110,"mr":11},{"m":"glm-5.2","r":9,"s":87.51,"lo":5,"hi":70,"n":6,"rr":24,"mr":8},{"m":"gpt-5.6-sol","r":10,"s":87.16,"lo":2,"hi":56,"n":4,"rr":135,"mr":14},{"m":"claude-sonnet-5","r":11,"s":87.01,"lo":6,"hi":28,"n":5,"rr":213,"mr":9},{"m":"claude-opus-4.6","r":12,"s":86.82,"lo":7,"hi":19,"n":11,"rr":146,"mr":10},{"m":"gemini-3.1-pro","r":13,"s":86.54,"lo":7,"hi":22,"n":9,"rr":178,"mr":12},{"m":"qwen3.8-max","r":14,"s":86.52,"lo":8,"hi":280,"n":3,"rr":131,"mr":15},{"m":"qwen3.8-omni-flash","r":15,"s":86.16,"lo":10,"hi":227,"n":3,"rr":22,"mr":16},{"m":"qwen3.8-flash-next","r":16,"s":86.12,"lo":7,"hi":222,"n":5,"rr":52,"mr":13},{"m":"fugu","r":17,"s":85.67,"lo":8,"hi":274,"n":3,"rr":96,"mr":23},{"m":"deepseek-v4-pro","r":18,"s":85.67,"lo":3,"hi":40,"n":7,"rr":29,"mr":17},{"m":"gpt-5.3-codex","r":19,"s":85.54,"lo":10,"hi":286,"n":3,"rr":103,"mr":27},{"m":"gemini-3-pro-preview","r":20,"s":85.37,"lo":8,"hi":40,"n":15,"rr":20,"mr":19},{"m":"gpt-5.4","r":21,"s":85.29,"lo":10,"hi":50,"n":9,"rr":259,"mr":18},{"m":"qwen3.7-max","r":22,"s":84.88,"lo":17,"hi":34,"n":6,"rr":70,"mr":20},{"m":"deepseek-v4-pro-thinking-max","r":23,"s":84.78,"lo":14,"hi":41,"n":6,"rr":88,"mr":21},{"m":"deepseek-v4-flash-0731","r":24,"s":84.72,"lo":8,"hi":263,"n":5,"rr":73,"mr":24},{"m":"claude-opus-4.5","r":25,"s":84.62,"lo":11,"hi":31,"n":21,"rr":48,"mr":22},{"m":"kimi-k2.6-thinking","r":26,"s":84.16,"lo":19,"hi":34,"n":7,"rr":106,"mr":25},{"m":"ornith-1.0-397b","r":27,"s":84.05,"lo":20,"hi":273,"n":3,"rr":46,"mr":30},{"m":"beam","r":28,"s":83.85,"lo":19,"hi":223,"n":5,"rr":64,"mr":26},{"m":"deepseek-v4-flash","r":29,"s":83.73,"lo":6,"hi":65,"n":7,"rr":91,"mr":29},{"m":"ornith-1.5-122b","r":30,"s":83.59,"lo":18,"hi":279,"n":3,"rr":82,"mr":32},{"m":"qwen3.7-plus","r":31,"s":83.55,"lo":20,"hi":55,"n":6,"rr":100,"mr":28},{"m":"glm-5.1","r":32,"s":82.93,"lo":22,"hi":59,"n":6,"rr":109,"mr":31},{"m":"hy3","r":33,"s":82.81,"lo":25,"hi":211,"n":4,"rr":35,"mr":36},{"m":"dots3-note-preview","r":34,"s":82.72,"lo":22,"hi":222,"n":3,"rr":9,"mr":40},{"m":"claude-sonnet-4.6","r":35,"s":82.67,"lo":14,"hi":51,"n":9,"rr":203,"mr":33},{"m":"deepseek-v4-pro-thinking","r":36,"s":82.55,"lo":29,"hi":60,"n":5,"rr":74,"mr":34},{"m":"gemini-3-pro","r":37,"s":82.49,"lo":17,"hi":60,"n":13,"rr":186,"mr":35},{"m":"gpt-5.2-high","r":38,"s":82.3,"lo":12,"hi":123,"n":3,"rr":242,"mr":51},{"m":"qwen3.6-max-preview","r":39,"s":82.17,"lo":27,"hi":260,"n":3,"rr":363,"mr":45},{"m":"deepseek-v4-flash-thinking-max","r":40,"s":81.96,"lo":22,"hi":79,"n":7,"rr":161,"mr":38},{"m":"claude-sonnet-4.5","r":41,"s":81.95,"lo":14,"hi":79,"n":22,"rr":87,"mr":37},{"m":"gpt-5.2","r":42,"s":81.69,"lo":25,"hi":57,"n":8,"rr":156,"mr":41},{"m":"inkling-small","r":43,"s":81.52,"lo":37,"hi":255,"n":5,"rr":118,"mr":44},{"m":"glm-5.3-flash","r":44,"s":81.51,"lo":15,"hi":241,"n":5,"rr":77,"mr":39},{"m":"qwen3.6-plus","r":45,"s":81.42,"lo":37,"hi":71,"n":6,"rr":152,"mr":43},{"m":"claude-opus-4.5-thinking","r":46,"s":81.41,"lo":25,"hi":71,"n":6,"rr":142,"mr":48},{"m":"gpt-5.2-thinking","r":47,"s":81.4,"lo":35,"hi":205,"n":3,"rr":58,"mr":52},{"m":"qwen3.8-27b","r":48,"s":81.38,"lo":25,"hi":76,"n":8,"rr":33,"mr":42},{"m":"glm-5","r":49,"s":81.12,"lo":35,"hi":67,"n":6,"rr":137,"mr":47},{"m":"seed2.1-pro","r":50,"s":81.01,"lo":32,"hi":277,"n":3,"rr":101,"mr":55},{"m":"mimo-v2.5","r":51,"s":80.98,"lo":33,"hi":107,"n":6,"rr":194,"mr":49},{"m":"minimax-m2.7","r":52,"s":80.95,"lo":28,"hi":106,"n":8,"rr":231,"mr":46},{"m":"minimax-m3","r":53,"s":80.91,"lo":39,"hi":271,"n":3,"rr":261,"mr":56},{"m":"deepseek-v4-flash-thinking","r":54,"s":80.68,"lo":41,"hi":70,"n":5,"rr":116,"mr":50},{"m":"gpt-5-medium","r":55,"s":80.45,"lo":17,"hi":131,"n":3,"rr":8,"mr":66},{"m":"iquest-coder-v1-40b-loop-thinking","r":56,"s":80.38,"lo":1,"hi":136,"n":4,"rr":1,"mr":70},{"m":"gpt-5.2-thinking-xhigh","r":57,"s":80.3,"lo":37,"hi":73,"n":5,"rr":238,"mr":53},{"m":"seed2.0-pro","r":58,"s":80.15,"lo":45,"hi":106,"n":3,"rr":81,"mr":60},{"m":"gpt-5.4-mini","r":59,"s":80.12,"lo":36,"hi":160,"n":5,"rr":148,"mr":58},{"m":"mimo-v2-pro","r":60,"s":80.08,"lo":49,"hi":109,"n":3,"rr":119,"mr":59},{"m":"kimi-k2.5-thinking","r":61,"s":79.85,"lo":36,"hi":71,"n":8,"rr":249,"mr":57},{"m":"qwen3.6-27b","r":62,"s":79.69,"lo":45,"hi":99,"n":6,"rr":201,"mr":54},{"m":"minimax-m2.5","r":63,"s":79.59,"lo":29,"hi":153,"n":4,"rr":351,"mr":67},{"m":"gemini-3-flash","r":64,"s":79.21,"lo":34,"hi":89,"n":9,"rr":355,"mr":65},{"m":"nemotron-3-ultra","r":65,"s":79.18,"lo":44,"hi":258,"n":5,"rr":181,"mr":64},{"m":"inkling","r":66,"s":79.04,"lo":58,"hi":294,"n":3,"rr":299,"mr":71},{"m":"kimi-k2.5","r":67,"s":79.04,"lo":57,"hi":105,"n":6,"rr":220,"mr":61},{"m":"ling-3.0-flash","r":68,"s":78.96,"lo":32,"hi":307,"n":3,"rr":25,"mr":80},{"m":"qwen3.5-397b-a17b","r":69,"s":78.93,"lo":62,"hi":92,"n":6,"rr":208,"mr":62},{"m":"iquest-coder-v1-40b-thinking","r":70,"s":78.92,"lo":2,"hi":142,"n":4,"rr":2,"mr":84},{"m":"gpt-5-codex","r":71,"s":78.86,"lo":24,"hi":93,"n":6,"rr":157,"mr":68},{"m":"ornith-1.5-35b-a3b","r":72,"s":78.79,"lo":55,"hi":281,"n":3,"rr":217,"mr":74},{"m":"nemotron-3.5-super-vl-120b-a12b","r":73,"s":78.76,"lo":53,"hi":264,"n":5,"rr":179,"mr":63},{"m":"gpt-5.1-high","r":74,"s":78.64,"lo":34,"hi":89,"n":4,"rr":373,"mr":72},{"m":"gpt-5.1","r":75,"s":78.44,"lo":27,"hi":118,"n":9,"rr":66,"mr":79},{"m":"gpt-5","r":76,"s":78.38,"lo":22,"hi":99,"n":16,"rr":265,"mr":75},{"m":"step-3.5-flash-20260204","r":77,"s":78.18,"lo":61,"hi":98,"n":5,"rr":182,"mr":69},{"m":"hy3-preview","r":78,"s":78.17,"lo":62,"hi":122,"n":3,"rr":175,"mr":73},{"m":"mai-thinking-1","r":79,"s":77.86,"lo":55,"hi":125,"n":4,"rr":185,"mr":76},{"m":"comet-60b-a12b-fp8","r":80,"s":77.3,"lo":75,"hi":291,"n":4,"rr":302,"mr":77},{"m":"qwen3.8-27b-ud-q4-k-xl","r":81,"s":77.29,"lo":50,"hi":238,"n":4,"rr":5,"mr":96},{"m":"gpt-5-mini","r":82,"s":77.29,"lo":23,"hi":128,"n":11,"rr":306,"mr":91},{"m":"gemini-3.5-flash-lite","r":83,"s":77.19,"lo":69,"hi":298,"n":3,"rr":359,"mr":93},{"m":"ornith-1.0-35b","r":84,"s":77.13,"lo":71,"hi":318,"n":4,"rr":368,"mr":86},{"m":"claude-opus-4.1","r":85,"s":77.05,"lo":34,"hi":164,"n":9,"rr":335,"mr":89},{"m":"kimi-k2-thinking","r":86,"s":77.03,"lo":34,"hi":109,"n":16,"rr":126,"mr":81},{"m":"qwen3.6-35b-a3b","r":87,"s":77,"lo":49,"hi":104,"n":8,"rr":230,"mr":78},{"m":"agents-a1","r":88,"s":76.99,"lo":8,"hi":167,"n":4,"rr":243,"mr":100},{"m":"nemotron-3.5-super-vl-120b-a12b-nvfp4","r":89,"s":76.97,"lo":79,"hi":304,"n":4,"rr":315,"mr":82},{"m":"step-3.7-flash","r":90,"s":76.97,"lo":61,"hi":270,"n":4,"rr":83,"mr":92},{"m":"mai-code-1-flash","r":91,"s":76.92,"lo":67,"hi":323,"n":5,"rr":380,"mr":83},{"m":"laguna-m.1","r":92,"s":76.84,"lo":79,"hi":278,"n":4,"rr":311,"mr":85},{"m":"solar-open-2-250b","r":93,"s":76.82,"lo":19,"hi":266,"n":3,"rr":62,"mr":105},{"m":"ternary-bonsai-2-27b","r":94,"s":76.79,"lo":40,"hi":243,"n":4,"rr":4,"mr":99},{"m":"mistral-medium-3.5","r":95,"s":76.65,"lo":67,"hi":313,"n":3,"rr":93,"mr":101},{"m":"glm-4.7-thinking","r":96,"s":76.43,"lo":68,"hi":113,"n":3,"rr":136,"mr":103},{"m":"claude-4.5-sonnet-thinking","r":97,"s":76.39,"lo":32,"hi":132,"n":9,"rr":346,"mr":97},{"m":"comet-60b-a12b","r":98,"s":76.36,"lo":83,"hi":311,"n":4,"rr":333,"mr":88},{"m":"deepseek-v3.2-thinking","r":99,"s":76.33,"lo":67,"hi":110,"n":9,"rr":183,"mr":87},{"m":"mimo-v2-flash","r":100,"s":76.32,"lo":56,"hi":160,"n":4,"rr":144,"mr":94},{"m":"minimax-m2.1","r":101,"s":76.24,"lo":58,"hi":128,"n":7,"rr":272,"mr":90},{"m":"comet-60b-a12b-nvfp4","r":102,"s":75.99,"lo":89,"hi":315,"n":4,"rr":345,"mr":95},{"m":"ring-2.6-1t-xhigh","r":103,"s":75.7,"lo":55,"hi":324,"n":3,"rr":107,"mr":112},{"m":"muse-glimmer-30b","r":104,"s":75.68,"lo":51,"hi":129,"n":4,"rr":57,"mr":102},{"m":"qwen3-max-thinking","r":105,"s":75.61,"lo":71,"hi":287,"n":4,"rr":234,"mr":98},{"m":"seed1.8","r":106,"s":75.3,"lo":76,"hi":121,"n":4,"rr":292,"mr":108},{"m":"o3","r":107,"s":75,"lo":33,"hi":144,"n":7,"rr":325,"mr":109},{"m":"grok-4-fast","r":108,"s":74.94,"lo":44,"hi":186,"n":4,"rr":206,"mr":114},{"m":"gpt-5-high","r":109,"s":74.91,"lo":33,"hi":133,"n":13,"rr":340,"mr":104},{"m":"qwen3.5-122b-a10b","r":110,"s":74.67,"lo":54,"hi":120,"n":9,"rr":319,"mr":106},{"m":"gpt-5-thinking","r":111,"s":74.64,"lo":52,"hi":136,"n":4,"rr":366,"mr":116},{"m":"seed2.0-lite","r":112,"s":74.57,"lo":93,"hi":169,"n":3,"rr":210,"mr":110},{"m":"gemini-2.5-pro-preview-06-05","r":113,"s":74.42,"lo":34,"hi":463,"n":3,"rr":327,"mr":122},{"m":"longcat-flash-thinking-2601","r":114,"s":74.27,"lo":84,"hi":138,"n":3,"rr":184,"mr":120},{"m":"qwen3.5-27b","r":115,"s":73.89,"lo":92,"hi":143,"n":10,"rr":215,"mr":107},{"m":"kat-coder-v2.5-dev","r":116,"s":73.88,"lo":107,"hi":283,"n":3,"rr":323,"mr":118},{"m":"deepseek-v3.2","r":117,"s":73.53,"lo":61,"hi":129,"n":19,"rr":162,"mr":115},{"m":"raon-1-mini-preview","r":118,"s":73.35,"lo":102,"hi":254,"n":3,"rr":211,"mr":123},{"m":"qwen3.5-35b-a3b","r":119,"s":73.08,"lo":95,"hi":152,"n":9,"rr":264,"mr":111},{"m":"gemini-3-flash-preview","r":120,"s":72.97,"lo":26,"hi":242,"n":12,"rr":56,"mr":113},{"m":"laguna-xs.2","r":121,"s":72.96,"lo":105,"hi":351,"n":4,"rr":417,"mr":119},{"m":"kimi-k2-0905-preview","r":122,"s":72.86,"lo":87,"hi":236,"n":5,"rr":457,"mr":124},{"m":"claude-4.5-haiku","r":123,"s":72.8,"lo":72,"hi":164,"n":11,"rr":372,"mr":121},{"m":"kolibri-1","r":124,"s":72.31,"lo":89,"hi":173,"n":3,"rr":11,"mr":126},{"m":"laguna-xs-2.1","r":125,"s":72.15,"lo":103,"hi":312,"n":5,"rr":412,"mr":117},{"m":"nanbeige4.2-3b","r":126,"s":71.88,"lo":70,"hi":170,"n":5,"rr":225,"mr":127},{"m":"gpt-5-mini-high","r":127,"s":71.8,"lo":82,"hi":162,"n":7,"rr":466,"mr":125},{"m":"devstral-2","r":128,"s":71.8,"lo":104,"hi":225,"n":3,"rr":386,"mr":129},{"m":"o3-high","r":129,"s":71.71,"lo":40,"hi":182,"n":8,"rr":558,"mr":139},{"m":"gpt-5.4-none","r":130,"s":71.59,"lo":96,"hi":180,"n":3,"rr":250,"mr":130},{"m":"qwen3-coder-next","r":131,"s":71.26,"lo":92,"hi":152,"n":4,"rr":318,"mr":133},{"m":"grok-4","r":132,"s":71.25,"lo":52,"hi":195,"n":9,"rr":362,"mr":140},{"m":"ornith-1.0-9b","r":133,"s":71.22,"lo":117,"hi":399,"n":3,"rr":401,"mr":132},{"m":"spark-x2.6-4b","r":134,"s":71.17,"lo":113,"hi":334,"n":3,"rr":402,"mr":131},{"m":"deepseek-v3.1-terminus","r":135,"s":71.15,"lo":62,"hi":157,"n":10,"rr":240,"mr":134},{"m":"telechat3-coder-36b-thinking","r":136,"s":71.12,"lo":79,"hi":157,"n":6,"rr":114,"mr":141},{"m":"claude-sonnet-4","r":137,"s":71.11,"lo":42,"hi":161,"n":17,"rr":405,"mr":135},{"m":"gpt-5.4-nano","r":138,"s":70.93,"lo":89,"hi":291,"n":4,"rr":568,"mr":146},{"m":"nemotron-3-super-120b-a12b","r":139,"s":70.87,"lo":84,"hi":169,"n":8,"rr":248,"mr":128},{"m":"longcat-flash-lite-sparse","r":140,"s":70.72,"lo":125,"hi":230,"n":3,"rr":411,"mr":136},{"m":"ling-2.6-1t","r":141,"s":70.59,"lo":106,"hi":220,"n":3,"rr":305,"mr":145},{"m":"nova-2-pro","r":142,"s":70.45,"lo":66,"hi":174,"n":3,"rr":314,"mr":152},{"m":"gemini-2.5-pro","r":143,"s":70.39,"lo":54,"hi":157,"n":24,"rr":392,"mr":142},{"m":"claude-opus-4","r":144,"s":70.34,"lo":54,"hi":210,"n":14,"rr":300,"mr":148},{"m":"o4-mini","r":145,"s":70.15,"lo":63,"hi":180,"n":5,"rr":330,"mr":151},{"m":"minimax-m2","r":146,"s":70.08,"lo":98,"hi":211,"n":11,"rr":239,"mr":138},{"m":"claude-opus-4-thinking","r":147,"s":70.01,"lo":48,"hi":193,"n":4,"rr":190,"mr":153},{"m":"deepseek-r1-0528","r":148,"s":69.68,"lo":54,"hi":171,"n":11,"rr":312,"mr":150},{"m":"nex-n2-mini","r":149,"s":69.49,"lo":85,"hi":252,"n":5,"rr":528,"mr":155},{"m":"claude-sonnet-4-thinking","r":150,"s":69.36,"lo":80,"hi":247,"n":4,"rr":391,"mr":168},{"m":"gemma-4-31b-it","r":151,"s":69.3,"lo":125,"hi":270,"n":8,"rr":285,"mr":137},{"m":"north-mini-code-1.0","r":152,"s":69.23,"lo":134,"hi":201,"n":5,"rr":478,"mr":143},{"m":"glm-4.6","r":153,"s":69.18,"lo":106,"hi":208,"n":10,"rr":222,"mr":147},{"m":"gemma-4-26b-a4b-it","r":154,"s":69.07,"lo":92,"hi":190,"n":8,"rr":382,"mr":144},{"m":"qwen3-coder-480b-a35b","r":155,"s":68.91,"lo":110,"hi":211,"n":6,"rr":636,"mr":156},{"m":"iquest-coder-v1-40b-instruct","r":156,"s":68.43,"lo":69,"hi":237,"n":16,"rr":127,"mr":149},{"m":"ernie-5.0","r":157,"s":68.38,"lo":103,"hi":199,"n":3,"rr":6,"mr":160},{"m":"deepseek-v3.1","r":158,"s":68.28,"lo":106,"hi":315,"n":13,"rr":224,"mr":154},{"m":"qwen3-235b-a22b-thinking-2507","r":159,"s":67.95,"lo":77,"hi":250,"n":18,"rr":367,"mr":157},{"m":"qwen3-coder-plus","r":160,"s":67.86,"lo":128,"hi":279,"n":3,"rr":486,"mr":161},{"m":"qwen3-coder-480b-a35b-instruct","r":161,"s":67.84,"lo":84,"hi":200,"n":21,"rr":187,"mr":159},{"m":"k2-horizon-7b","r":162,"s":67.59,"lo":119,"hi":202,"n":4,"rr":448,"mr":167},{"m":"o4-mini-high","r":163,"s":67.45,"lo":62,"hi":242,"n":5,"rr":253,"mr":172},{"m":"deepseek-v3.2-exp","r":164,"s":67.44,"lo":128,"hi":426,"n":15,"rr":371,"mr":158},{"m":"claude-3.7-sonnet","r":165,"s":67.32,"lo":79,"hi":208,"n":7,"rr":527,"mr":171},{"m":"keye-vl-2.0-30b-a3b","r":166,"s":67.26,"lo":10,"hi":224,"n":3,"rr":167,"mr":174},{"m":"gemini-3.1-flash-lite","r":167,"s":67.15,"lo":151,"hi":291,"n":4,"rr":435,"mr":162},{"m":"claude-3.7-sonnet-20250219","r":168,"s":67.14,"lo":87,"hi":267,"n":3,"rr":473,"mr":181},{"m":"iquest-coder-v1-40b-loop-instruct","r":169,"s":67.12,"lo":90,"hi":218,"n":15,"rr":134,"mr":163},{"m":"kimi-k2-instruct-0711","r":170,"s":67,"lo":125,"hi":248,"n":6,"rr":446,"mr":173},{"m":"glm-4.5","r":171,"s":66.86,"lo":117,"hi":218,"n":12,"rr":432,"mr":165},{"m":"o1-2024-12-17-high","r":172,"s":66.72,"lo":87,"hi":249,"n":3,"rr":360,"mr":182},{"m":"qwen3-next-80b-a3b-thinking","r":173,"s":66.52,"lo":136,"hi":191,"n":5,"rr":165,"mr":166},{"m":"deepseek-v3.1-thinking","r":174,"s":66.5,"lo":119,"hi":189,"n":8,"rr":604,"mr":170},{"m":"glm-4.7","r":175,"s":66.33,"lo":106,"hi":293,"n":15,"rr":138,"mr":175},{"m":"kimi-k2-0905","r":176,"s":66.06,"lo":102,"hi":238,"n":11,"rr":437,"mr":177},{"m":"longcat-flash-lite","r":177,"s":65.94,"lo":100,"hi":265,"n":3,"rr":593,"mr":184},{"m":"kimi-k2","r":178,"s":65.91,"lo":83,"hi":306,"n":4,"rr":492,"mr":185},{"m":"kimi-k2-instruct-0905","r":179,"s":65.81,"lo":96,"hi":223,"n":19,"rr":159,"mr":169},{"m":"nova-2-lite","r":180,"s":65.67,"lo":98,"hi":214,"n":3,"rr":440,"mr":188},{"m":"mistral-small-4-thinking","r":181,"s":65.64,"lo":146,"hi":201,"n":3,"rr":43,"mr":178},{"m":"kimi-k2-instruct","r":182,"s":65.48,"lo":105,"hi":193,"n":11,"rr":572,"mr":179},{"m":"grok-4.1-fast","r":183,"s":65.41,"lo":128,"hi":209,"n":4,"rr":476,"mr":183},{"m":"k-exaone","r":184,"s":65.24,"lo":131,"hi":251,"n":4,"rr":510,"mr":176},{"m":"grok-code-fast-1","r":185,"s":65.23,"lo":115,"hi":232,"n":3,"rr":246,"mr":187},{"m":"granite-4.2-30b","r":186,"s":64.96,"lo":152,"hi":369,"n":5,"rr":501,"mr":164},{"m":"o1-2024-12-17","r":187,"s":64.65,"lo":108,"hi":256,"n":4,"rr":354,"mr":198},{"m":"o3-mini-2025-01-31-high","r":188,"s":64.37,"lo":82,"hi":244,"n":3,"rr":324,"mr":193},{"m":"gemma-4-26b-a4b","r":189,"s":64.32,"lo":122,"hi":586,"n":5,"rr":274,"mr":186},{"m":"nemotron-cascade-14b-thinking","r":190,"s":64.31,"lo":70,"hi":268,"n":4,"rr":176,"mr":194},{"m":"claude-sonnet-4-20250514","r":191,"s":64.18,"lo":103,"hi":594,"n":3,"rr":612,"mr":207},{"m":"qwen3-max","r":192,"s":64.07,"lo":137,"hi":245,"n":3,"rr":540,"mr":204},{"m":"o1","r":193,"s":63.87,"lo":98,"hi":305,"n":3,"rr":192,"mr":206},{"m":"iquest-coder-v1-14b-thinking","r":194,"s":63.59,"lo":107,"hi":257,"n":5,"rr":350,"mr":191},{"m":"grok-3-beta-think","r":195,"s":63.58,"lo":114,"hi":216,"n":3,"rr":188,"mr":201},{"m":"gpt-oss-120b-high","r":196,"s":63.54,"lo":62,"hi":240,"n":5,"rr":469,"mr":199},{"m":"ministral-3-r-8b","r":197,"s":63.49,"lo":88,"hi":249,"n":4,"rr":18,"mr":200},{"m":"qwen3-30b-a3b-2507","r":198,"s":63.43,"lo":133,"hi":260,"n":6,"rr":282,"mr":190},{"m":"devstral-small-2","r":199,"s":63.41,"lo":141,"hi":369,"n":6,"rr":596,"mr":180},{"m":"gpt-4.1","r":200,"s":63.23,"lo":102,"hi":224,"n":15,"rr":390,"mr":192},{"m":"qwen-3-235b-a22b-thinking","r":201,"s":63.09,"lo":136,"hi":243,"n":7,"rr":59,"mr":197},{"m":"gpt-oss-120b","r":202,"s":63.06,"lo":105,"hi":231,"n":15,"rr":500,"mr":196},{"m":"quasar-alpha","r":203,"s":62.91,"lo":121,"hi":277,"n":3,"rr":520,"mr":221},{"m":"mellum2.1-12b-a2.5b-thinking","r":204,"s":62.89,"lo":121,"hi":249,"n":4,"rr":42,"mr":189},{"m":"o3-mini","r":205,"s":62.8,"lo":131,"hi":251,"n":4,"rr":204,"mr":212},{"m":"minimax-m1-80k","r":206,"s":62.37,"lo":184,"hi":262,"n":3,"rr":221,"mr":210},{"m":"nemotron-cascade-2-30b-a3b","r":207,"s":62.35,"lo":62,"hi":300,"n":3,"rr":518,"mr":209},{"m":"ornith-1.5-9b","r":208,"s":62.34,"lo":130,"hi":309,"n":4,"rr":151,"mr":202},{"m":"qwen3-max-instruct-preview","r":209,"s":62.26,"lo":133,"hi":247,"n":3,"rr":223,"mr":227},{"m":"nemotron-3-nano-30b-a3b","r":210,"s":62.05,"lo":115,"hi":243,"n":6,"rr":80,"mr":211},{"m":"deepseek-r1","r":211,"s":61.96,"lo":114,"hi":242,"n":12,"rr":535,"mr":213},{"m":"gemini-2.5-flash","r":212,"s":61.87,"lo":127,"hi":217,"n":15,"rr":541,"mr":216},{"m":"minicpm5-2b","r":213,"s":61.67,"lo":153,"hi":254,"n":3,"rr":502,"mr":215},{"m":"gemini-2.5-flash-thinking","r":214,"s":61.61,"lo":143,"hi":225,"n":8,"rr":431,"mr":220},{"m":"nemotron-cascade-8b-thinking","r":215,"s":61.43,"lo":92,"hi":291,"n":4,"rr":228,"mr":228},{"m":"o1-preview-2024-09-12","r":216,"s":61.28,"lo":131,"hi":303,"n":8,"rr":28,"mr":214},{"m":"gpt-oss-20b","r":217,"s":61.26,"lo":148,"hi":328,"n":13,"rr":377,"mr":195},{"m":"minimax-m1-40k","r":218,"s":61.2,"lo":188,"hi":265,"n":3,"rr":254,"mr":222},{"m":"telechat3-36b-thinking","r":219,"s":61.02,"lo":198,"hi":266,"n":3,"rr":232,"mr":226},{"m":"k2-think","r":220,"s":60.92,"lo":143,"hi":276,"n":3,"rr":626,"mr":230},{"m":"qwen3-235b-a22b-instruct-2507","r":221,"s":60.88,"lo":132,"hi":250,"n":19,"rr":341,"mr":208},{"m":"seed-thinking-v1.5","r":222,"s":60.79,"lo":138,"hi":247,"n":4,"rr":241,"mr":225},{"m":"qwen3-235b-a22b","r":223,"s":60.7,"lo":112,"hi":303,"n":18,"rr":456,"mr":217},{"m":"olmo-3-think-32b-dpo","r":224,"s":60.5,"lo":140,"hi":263,"n":6,"rr":7,"mr":224},{"m":"nemotron-cascade-8b","r":225,"s":60.46,"lo":101,"hi":304,"n":4,"rr":256,"mr":235},{"m":"nvidia-nemotron-nano-9b-v2","r":226,"s":60.43,"lo":150,"hi":285,"n":6,"rr":51,"mr":229},{"m":"intern-s1-pro","r":227,"s":60.3,"lo":143,"hi":300,"n":3,"rr":451,"mr":232},{"m":"o1-preview","r":228,"s":60.22,"lo":138,"hi":275,"n":11,"rr":32,"mr":219},{"m":"gemma-4-12b-it","r":229,"s":60.2,"lo":139,"hi":258,"n":8,"rr":517,"mr":203},{"m":"glm-4.5-air","r":230,"s":59.93,"lo":171,"hi":288,"n":11,"rr":356,"mr":223},{"m":"gpt-5-minimal","r":231,"s":59.84,"lo":148,"hi":298,"n":3,"rr":262,"mr":238},{"m":"o3-mini-2025-01-31-med","r":232,"s":59.68,"lo":135,"hi":256,"n":3,"rr":395,"mr":239},{"m":"olmo-3.1-think-32b","r":233,"s":59.46,"lo":162,"hi":321,"n":6,"rr":23,"mr":234},{"m":"o1-mini","r":234,"s":59.27,"lo":101,"hi":271,"n":11,"rr":31,"mr":231},{"m":"k2-horizon-3.7b","r":235,"s":59.23,"lo":160,"hi":287,"n":4,"rr":563,"mr":237},{"m":"qwen3.5-9b","r":236,"s":59.21,"lo":188,"hi":287,"n":15,"rr":336,"mr":205},{"m":"nemotron-nano-v2-9b","r":237,"s":59.21,"lo":121,"hi":272,"n":4,"rr":21,"mr":236},{"m":"granite-4.2-8b","r":238,"s":59.09,"lo":145,"hi":332,"n":6,"rr":475,"mr":218},{"m":"falcon-h1r-7b","r":239,"s":58.93,"lo":148,"hi":314,"n":6,"rr":307,"mr":241},{"m":"claude-3.5-sonnet-20241022","r":240,"s":58.86,"lo":144,"hi":294,"n":15,"rr":267,"mr":233},{"m":"ling-2.6-flash","r":241,"s":58.69,"lo":178,"hi":460,"n":3,"rr":439,"mr":240},{"m":"gka-primed-hqwen3-32b-reasoner","r":242,"s":58.62,"lo":123,"hi":537,"n":3,"rr":495,"mr":258},{"m":"qwen3-vl-32b-thinking","r":243,"s":58.58,"lo":150,"hi":340,"n":3,"rr":16,"mr":250},{"m":"nemotron-32b","r":244,"s":58.55,"lo":153,"hi":293,"n":3,"rr":650,"mr":246},{"m":"deepseek-v3-0324","r":245,"s":58.49,"lo":125,"hi":281,"n":11,"rr":576,"mr":242},{"m":"joyai-llm-flash","r":246,"s":58.48,"lo":172,"hi":379,"n":5,"rr":491,"mr":247},{"m":"qwen3-32b-thinking","r":247,"s":57.98,"lo":119,"hi":362,"n":14,"rr":404,"mr":244},{"m":"glm-4.7-flash","r":248,"s":57.57,"lo":182,"hi":317,"n":7,"rr":294,"mr":245},{"m":"openthinkeragent-32b","r":249,"s":57.47,"lo":191,"hi":283,"n":3,"rr":635,"mr":249},{"m":"qwen3-next-80b-a3b-instruct","r":250,"s":57.22,"lo":140,"hi":286,"n":7,"rr":489,"mr":251},{"m":"qwen3-30b-a3b-thinking-2507","r":251,"s":57.05,"lo":168,"hi":322,"n":11,"rr":332,"mr":243},{"m":"openreasoning-nemotron-7b","r":252,"s":56.63,"lo":176,"hi":342,"n":6,"rr":352,"mr":252},{"m":"gpt-4.1-2025-04-14","r":253,"s":56.59,"lo":171,"hi":546,"n":5,"rr":640,"mr":273},{"m":"olmo-3-think-32b-sft","r":254,"s":56.49,"lo":191,"hi":307,"n":6,"rr":15,"mr":253},{"m":"telechat3-105b-a4.7b-thinking","r":255,"s":56.46,"lo":222,"hi":310,"n":3,"rr":337,"mr":254},{"m":"gemini-2.5-flash-preview-09-2025","r":256,"s":56.17,"lo":172,"hi":380,"n":5,"rr":557,"mr":255},{"m":"gemini-exp-1206","r":257,"s":55.79,"lo":181,"hi":289,"n":3,"rr":591,"mr":268},{"m":"o3-mini-2025-01-31-low","r":258,"s":55.71,"lo":163,"hi":285,"n":3,"rr":462,"mr":263},{"m":"deepseek-r1-distill-qwen-32b","r":259,"s":55.69,"lo":171,"hi":313,"n":5,"rr":212,"mr":266},{"m":"hypernova-60b-2605","r":260,"s":55.6,"lo":164,"hi":291,"n":4,"rr":624,"mr":264},{"m":"qwen3.8-27b-iq2-xxs","r":261,"s":55.38,"lo":167,"hi":289,"n":4,"rr":50,"mr":262},{"m":"qwq-32b","r":262,"s":55.29,"lo":189,"hi":318,"n":6,"rr":594,"mr":260},{"m":"apriel-1.6-15b-thinker","r":263,"s":55.12,"lo":126,"hi":377,"n":5,"rr":514,"mr":267},{"m":"o1-mini-2024-09-12","r":264,"s":55.1,"lo":175,"hi":313,"n":9,"rr":92,"mr":259},{"m":"spark-x2.5-4b","r":265,"s":55.04,"lo":181,"hi":296,"n":5,"rr":388,"mr":248},{"m":"gemini-2.5-flash-lite","r":266,"s":55.01,"lo":164,"hi":412,"n":3,"rr":678,"mr":278},{"m":"motif-2-12.7b-reasoning","r":267,"s":54.95,"lo":181,"hi":326,"n":4,"rr":27,"mr":271},{"m":"granite-4.2-3b","r":268,"s":54.92,"lo":210,"hi":327,"n":4,"rr":628,"mr":256},{"m":"sarvam-30b","r":269,"s":54.85,"lo":189,"hi":321,"n":4,"rr":75,"mr":261},{"m":"mellum2-12b-a2.5b-thinking","r":270,"s":54.67,"lo":179,"hi":666,"n":5,"rr":263,"mr":265},{"m":"minicpm-sala","r":271,"s":54.49,"lo":176,"hi":308,"n":4,"rr":53,"mr":270},{"m":"ling-1t","r":272,"s":54.17,"lo":196,"hi":347,"n":6,"rr":338,"mr":276},{"m":"ernie-4.5","r":273,"s":54.17,"lo":149,"hi":367,"n":4,"rr":104,"mr":284},{"m":"deepseek-v3","r":274,"s":54.11,"lo":171,"hi":308,"n":16,"rr":189,"mr":257},{"m":"motif-2-12.7b-instruct","r":275,"s":54,"lo":218,"hi":382,"n":4,"rr":39,"mr":272},{"m":"command-a-plus-05-2026","r":276,"s":53.73,"lo":80,"hi":504,"n":4,"rr":553,"mr":283},{"m":"ax-k1","r":277,"s":53.7,"lo":168,"hi":387,"n":4,"rr":160,"mr":281},{"m":"nemotron-3.5-lightning-30b-a3b","r":278,"s":52.62,"lo":215,"hi":581,"n":5,"rr":464,"mr":269},{"m":"qwen3-14b-thinking","r":279,"s":52.32,"lo":252,"hi":383,"n":4,"rr":427,"mr":290},{"m":"gka-primed-hqwen3-8b-reasoner","r":280,"s":52.31,"lo":175,"hi":642,"n":3,"rr":574,"mr":306},{"m":"qwen3-vl-8b-thinking","r":281,"s":52.29,"lo":170,"hi":358,"n":4,"rr":68,"mr":286},{"m":"olmo-3-think-32b","r":282,"s":52.19,"lo":188,"hi":610,"n":6,"rr":155,"mr":285},{"m":"agents-a1-4b","r":283,"s":52.13,"lo":236,"hi":320,"n":3,"rr":277,"mr":279},{"m":"qwen3-32b","r":284,"s":52.08,"lo":171,"hi":376,"n":20,"rr":458,"mr":277},{"m":"rnj-1.5","r":285,"s":51.87,"lo":233,"hi":305,"n":5,"rr":207,"mr":282},{"m":"mimo-7b-rl","r":286,"s":51.81,"lo":197,"hi":325,"n":3,"rr":579,"mr":292},{"m":"qwen3-coder-30b-a3b-instruct","r":287,"s":51.73,"lo":191,"hi":322,"n":17,"rr":419,"mr":275},{"m":"qwen3-32b-nothinking","r":288,"s":51.68,"lo":180,"hi":457,"n":5,"rr":397,"mr":304},{"m":"llada2.0-flash","r":289,"s":51.67,"lo":197,"hi":310,"n":9,"rr":47,"mr":280},{"m":"o3-mini-high","r":290,"s":51.67,"lo":159,"hi":336,"n":7,"rr":548,"mr":296},{"m":"qwen3-4b-2507","r":291,"s":51.56,"lo":256,"hi":432,"n":3,"rr":550,"mr":295},{"m":"gpt-4.1-mini","r":292,"s":51.53,"lo":189,"hi":334,"n":4,"rr":504,"mr":291},{"m":"apriel-1.5-15b-thinker","r":293,"s":51.34,"lo":192,"hi":422,"n":6,"rr":654,"mr":293},{"m":"olmo-3-think-7b","r":294,"s":51.23,"lo":213,"hi":333,"n":5,"rr":273,"mr":289},{"m":"gdn-primed-hqwen3-8b-reasoner","r":295,"s":51.06,"lo":186,"hi":711,"n":3,"rr":607,"mr":316},{"m":"phi-4-reasoning-plus","r":296,"s":51.05,"lo":225,"hi":359,"n":4,"rr":702,"mr":294},{"m":"k2-high-70b","r":297,"s":51,"lo":240,"hi":343,"n":3,"rr":13,"mr":298},{"m":"gpt-5-nano","r":298,"s":50.95,"lo":215,"hi":328,"n":4,"rr":664,"mr":309},{"m":"minicpm4.1-8b","r":299,"s":50.8,"lo":201,"hi":318,"n":4,"rr":65,"mr":288},{"m":"deepcoder-14b-preview","r":300,"s":50.54,"lo":199,"hi":410,"n":3,"rr":600,"mr":320},{"m":"seed1.6","r":301,"s":50.53,"lo":213,"hi":377,"n":3,"rr":310,"mr":312},{"m":"ministral-3-14b-reasoning","r":302,"s":50.41,"lo":236,"hi":459,"n":3,"rr":562,"mr":313},{"m":"grok-3-beta","r":303,"s":50.22,"lo":197,"hi":362,"n":7,"rr":276,"mr":287},{"m":"llada2.1-flash-q","r":304,"s":50.02,"lo":183,"hi":340,"n":7,"rr":105,"mr":300},{"m":"qwen3.5-4b","r":305,"s":49.9,"lo":230,"hi":354,"n":13,"rr":443,"mr":274},{"m":"olmo-3-think-7b-dpo","r":306,"s":49.88,"lo":188,"hi":349,"n":4,"rr":115,"mr":310},{"m":"kimi-linear-instruct","r":307,"s":49.78,"lo":208,"hi":385,"n":7,"rr":595,"mr":303},{"m":"nvidia-nemotron-3-nano-30b-a3b-bf16","r":308,"s":49.28,"lo":178,"hi":402,"n":6,"rr":627,"mr":299},{"m":"hypernova-60b-2602","r":309,"s":48.98,"lo":230,"hi":329,"n":4,"rr":685,"mr":315},{"m":"qwen3-vl-32b-instruct","r":310,"s":48.86,"lo":226,"hi":361,"n":3,"rr":30,"mr":318},{"m":"llama-3.1-405b","r":311,"s":48.8,"lo":76,"hi":447,"n":5,"rr":117,"mr":352},{"m":"deepseek-r1-distill-llama-70b","r":312,"s":48.73,"lo":217,"hi":417,"n":3,"rr":613,"mr":328},{"m":"qwen3-30b-a3b","r":313,"s":48.64,"lo":236,"hi":421,"n":15,"rr":321,"mr":297},{"m":"llada2.1-flash-s","r":314,"s":48.49,"lo":189,"hi":349,"n":7,"rr":125,"mr":311},{"m":"kat-dev-32b","r":315,"s":48.18,"lo":217,"hi":372,"n":15,"rr":403,"mr":305},{"m":"gpt-4o-2024-08-06","r":316,"s":47.75,"lo":204,"hi":346,"n":15,"rr":235,"mr":308},{"m":"mistral-large-instruct-2407","r":317,"s":47.44,"lo":209,"hi":367,"n":6,"rr":141,"mr":317},{"m":"claude-3.5-sonnet-20240620","r":318,"s":47.33,"lo":232,"hi":340,"n":14,"rr":99,"mr":301},{"m":"qwen3-8b-thinking","r":319,"s":47.32,"lo":228,"hi":396,"n":9,"rr":410,"mr":319},{"m":"instella-moe-16b-a3b-think","r":320,"s":47.25,"lo":248,"hi":388,"n":3,"rr":133,"mr":321},{"m":"iquest-coder-v1-14b-instruct","r":321,"s":46.96,"lo":160,"hi":375,"n":5,"rr":529,"mr":325},{"m":"qwen3-4b","r":322,"s":46.86,"lo":200,"hi":406,"n":9,"rr":150,"mr":314},{"m":"gemma-4-e4b-it","r":323,"s":46.83,"lo":247,"hi":375,"n":10,"rr":485,"mr":302},{"m":"qwen3-30b-a3b-instruct-2507","r":324,"s":46.82,"lo":211,"hi":334,"n":13,"rr":297,"mr":307},{"m":"qwen3-4b-thinking-2507","r":325,"s":46.49,"lo":241,"hi":382,"n":4,"rr":647,"mr":333},{"m":"mistral-medium-3","r":326,"s":46.32,"lo":245,"hi":419,"n":5,"rr":441,"mr":326},{"m":"openthinker3-7b","r":327,"s":45.82,"lo":248,"hi":406,"n":3,"rr":72,"mr":340},{"m":"claude-3.5-haiku-20241022","r":328,"s":45.77,"lo":232,"hi":510,"n":5,"rr":684,"mr":334},{"m":"instella-moe-16b-a3b-dpo","r":329,"s":45.64,"lo":275,"hi":389,"n":3,"rr":145,"mr":329},{"m":"amazon-nova-premier","r":330,"s":45.63,"lo":252,"hi":413,"n":3,"rr":694,"mr":357},{"m":"nemotron-h-47b-reasoning","r":331,"s":45.58,"lo":287,"hi":401,"n":3,"rr":706,"mr":337},{"m":"gpt-4o-2024-05-13","r":332,"s":45.58,"lo":243,"hi":353,"n":13,"rr":379,"mr":327},{"m":"gpt-4o-2024-11-20","r":333,"s":45.37,"lo":229,"hi":361,"n":6,"rr":621,"mr":343},{"m":"qwen2.5-coder-32b-instruct","r":334,"s":45.33,"lo":238,"hi":362,"n":18,"rr":383,"mr":322},{"m":"kimi-dev-72b","r":335,"s":45.03,"lo":239,"hi":391,"n":15,"rr":447,"mr":324},{"m":"ling-flash-2.0","r":336,"s":44.75,"lo":257,"hi":370,"n":9,"rr":76,"mr":323},{"m":"olmo-3-think-7b-sft","r":337,"s":44.55,"lo":240,"hi":378,"n":4,"rr":177,"mr":344},{"m":"ling-2.6-1t-base","r":338,"s":44.53,"lo":241,"hi":347,"n":3,"rr":112,"mr":341},{"m":"gpt-4o","r":339,"s":44.16,"lo":249,"hi":360,"n":15,"rr":566,"mr":338},{"m":"olmo-hybrid-think-7b-sft","r":340,"s":44,"lo":267,"hi":403,"n":3,"rr":78,"mr":351},{"m":"k2-medium-70b","r":341,"s":43.88,"lo":289,"hi":470,"n":3,"rr":63,"mr":349},{"m":"qwen2.5-plus-1127","r":342,"s":43.85,"lo":278,"hi":359,"n":4,"rr":38,"mr":339},{"m":"nemotron-3-nano-4b","r":343,"s":43.79,"lo":278,"hi":641,"n":4,"rr":668,"mr":354},{"m":"instella-moe-16b-a3b-sft","r":344,"s":43.75,"lo":269,"hi":394,"n":3,"rr":173,"mr":345},{"m":"gemini-2.0-flash-exp","r":345,"s":43.66,"lo":255,"hi":396,"n":4,"rr":665,"mr":355},{"m":"solar-open-100b","r":346,"s":43.62,"lo":163,"hi":521,"n":3,"rr":564,"mr":365},{"m":"deepseek-coder-v2-instruct","r":347,"s":43.61,"lo":261,"hi":358,"n":14,"rr":269,"mr":332},{"m":"deepseek-v2.5","r":348,"s":43.6,"lo":256,"hi":351,"n":11,"rr":252,"mr":331},{"m":"gpt-4-turbo-2024-04-09","r":349,"s":43.57,"lo":273,"hi":362,"n":14,"rr":198,"mr":330},{"m":"youtu-llm-2b","r":350,"s":43.41,"lo":220,"hi":389,"n":7,"rr":169,"mr":347},{"m":"kimi-k2-base","r":351,"s":43.21,"lo":242,"hi":387,"n":12,"rr":129,"mr":342},{"m":"qwen2.5-72b-instruct","r":352,"s":43.03,"lo":270,"hi":399,"n":16,"rr":353,"mr":335},{"m":"claude-3.5-sonnet","r":353,"s":42.95,"lo":168,"hi":379,"n":7,"rr":26,"mr":348},{"m":"gpt-4-turbo","r":354,"s":42.32,"lo":292,"hi":383,"n":5,"rr":79,"mr":350},{"m":"qwen3-8b","r":355,"s":42.25,"lo":255,"hi":407,"n":17,"rr":536,"mr":336},{"m":"deepseek-r1-0528-qwen3-8b","r":356,"s":41.87,"lo":296,"hi":487,"n":3,"rr":699,"mr":368},{"m":"exaone-4.0-1.2b","r":357,"s":41.83,"lo":294,"hi":467,"n":3,"rr":530,"mr":370},{"m":"llama-4-maverick","r":358,"s":41.65,"lo":253,"hi":397,"n":8,"rr":608,"mr":360},{"m":"qwen3-4b-instruct-2507","r":359,"s":41.61,"lo":282,"hi":375,"n":5,"rr":460,"mr":361},{"m":"tri-21b-think","r":360,"s":41.53,"lo":294,"hi":416,"n":4,"rr":257,"mr":359},{"m":"gpt-4o-mini","r":361,"s":41.2,"lo":289,"hi":369,"n":5,"rr":45,"mr":362},{"m":"llama-3.1-405b-instruct","r":362,"s":41.16,"lo":243,"hi":397,"n":9,"rr":365,"mr":356},{"m":"spark-x2.5-1.7b","r":363,"s":41.07,"lo":309,"hi":489,"n":3,"rr":714,"mr":346},{"m":"rnj-1","r":364,"s":40.97,"lo":266,"hi":385,"n":5,"rr":293,"mr":366},{"m":"gpt-4-1106-preview","r":365,"s":40.77,"lo":293,"hi":377,"n":10,"rr":122,"mr":353},{"m":"mimo-v2.5-pro-base","r":366,"s":40.33,"lo":211,"hi":408,"n":4,"rr":369,"mr":367},{"m":"ling-1t-base","r":367,"s":40.22,"lo":288,"hi":377,"n":3,"rr":170,"mr":371},{"m":"qwq-32b-preview","r":368,"s":40.2,"lo":283,"hi":426,"n":5,"rr":560,"mr":372},{"m":"qwen2.5-32b-instruct","r":369,"s":40.19,"lo":311,"hi":411,"n":10,"rr":205,"mr":358},{"m":"deepseek-coder-v2-instruct-0724","r":370,"s":40,"lo":273,"hi":391,"n":5,"rr":494,"mr":369},{"m":"kat-dev-72b-exp","r":371,"s":39.93,"lo":291,"hi":411,"n":14,"rr":442,"mr":363},{"m":"alodlm-8b","r":372,"s":39.69,"lo":296,"hi":374,"n":4,"rr":12,"mr":373},{"m":"deepseek-v2-chat-0628","r":373,"s":39.64,"lo":268,"hi":406,"n":5,"rr":399,"mr":376},{"m":"ling-3.0-flash-base","r":374,"s":39.05,"lo":312,"hi":379,"n":5,"rr":317,"mr":377},{"m":"qwen2.5-coder-14b-instruct","r":375,"s":39,"lo":284,"hi":488,"n":15,"rr":426,"mr":364},{"m":"llama-3.1-70b-instruct","r":376,"s":38.91,"lo":245,"hi":532,"n":8,"rr":316,"mr":374},{"m":"qwen3-vl-8b-instruct","r":377,"s":38.81,"lo":302,"hi":398,"n":5,"rr":247,"mr":383},{"m":"granite-4.1-30b","r":378,"s":38.81,"lo":300,"hi":425,"n":8,"rr":98,"mr":380},{"m":"gpt-4","r":379,"s":38.64,"lo":320,"hi":403,"n":5,"rr":10,"mr":379},{"m":"stable-diffcoder-8b-instruct","r":380,"s":38.46,"lo":310,"hi":419,"n":7,"rr":236,"mr":382},{"m":"qwen-turbo-0919","r":381,"s":38.08,"lo":336,"hi":395,"n":4,"rr":94,"mr":381},{"m":"gemini-1.5-pro-002","r":382,"s":37.78,"lo":300,"hi":656,"n":9,"rr":349,"mr":378},{"m":"claude-3-opus-20240229","r":383,"s":37.72,"lo":306,"hi":411,"n":12,"rr":237,"mr":375},{"m":"olmo-3.1-instruct-32b","r":384,"s":37.64,"lo":300,"hi":479,"n":5,"rr":69,"mr":391},{"m":"llama-4-scout-17b","r":385,"s":37.62,"lo":233,"hi":414,"n":4,"rr":511,"mr":395},{"m":"falcon-h1-34b-instruct","r":386,"s":37.54,"lo":318,"hi":705,"n":4,"rr":470,"mr":387},{"m":"qwen2.5-turbo","r":387,"s":37.51,"lo":327,"hi":395,"n":4,"rr":102,"mr":385},{"m":"olmo-3.1-instruct-32b-dpo","r":388,"s":37.29,"lo":300,"hi":444,"n":3,"rr":158,"mr":403},{"m":"qwen3-14b","r":389,"s":37.14,"lo":289,"hi":462,"n":13,"rr":424,"mr":386},{"m":"lfm2.5-2.6b","r":390,"s":37.11,"lo":286,"hi":583,"n":3,"rr":707,"mr":392},{"m":"deepseek-v2.5-1210","r":391,"s":37.07,"lo":270,"hi":419,"n":3,"rr":639,"mr":400},{"m":"deepseek-r1-distill-qwen-7b","r":392,"s":36.86,"lo":318,"hi":628,"n":5,"rr":544,"mr":404},{"m":"iquest-coder-v1-7b-thinking","r":393,"s":36.78,"lo":277,"hi":457,"n":5,"rr":669,"mr":388},{"m":"gpt-4o-mini-2024-07-18","r":394,"s":36.68,"lo":310,"hi":438,"n":14,"rr":304,"mr":384},{"m":"gpt-4-0613","r":395,"s":36.52,"lo":324,"hi":420,"n":4,"rr":428,"mr":418},{"m":"qwen3-4b-thinking","r":396,"s":36.28,"lo":338,"hi":501,"n":3,"rr":677,"mr":422},{"m":"mellum2-12b-a2.5b-instruct","r":397,"s":36.18,"lo":324,"hi":405,"n":4,"rr":244,"mr":398},{"m":"grok-beta","r":398,"s":36.17,"lo":328,"hi":506,"n":7,"rr":168,"mr":389},{"m":"ling-2.6-flash-base","r":399,"s":35.95,"lo":310,"hi":417,"n":3,"rr":233,"mr":399},{"m":"mimo-v2.5-base","r":400,"s":35.91,"lo":260,"hi":436,"n":7,"rr":438,"mr":397},{"m":"k2-horizon-0.9b","r":401,"s":35.89,"lo":350,"hi":405,"n":3,"rr":255,"mr":396},{"m":"granite-4.0-h-small","r":402,"s":35.89,"lo":337,"hi":456,"n":8,"rr":132,"mr":393},{"m":"gemini-1.5-pro","r":403,"s":35.8,"lo":305,"hi":426,"n":10,"rr":197,"mr":390},{"m":"ministral-3-14b-instruct","r":404,"s":35.78,"lo":345,"hi":433,"n":4,"rr":289,"mr":411},{"m":"ling-mini-2.0","r":405,"s":35.51,"lo":338,"hi":427,"n":8,"rr":290,"mr":401},{"m":"hy3-preview-base","r":406,"s":35.38,"lo":337,"hi":428,"n":8,"rr":275,"mr":402},{"m":"ling-2.5-flash-base","r":407,"s":35.24,"lo":330,"hi":419,"n":5,"rr":375,"mr":407},{"m":"llama-3.3-70b-instruct","r":408,"s":35.19,"lo":290,"hi":447,"n":4,"rr":284,"mr":417},{"m":"nemotron-3.5-super-vl-120b-a12b-base","r":409,"s":35.15,"lo":353,"hi":437,"n":3,"rr":113,"mr":406},{"m":"claude-3-opus","r":410,"s":35.12,"lo":332,"hi":431,"n":6,"rr":34,"mr":416},{"m":"granite-3.3-8b-instruct","r":411,"s":35.07,"lo":295,"hi":632,"n":4,"rr":281,"mr":438},{"m":"nemotron-3-super-120b-a12b-base","r":412,"s":35,"lo":357,"hi":428,"n":7,"rr":202,"mr":405},{"m":"granite-4.1-8b","r":413,"s":34.83,"lo":332,"hi":459,"n":8,"rr":147,"mr":413},{"m":"qwen2.5-7b-instruct","r":414,"s":34.59,"lo":260,"hi":484,"n":11,"rr":331,"mr":394},{"m":"qwen3-30b-a3b-base","r":415,"s":34.51,"lo":353,"hi":505,"n":3,"rr":166,"mr":415},{"m":"qwen2-72b-instruct","r":416,"s":34.48,"lo":359,"hi":420,"n":6,"rr":140,"mr":412},{"m":"step-3.5-flash-base","r":417,"s":34.21,"lo":343,"hi":426,"n":10,"rr":214,"mr":410},{"m":"mimo-v2-flash-base","r":418,"s":33.84,"lo":270,"hi":450,"n":11,"rr":219,"mr":414},{"m":"qwen2.5-14b-instruct","r":419,"s":33.38,"lo":365,"hi":500,"n":7,"rr":396,"mr":409},{"m":"llada2.1-mini-q","r":420,"s":33.25,"lo":324,"hi":438,"n":8,"rr":288,"mr":419},{"m":"llada2.0-mini","r":421,"s":33.12,"lo":332,"hi":455,"n":8,"rr":308,"mr":424},{"m":"deepseek-r1-distill-llama-8b","r":422,"s":32.9,"lo":349,"hi":544,"n":7,"rr":463,"mr":408},{"m":"qwen3-8b-non-thinking","r":423,"s":32.75,"lo":345,"hi":444,"n":8,"rr":301,"mr":423},{"m":"gemma-3-27b-it","r":424,"s":32.34,"lo":349,"hi":462,"n":8,"rr":409,"mr":421},{"m":"mistral-small-3.2-24b-instruct","r":425,"s":32.02,"lo":272,"hi":485,"n":3,"rr":171,"mr":437},{"m":"gemini-1.5-flash","r":426,"s":31.99,"lo":359,"hi":443,"n":5,"rr":128,"mr":429},{"m":"seed-coder-8b-instruct","r":427,"s":31.81,"lo":360,"hi":451,"n":18,"rr":484,"mr":420},{"m":"k2-low-70b","r":428,"s":31.62,"lo":393,"hi":522,"n":3,"rr":196,"mr":441},{"m":"llada2.1-mini","r":429,"s":31.58,"lo":263,"hi":452,"n":3,"rr":393,"mr":444},{"m":"gpt-oss-20b-moe","r":430,"s":31.57,"lo":316,"hi":704,"n":5,"rr":449,"mr":469},{"m":"llada2.2-mini","r":431,"s":31.57,"lo":293,"hi":456,"n":3,"rr":408,"mr":431},{"m":"glm-4.5-base","r":432,"s":31.56,"lo":373,"hi":451,"n":7,"rr":121,"mr":428},{"m":"iquest-coder-v1-7b-instruct","r":433,"s":31.35,"lo":261,"hi":489,"n":5,"rr":691,"mr":426},{"m":"lfm2.5-8b-a1b","r":434,"s":31.28,"lo":372,"hi":704,"n":4,"rr":698,"mr":430},{"m":"llama-3.3-70b","r":435,"s":31.19,"lo":339,"hi":492,"n":4,"rr":191,"mr":442},{"m":"llada2.1-mini-s","r":436,"s":31.15,"lo":348,"hi":458,"n":8,"rr":328,"mr":435},{"m":"deepseek-v2-chat","r":437,"s":31.07,"lo":371,"hi":465,"n":8,"rr":361,"mr":436},{"m":"falcon-h1-7b","r":438,"s":31.07,"lo":341,"hi":706,"n":4,"rr":545,"mr":440},{"m":"gemini-1.5-flash-002","r":439,"s":31.02,"lo":374,"hi":538,"n":8,"rr":298,"mr":432},{"m":"qwen3-1.7b","r":440,"s":30.92,"lo":364,"hi":528,"n":9,"rr":347,"mr":425},{"m":"gpt-3.5-turbo-nov-2023","r":441,"s":30.85,"lo":363,"hi":469,"n":3,"rr":49,"mr":449},{"m":"deepseek-v4-flash-base","r":442,"s":30.84,"lo":291,"hi":532,"n":3,"rr":400,"mr":447},{"m":"stable-diffcoder-8b-base","r":443,"s":30.62,"lo":361,"hi":492,"n":4,"rr":60,"mr":451},{"m":"dream-coder-7b-instruct","r":444,"s":30.56,"lo":393,"hi":461,"n":3,"rr":153,"mr":454},{"m":"mellum2-12b-a2.5b-instruct-sft","r":445,"s":30.21,"lo":387,"hi":492,"n":4,"rr":413,"mr":445},{"m":"llama-3-70b-instruct","r":446,"s":30.2,"lo":390,"hi":459,"n":12,"rr":287,"mr":427},{"m":"gemma-4-e2b-it","r":447,"s":30.01,"lo":334,"hi":656,"n":7,"rr":625,"mr":433},{"m":"ling-flash-base-2.0","r":448,"s":30.01,"lo":331,"hi":490,"n":5,"rr":149,"mr":443},{"m":"qwen-2.5-72b","r":449,"s":29.99,"lo":389,"hi":532,"n":8,"rr":216,"mr":434},{"m":"glm-4.5-air-base","r":450,"s":29.87,"lo":180,"hi":505,"n":4,"rr":286,"mr":455},{"m":"skywork-o1-open-llama-3.1-8b","r":451,"s":29.77,"lo":380,"hi":464,"n":5,"rr":163,"mr":439},{"m":"llama-3.1-70b","r":452,"s":29.69,"lo":232,"hi":613,"n":6,"rr":120,"mr":510},{"m":"olmo-3.1-instruct-32b-sft","r":453,"s":29.66,"lo":365,"hi":503,"n":3,"rr":309,"mr":464},{"m":"opencodeinterpreter-ds-33b","r":454,"s":29.49,"lo":400,"hi":459,"n":5,"rr":41,"mr":448},{"m":"mistral-large-3-base","r":455,"s":29.35,"lo":364,"hi":543,"n":3,"rr":258,"mr":458},{"m":"nemotron-3-nano-4b-thinking","r":456,"s":29.22,"lo":325,"hi":680,"n":4,"rr":673,"mr":460},{"m":"ling-3.0-tiny-base","r":457,"s":29.17,"lo":370,"hi":486,"n":5,"rr":481,"mr":452},{"m":"qwen2.5-coder-7b-instruct","r":458,"s":29.13,"lo":353,"hi":522,"n":18,"rr":551,"mr":450},{"m":"wizardcoder-33b-v1.1","r":459,"s":28.91,"lo":411,"hi":463,"n":3,"rr":37,"mr":463},{"m":"yi-coder-9b-chat","r":460,"s":28.66,"lo":389,"hi":509,"n":12,"rr":434,"mr":446},{"m":"claude-3-haiku-mar-2024","r":461,"s":28.59,"lo":386,"hi":489,"n":3,"rr":67,"mr":473},{"m":"gemma-2-27b-it","r":462,"s":28.47,"lo":373,"hi":515,"n":9,"rr":342,"mr":453},{"m":"gpt-3.5-turbo","r":463,"s":28.39,"lo":382,"hi":480,"n":4,"rr":44,"mr":459},{"m":"claude-3-sonnet-mar-2024","r":464,"s":28.26,"lo":349,"hi":527,"n":3,"rr":71,"mr":500},{"m":"ouro-2.6b","r":465,"s":28.06,"lo":405,"hi":476,"n":4,"rr":54,"mr":466},{"m":"minicpm5-1b","r":466,"s":28.02,"lo":423,"hi":523,"n":4,"rr":597,"mr":457},{"m":"gpt-3.5-turbo-1106","r":467,"s":27.93,"lo":406,"hi":482,"n":5,"rr":55,"mr":462},{"m":"wedlm-8b-instruct","r":468,"s":27.92,"lo":413,"hi":482,"n":4,"rr":61,"mr":468},{"m":"llada2.0-flash-preview","r":469,"s":27.74,"lo":417,"hi":481,"n":5,"rr":378,"mr":470},{"m":"falcon-h1-3b","r":470,"s":27.65,"lo":398,"hi":481,"n":3,"rr":394,"mr":478},{"m":"deepseek-coder-33b-instruct","r":471,"s":27.63,"lo":415,"hi":515,"n":15,"rr":516,"mr":456},{"m":"ling-2.5-mini-base","r":472,"s":27.5,"lo":387,"hi":504,"n":5,"rr":506,"mr":471},{"m":"artigenz-coder-ds-6.7b","r":473,"s":27.49,"lo":419,"hi":487,"n":7,"rr":271,"mr":465},{"m":"seed-coder-8b-base","r":474,"s":27.42,"lo":395,"hi":523,"n":4,"rr":97,"mr":485},{"m":"codestral-22b","r":475,"s":27.39,"lo":413,"hi":557,"n":9,"rr":465,"mr":481},{"m":"codestral-22b-v0.1","r":476,"s":27.36,"lo":403,"hi":498,"n":12,"rr":370,"mr":461},{"m":"opencoder-8b-instruct","r":477,"s":27.16,"lo":405,"hi":533,"n":11,"rr":487,"mr":467},{"m":"step-3.5-flash-base-midtrain","r":478,"s":27.01,"lo":384,"hi":529,"n":6,"rr":174,"mr":488},{"m":"codegeex4-all-9b","r":479,"s":26.96,"lo":412,"hi":533,"n":6,"rr":505,"mr":474},{"m":"mistral-small-instruct-2409","r":480,"s":26.88,"lo":406,"hi":511,"n":3,"rr":672,"mr":505},{"m":"magicoder-s-ds-6.7b","r":481,"s":26.83,"lo":419,"hi":523,"n":10,"rr":343,"mr":475},{"m":"qwen2-57b-a14b-instruct","r":482,"s":26.83,"lo":411,"hi":500,"n":5,"rr":226,"mr":484},{"m":"opencodeinterpreter-ds-6.7b","r":483,"s":26.71,"lo":431,"hi":485,"n":7,"rr":291,"mr":479},{"m":"qwen2.5-coder-32b","r":484,"s":26.6,"lo":372,"hi":546,"n":8,"rr":270,"mr":476},{"m":"deepseek-v3-base","r":485,"s":26.5,"lo":412,"hi":529,"n":7,"rr":199,"mr":480},{"m":"speechless-codellama-34b-v2.0","r":486,"s":26.05,"lo":427,"hi":495,"n":5,"rr":85,"mr":489},{"m":"qwen2.5-7b","r":487,"s":25.97,"lo":443,"hi":504,"n":9,"rr":376,"mr":472},{"m":"mixtral-8x22b-instruct-v0.1","r":488,"s":25.93,"lo":437,"hi":495,"n":9,"rr":218,"mr":477},{"m":"granite-4.0-h-tiny","r":489,"s":25.71,"lo":429,"hi":540,"n":10,"rr":420,"mr":486},{"m":"deepseek-coder-7b-instruct-v1.5","r":490,"s":25.57,"lo":434,"hi":499,"n":5,"rr":90,"mr":491},{"m":"falcon-h1-1.5b-deep","r":491,"s":25.55,"lo":419,"hi":516,"n":4,"rr":381,"mr":497},{"m":"granite-4.0-h-micro","r":492,"s":25.52,"lo":432,"hi":548,"n":8,"rr":268,"mr":490},{"m":"deepseek-coder-33b","r":493,"s":25.44,"lo":417,"hi":555,"n":4,"rr":322,"mr":513},{"m":"falcon3-10b","r":494,"s":25.43,"lo":401,"hi":529,"n":3,"rr":430,"mr":507},{"m":"code-millenials-34b","r":495,"s":25.41,"lo":438,"hi":502,"n":5,"rr":84,"mr":492},{"m":"claude-3-sonnet-20240229","r":496,"s":25.4,"lo":402,"hi":532,"n":7,"rr":279,"mr":499},{"m":"xwincoder-34b","r":497,"s":25.39,"lo":438,"hi":502,"n":5,"rr":86,"mr":494},{"m":"smollm3-3b","r":498,"s":25.36,"lo":405,"hi":555,"n":10,"rr":513,"mr":483},{"m":"starchat2-15b-v0.1","r":499,"s":25.27,"lo":438,"hi":503,"n":5,"rr":89,"mr":496},{"m":"granite-4.1-3b","r":500,"s":25.13,"lo":428,"hi":566,"n":8,"rr":295,"mr":501},{"m":"deepseek-coder-v2-base","r":501,"s":24.84,"lo":408,"hi":616,"n":8,"rr":389,"mr":493},{"m":"deepseek-v2-chat-sft","r":502,"s":24.79,"lo":458,"hi":522,"n":5,"rr":313,"mr":509},{"m":"gemma-3-12b-it","r":503,"s":24.71,"lo":400,"hi":641,"n":8,"rr":471,"mr":482},{"m":"whiterabbitneo-33b-v1","r":504,"s":24.71,"lo":437,"hi":522,"n":7,"rr":303,"mr":498},{"m":"claude-3-haiku-20240307","r":505,"s":24.71,"lo":427,"hi":522,"n":9,"rr":455,"mr":495},{"m":"olmo-3-instruct-7b","r":506,"s":24.65,"lo":442,"hi":578,"n":9,"rr":406,"mr":504},{"m":"wavecoder-ultra-6.7b","r":507,"s":24.46,"lo":457,"hi":514,"n":7,"rr":339,"mr":502},{"m":"motif-2-12.7b-base","r":508,"s":24.42,"lo":413,"hi":544,"n":4,"rr":95,"mr":514},{"m":"llama-4-maverick-base","r":509,"s":24.42,"lo":451,"hi":515,"n":3,"rr":387,"mr":523},{"m":"deepseek-coder-v2-lite-instruct","r":510,"s":24.4,"lo":412,"hi":561,"n":17,"rr":598,"mr":487},{"m":"qwen1.5-110b-chat","r":511,"s":24.31,"lo":461,"hi":511,"n":6,"rr":526,"mr":503},{"m":"qwen2.5-coder-14b","r":512,"s":24.09,"lo":406,"hi":559,"n":8,"rr":326,"mr":506},{"m":"qwen3.5-35b-a3b-base","r":513,"s":23.89,"lo":335,"hi":547,"n":4,"rr":334,"mr":518},{"m":"gpt-3.5-turbo-0125","r":514,"s":23.83,"lo":397,"hi":546,"n":5,"rr":552,"mr":528},{"m":"granite-4.0-micro","r":515,"s":23.72,"lo":450,"hi":562,"n":8,"rr":296,"mr":511},{"m":"gemma-3-27b","r":516,"s":23.67,"lo":464,"hi":564,"n":3,"rr":374,"mr":516},{"m":"kimi-linear-base","r":517,"s":23.65,"lo":419,"hi":533,"n":4,"rr":423,"mr":526},{"m":"lfm2-8b-a1b","r":518,"s":23.61,"lo":452,"hi":543,"n":4,"rr":619,"mr":522},{"m":"deepseek-v3.1-base","r":519,"s":23.52,"lo":454,"hi":527,"n":6,"rr":209,"mr":515},{"m":"ouro-1.4b","r":520,"s":23.32,"lo":459,"hi":521,"n":4,"rr":111,"mr":520},{"m":"deepseek-coder-6.7b-instruct","r":521,"s":23.3,"lo":448,"hi":566,"n":15,"rr":555,"mr":508},{"m":"databricks-dbrx-instruct","r":522,"s":23.09,"lo":461,"hi":536,"n":5,"rr":139,"mr":517},{"m":"gpt-3.5-may-2023","r":523,"s":23.08,"lo":466,"hi":527,"n":3,"rr":123,"mr":531},{"m":"qwen2-7b-instruct","r":524,"s":22.83,"lo":466,"hi":552,"n":10,"rr":483,"mr":512},{"m":"deepseek-v3.2-exp-base","r":525,"s":22.77,"lo":459,"hi":534,"n":6,"rr":227,"mr":527},{"m":"qwen-2.5-3b-instruct","r":526,"s":22.72,"lo":455,"hi":535,"n":4,"rr":357,"mr":525},{"m":"speechless-coder-ds-6.7b","r":527,"s":22.72,"lo":470,"hi":532,"n":5,"rr":124,"mr":524},{"m":"wizardcoder-python-34b-v1.0","r":528,"s":22.45,"lo":466,"hi":536,"n":5,"rr":130,"mr":529},{"m":"qwen2.5-coder-3b-instruct","r":529,"s":22.36,"lo":424,"hi":579,"n":10,"rr":467,"mr":519},{"m":"diffucoder-7b-instruct","r":530,"s":22.16,"lo":479,"hi":537,"n":5,"rr":251,"mr":532},{"m":"olmo-hybrid-instruct-7b-dpo","r":531,"s":22.15,"lo":414,"hi":572,"n":3,"rr":459,"mr":536},{"m":"magicoder-s-cl-7b","r":532,"s":22.04,"lo":474,"hi":537,"n":5,"rr":143,"mr":533},{"m":"codestral-mamba","r":533,"s":21.94,"lo":474,"hi":550,"n":4,"rr":499,"mr":541},{"m":"yi-1.5-34b-chat","r":534,"s":21.87,"lo":458,"hi":574,"n":4,"rr":498,"mr":539},{"m":"qwen2.5-coder-7b","r":535,"s":21.65,"lo":461,"hi":559,"n":9,"rr":384,"mr":521},{"m":"minicpm3-4b","r":536,"s":21.64,"lo":484,"hi":546,"n":7,"rr":422,"mr":530},{"m":"alodlm-1.7b","r":537,"s":21.17,"lo":463,"hi":549,"n":4,"rr":154,"mr":535},{"m":"codestral-12b-instruct","r":538,"s":21.16,"lo":410,"hi":619,"n":5,"rr":523,"mr":555},{"m":"openchat-3.5-7b-0106","r":539,"s":21.08,"lo":484,"hi":559,"n":5,"rr":180,"mr":534},{"m":"opencoder-8b-base","r":540,"s":20.86,"lo":440,"hi":580,"n":4,"rr":229,"mr":554},{"m":"phind-codellama-34b-v2","r":541,"s":20.83,"lo":495,"hi":552,"n":7,"rr":452,"mr":538},{"m":"glm-4-9b-chat","r":542,"s":20.64,"lo":468,"hi":572,"n":5,"rr":280,"mr":559},{"m":"olmo-hybrid-instruct-7b-sft","r":543,"s":20.56,"lo":465,"hi":580,"n":3,"rr":512,"mr":547},{"m":"qwen3-8b-base","r":544,"s":20.54,"lo":433,"hi":561,"n":6,"rr":493,"mr":542},{"m":"qwen2-72b","r":545,"s":20.48,"lo":481,"hi":562,"n":6,"rr":193,"mr":543},{"m":"yi-1.5-9b-chat","r":546,"s":20.38,"lo":467,"hi":573,"n":4,"rr":508,"mr":553},{"m":"mistral-large","r":547,"s":20.36,"lo":489,"hi":550,"n":4,"rr":164,"mr":545},{"m":"speechless-starcoder2-15b","r":548,"s":20.25,"lo":499,"hi":552,"n":5,"rr":172,"mr":544},{"m":"olmo-3-instruct-7b-dpo","r":549,"s":20.08,"lo":443,"hi":596,"n":4,"rr":503,"mr":562},{"m":"claude-2","r":550,"s":20.04,"lo":499,"hi":554,"n":3,"rr":200,"mr":556},{"m":"llama-3-70b","r":551,"s":19.99,"lo":455,"hi":663,"n":7,"rr":358,"mr":572},{"m":"codellama-70b-instruct","r":552,"s":19.57,"lo":484,"hi":585,"n":11,"rr":507,"mr":540},{"m":"qwen1.5-72b-chat","r":553,"s":19.57,"lo":511,"hi":566,"n":11,"rr":477,"mr":537},{"m":"falcon-h1-1.5b","r":554,"s":19.56,"lo":503,"hi":559,"n":3,"rr":554,"mr":558},{"m":"moonlight-instruct","r":555,"s":19.33,"lo":473,"hi":580,"n":3,"rr":549,"mr":563},{"m":"falcon3-7b","r":556,"s":19.25,"lo":415,"hi":586,"n":3,"rr":521,"mr":565},{"m":"gemma-2-9b-it","r":557,"s":19.23,"lo":508,"hi":578,"n":10,"rr":569,"mr":548},{"m":"codeqwen1.5-7b-chat","r":558,"s":19.14,"lo":425,"hi":638,"n":13,"rr":546,"mr":550},{"m":"qwen2.5-32b-base","r":559,"s":19.11,"lo":406,"hi":585,"n":5,"rr":195,"mr":560},{"m":"mistral-large-2402","r":560,"s":19.02,"lo":511,"hi":568,"n":7,"rr":436,"mr":557},{"m":"phi-3.5-mini-instruct","r":561,"s":19,"lo":503,"hi":580,"n":9,"rr":561,"mr":546},{"m":"lfm2.5-1.2b-thinking","r":562,"s":18.95,"lo":403,"hi":656,"n":3,"rr":703,"mr":569},{"m":"gemma-3-4b-it","r":563,"s":18.8,"lo":514,"hi":611,"n":6,"rr":565,"mr":551},{"m":"llama-3.1-405b-base","r":564,"s":18.47,"lo":497,"hi":574,"n":5,"rr":414,"mr":568},{"m":"command-r-plus","r":565,"s":18.4,"lo":516,"hi":569,"n":8,"rr":522,"mr":552},{"m":"code-290k-6.7b-instruct","r":566,"s":18.22,"lo":518,"hi":569,"n":3,"rr":266,"mr":574},{"m":"deepseek-llm-67b-chat","r":567,"s":18.22,"lo":513,"hi":589,"n":5,"rr":472,"mr":567},{"m":"qwen1.5-32b-chat","r":568,"s":18.14,"lo":515,"hi":576,"n":7,"rr":559,"mr":566},{"m":"llama-3.1-8b-instruct","r":569,"s":18.08,"lo":498,"hi":612,"n":15,"rr":601,"mr":564},{"m":"starcoder2-15b-instruct-v0.1","r":570,"s":17.92,"lo":508,"hi":582,"n":10,"rr":497,"mr":561},{"m":"gemini-1.0-pro","r":571,"s":17.64,"lo":509,"hi":579,"n":5,"rr":245,"mr":573},{"m":"lfm2-2.6b","r":572,"s":17.56,"lo":526,"hi":585,"n":3,"rr":692,"mr":580},{"m":"internlm2.5-7b-chat","r":573,"s":17.55,"lo":502,"hi":662,"n":4,"rr":582,"mr":585},{"m":"qwen3.5-9b-base","r":574,"s":17.51,"lo":522,"hi":581,"n":5,"rr":630,"mr":571},{"m":"dolphin-2.6-mixtral-8x7b","r":575,"s":17.44,"lo":521,"hi":577,"n":5,"rr":260,"mr":575},{"m":"olmo-3-7b-sft","r":576,"s":17.25,"lo":499,"hi":675,"n":6,"rr":629,"mr":583},{"m":"phi-3-mini-4k-instruct","r":577,"s":17.15,"lo":520,"hi":580,"n":5,"rr":278,"mr":576},{"m":"qwen2.5-14b","r":578,"s":17.09,"lo":512,"hi":589,"n":5,"rr":283,"mr":577},{"m":"llama-3-8b-instruct","r":579,"s":16.71,"lo":534,"hi":586,"n":10,"rr":531,"mr":570},{"m":"qwen3.5-2b","r":580,"s":16.65,"lo":482,"hi":642,"n":10,"rr":690,"mr":549},{"m":"gemma-2-27b","r":581,"s":16.53,"lo":525,"hi":602,"n":6,"rr":468,"mr":579},{"m":"qwen2.5-3b","r":582,"s":16.39,"lo":503,"hi":606,"n":6,"rr":445,"mr":578},{"m":"qwen1.5-110b","r":583,"s":16.29,"lo":530,"hi":595,"n":4,"rr":320,"mr":586},{"m":"llada-moe-7b-a1b-instruct","r":584,"s":16.12,"lo":514,"hi":589,"n":3,"rr":474,"mr":591},{"m":"deepseek-r1-distill-qwen-1.5b","r":585,"s":16.06,"lo":534,"hi":639,"n":6,"rr":606,"mr":581},{"m":"dream-7b-instruct","r":586,"s":15.91,"lo":533,"hi":589,"n":6,"rr":450,"mr":590},{"m":"yi-1.5-6b-chat","r":587,"s":15.77,"lo":521,"hi":641,"n":4,"rr":588,"mr":595},{"m":"qwen2.5-coder-1.5b-instruct","r":588,"s":15.23,"lo":524,"hi":646,"n":10,"rr":587,"mr":587},{"m":"qwen2.57b-a14b","r":589,"s":15.16,"lo":535,"hi":604,"n":8,"rr":509,"mr":584},{"m":"codegemma-7b-it","r":590,"s":15.12,"lo":535,"hi":598,"n":7,"rr":519,"mr":589},{"m":"deepseek-coder-33b-base","r":591,"s":15.07,"lo":538,"hi":614,"n":9,"rr":479,"mr":582},{"m":"qwen3-0.6b","r":592,"s":15.05,"lo":519,"hi":675,"n":4,"rr":726,"mr":603},{"m":"qwen3.5-4b-base","r":593,"s":14.92,"lo":549,"hi":616,"n":6,"rr":634,"mr":588},{"m":"yi-coder-9b","r":594,"s":14.85,"lo":543,"hi":606,"n":3,"rr":329,"mr":605},{"m":"dream-7b-base","r":595,"s":14.85,"lo":537,"hi":598,"n":5,"rr":348,"mr":596},{"m":"gemma-2-2b-it","r":596,"s":14.72,"lo":491,"hi":662,"n":4,"rr":556,"mr":621},{"m":"codellama-70b","r":597,"s":14.63,"lo":548,"hi":617,"n":6,"rr":496,"mr":597},{"m":"deepseek-v2","r":598,"s":14.36,"lo":537,"hi":616,"n":7,"rr":524,"mr":593},{"m":"code-13b","r":599,"s":14.35,"lo":552,"hi":602,"n":3,"rr":416,"mr":606},{"m":"speechless-starcoder2-7b","r":600,"s":14.33,"lo":546,"hi":603,"n":5,"rr":364,"mr":598},{"m":"mixtral-8x22b","r":601,"s":14.2,"lo":543,"hi":619,"n":8,"rr":415,"mr":594},{"m":"qwen2.5-1.5b-instruct","r":602,"s":14.09,"lo":565,"hi":621,"n":8,"rr":660,"mr":592},{"m":"claude-instant-1-mar-2024","r":603,"s":14.04,"lo":552,"hi":606,"n":3,"rr":433,"mr":608},{"m":"gemma-3-12b","r":604,"s":14.04,"lo":516,"hi":631,"n":3,"rr":577,"mr":613},{"m":"moonlight-base","r":605,"s":14.02,"lo":547,"hi":614,"n":6,"rr":589,"mr":600},{"m":"wizardcoder-15b-v1.0","r":606,"s":13.87,"lo":552,"hi":608,"n":5,"rr":385,"mr":602},{"m":"llama-3-70b-base","r":607,"s":13.77,"lo":546,"hi":621,"n":8,"rr":429,"mr":599},{"m":"codeqwen1.5-7b","r":608,"s":13.53,"lo":556,"hi":624,"n":9,"rr":538,"mr":604},{"m":"qwen2.5-coder-3b","r":609,"s":13.49,"lo":551,"hi":623,"n":8,"rr":543,"mr":601},{"m":"chatglm3-6b","r":610,"s":13.47,"lo":551,"hi":636,"n":3,"rr":344,"mr":624},{"m":"speechless-coding-7b-16k-tora","r":611,"s":13.36,"lo":555,"hi":614,"n":5,"rr":407,"mr":609},{"m":"codellama-34b","r":612,"s":13.35,"lo":545,"hi":624,"n":7,"rr":421,"mr":607},{"m":"code-33b","r":613,"s":13.34,"lo":563,"hi":614,"n":3,"rr":461,"mr":615},{"m":"coda-1.7b-instruct","r":614,"s":13.24,"lo":560,"hi":633,"n":5,"rr":418,"mr":612},{"m":"qwen2-7b","r":615,"s":12.99,"lo":565,"hi":622,"n":6,"rr":444,"mr":614},{"m":"mimo-7b-base","r":616,"s":12.9,"lo":521,"hi":643,"n":5,"rr":571,"mr":619},{"m":"codellama-python-34b","r":617,"s":12.77,"lo":563,"hi":627,"n":4,"rr":454,"mr":617},{"m":"qwen2.5-1.5b","r":618,"s":12.48,"lo":579,"hi":628,"n":6,"rr":567,"mr":611},{"m":"starcoder2-15b","r":619,"s":12.44,"lo":563,"hi":640,"n":10,"rr":602,"mr":610},{"m":"fast-dllm-v2-7b","r":620,"s":12.43,"lo":520,"hi":647,"n":5,"rr":480,"mr":616},{"m":"llama-3.1-8b","r":621,"s":12.37,"lo":452,"hi":664,"n":7,"rr":398,"mr":638},{"m":"phi-2-2.7b","r":622,"s":12.06,"lo":568,"hi":627,"n":4,"rr":425,"mr":622},{"m":"olmo-2-0325-32b-instruct","r":623,"s":11.94,"lo":587,"hi":649,"n":3,"rr":658,"mr":634},{"m":"openhermes-2.5-code-290k-13b","r":624,"s":11.74,"lo":574,"hi":641,"n":5,"rr":482,"mr":627},{"m":"deepseek-coder-6.7b-base","r":625,"s":11.71,"lo":575,"hi":641,"n":10,"rr":573,"mr":618},{"m":"yi-1.5-34b","r":626,"s":11.67,"lo":579,"hi":637,"n":6,"rr":488,"mr":625},{"m":"llama-3.2-3b-instruct","r":627,"s":11.58,"lo":574,"hi":699,"n":5,"rr":735,"mr":636},{"m":"phi-3-medium-4k-instruct","r":628,"s":11.42,"lo":549,"hi":663,"n":3,"rr":575,"mr":648},{"m":"qwen1.5-72b","r":629,"s":11.28,"lo":582,"hi":644,"n":8,"rr":537,"mr":623},{"m":"wizardcoder-python-7b-v1.0","r":630,"s":11.27,"lo":577,"hi":634,"n":5,"rr":490,"mr":631},{"m":"mixtral-8x7b-instruct-v0.1","r":631,"s":11.25,"lo":589,"hi":641,"n":6,"rr":590,"mr":628},{"m":"codegemma-7b","r":632,"s":11.16,"lo":585,"hi":644,"n":6,"rr":585,"mr":626},{"m":"codellama-34b-instruct","r":633,"s":11.1,"lo":592,"hi":647,"n":10,"rr":653,"mr":620},{"m":"phi-2","r":634,"s":11.08,"lo":590,"hi":644,"n":7,"rr":525,"mr":630},{"m":"qwen1.5-32b","r":635,"s":11.05,"lo":588,"hi":645,"n":6,"rr":515,"mr":632},{"m":"deepseek-coder-v2-lite-base","r":636,"s":10.98,"lo":563,"hi":658,"n":8,"rr":583,"mr":629},{"m":"deepseek-coder-1.3b-instruct","r":637,"s":10.93,"lo":563,"hi":691,"n":11,"rr":643,"mr":635},{"m":"qwen3-0.8b","r":638,"s":10.79,"lo":595,"hi":650,"n":3,"rr":680,"mr":641},{"m":"mistral-codealpaca-7b","r":639,"s":10.66,"lo":589,"hi":644,"n":3,"rr":570,"mr":646},{"m":"yi-coder-1.5b-chat","r":640,"s":10.63,"lo":548,"hi":690,"n":10,"rr":645,"mr":633},{"m":"llama-3.2-3b-base","r":641,"s":10.61,"lo":557,"hi":717,"n":3,"rr":663,"mr":658},{"m":"qwen2.5-coder-1.5b","r":642,"s":10.46,"lo":587,"hi":654,"n":8,"rr":605,"mr":637},{"m":"codellama-13b","r":643,"s":10.46,"lo":587,"hi":653,"n":7,"rr":534,"mr":640},{"m":"olmo-hybrid-7b","r":644,"s":10.45,"lo":562,"hi":650,"n":5,"rr":610,"mr":642},{"m":"deepseek-llm-67b-base","r":645,"s":10.34,"lo":595,"hi":648,"n":4,"rr":542,"mr":651},{"m":"speechless-code-mistral-7b-v1.0","r":646,"s":10.26,"lo":590,"hi":648,"n":5,"rr":533,"mr":644},{"m":"mistralhermes-codepro-7b-v1","r":647,"s":10.21,"lo":591,"hi":647,"n":5,"rr":539,"mr":645},{"m":"olmo-3-7b","r":648,"s":10.2,"lo":586,"hi":654,"n":7,"rr":603,"mr":639},{"m":"codellama-python-13b","r":649,"s":10.14,"lo":585,"hi":659,"n":4,"rr":547,"mr":653},{"m":"falcon3-3b","r":650,"s":10.09,"lo":537,"hi":709,"n":3,"rr":656,"mr":659},{"m":"llama-3.1-8b-base","r":651,"s":10.02,"lo":565,"hi":687,"n":8,"rr":675,"mr":650},{"m":"apertus-70b-instruct","r":652,"s":9.99,"lo":610,"hi":668,"n":6,"rr":671,"mr":643},{"m":"falcon-h1-0.5b-instruct","r":653,"s":9.89,"lo":576,"hi":673,"n":3,"rr":696,"mr":652},{"m":"mixtral-8x7b","r":654,"s":9.65,"lo":595,"hi":666,"n":8,"rr":580,"mr":647},{"m":"deepseek-v2-lite-chat","r":655,"s":9.63,"lo":567,"hi":674,"n":5,"rr":620,"mr":654},{"m":"gemma-2-9b","r":656,"s":9.48,"lo":613,"hi":662,"n":9,"rr":646,"mr":649},{"m":"yi-1.5-9b","r":657,"s":9.39,"lo":598,"hi":660,"n":4,"rr":532,"mr":656},{"m":"codellama-python-7b","r":658,"s":8.9,"lo":602,"hi":672,"n":4,"rr":584,"mr":661},{"m":"codellama-7b","r":659,"s":8.72,"lo":615,"hi":670,"n":7,"rr":586,"mr":655},{"m":"qwen1.5-7b-chat","r":660,"s":8.62,"lo":615,"hi":678,"n":5,"rr":659,"mr":660},{"m":"gemma-1.1-7b-it","r":661,"s":8.59,"lo":609,"hi":666,"n":5,"rr":581,"mr":662},{"m":"qwen2-1.5b-instruct","r":662,"s":8.48,"lo":600,"hi":683,"n":4,"rr":649,"mr":663},{"m":"llama-3-8b","r":663,"s":8.47,"lo":581,"hi":678,"n":5,"rr":453,"mr":667},{"m":"codellama-13b-instruct","r":664,"s":8.44,"lo":611,"hi":672,"n":10,"rr":676,"mr":657},{"m":"apertus-8b-instruct","r":665,"s":8.23,"lo":629,"hi":695,"n":5,"rr":670,"mr":664},{"m":"yi-coder-1.5b","r":666,"s":8.16,"lo":622,"hi":674,"n":3,"rr":599,"mr":677},{"m":"map-neo-7b-instruct","r":667,"s":8.08,"lo":601,"hi":686,"n":4,"rr":609,"mr":679},{"m":"codet5-16b","r":668,"s":8.05,"lo":554,"hi":687,"n":3,"rr":578,"mr":678},{"m":"olmo-2-1124-7b-instruct","r":669,"s":8.03,"lo":631,"hi":697,"n":3,"rr":709,"mr":681},{"m":"llada-8b-instruct","r":670,"s":8,"lo":611,"hi":685,"n":6,"rr":638,"mr":665},{"m":"starcoderbase-16b","r":671,"s":7.96,"lo":610,"hi":683,"n":4,"rr":611,"mr":676},{"m":"mistral-7b-instruct-v0.2","r":672,"s":7.9,"lo":617,"hi":675,"n":5,"rr":614,"mr":672},{"m":"solar-10.7b-instruct-v1.0","r":673,"s":7.88,"lo":619,"hi":682,"n":5,"rr":617,"mr":673},{"m":"starcoder2-7b","r":674,"s":7.77,"lo":623,"hi":681,"n":9,"rr":648,"mr":666},{"m":"yi-1.5-6b","r":675,"s":7.63,"lo":620,"hi":680,"n":4,"rr":592,"mr":674},{"m":"gemma-7b","r":676,"s":7.56,"lo":629,"hi":685,"n":6,"rr":623,"mr":669},{"m":"xdan-l1-chat-rl-v1-7b","r":677,"s":7.52,"lo":622,"hi":680,"n":5,"rr":618,"mr":675},{"m":"llama-3-8b-base","r":678,"s":7.52,"lo":618,"hi":690,"n":6,"rr":615,"mr":671},{"m":"qwen2.5-coder-0.5b-instruct","r":679,"s":7.33,"lo":583,"hi":721,"n":10,"rr":687,"mr":670},{"m":"qwen1.5-7b","r":680,"s":7.28,"lo":634,"hi":687,"n":6,"rr":637,"mr":680},{"m":"starcoder2-3b","r":681,"s":6.98,"lo":625,"hi":699,"n":9,"rr":657,"mr":683},{"m":"starcoder-15b","r":682,"s":6.92,"lo":630,"hi":691,"n":5,"rr":622,"mr":684},{"m":"codet5-6b","r":683,"s":6.86,"lo":549,"hi":701,"n":3,"rr":616,"mr":693},{"m":"codellama-7b-instruct","r":684,"s":6.81,"lo":635,"hi":706,"n":11,"rr":705,"mr":682},{"m":"python-code-13b","r":685,"s":6.77,"lo":640,"hi":689,"n":3,"rr":681,"mr":691},{"m":"qwen3.5-0.8b-thinking","r":686,"s":6.66,"lo":622,"hi":721,"n":5,"rr":724,"mr":668},{"m":"codegen-16b","r":687,"s":6.59,"lo":633,"hi":695,"n":5,"rr":633,"mr":686},{"m":"map-neo-7b-sft","r":688,"s":6.57,"lo":626,"hi":694,"n":4,"rr":641,"mr":697},{"m":"llama-3.2-3b","r":689,"s":6.5,"lo":637,"hi":696,"n":4,"rr":632,"mr":695},{"m":"codet5plus-16b","r":690,"s":6.48,"lo":631,"hi":701,"n":5,"rr":631,"mr":690},{"m":"qwen2-1.5b","r":691,"s":6.47,"lo":642,"hi":699,"n":5,"rr":651,"mr":696},{"m":"stablecode-3b","r":692,"s":6.46,"lo":641,"hi":704,"n":7,"rr":642,"mr":688},{"m":"qwen2.5-0.5b-instruct","r":693,"s":6.37,"lo":642,"hi":709,"n":6,"rr":718,"mr":687},{"m":"mistral-7b-v0.1","r":694,"s":6.34,"lo":648,"hi":704,"n":6,"rr":652,"mr":689},{"m":"mistral-7b","r":695,"s":6.18,"lo":633,"hi":708,"n":7,"rr":644,"mr":685},{"m":"deepseek-coder-1.3b-base","r":696,"s":6.13,"lo":647,"hi":705,"n":9,"rr":679,"mr":694},{"m":"deepseek-v2-lite","r":697,"s":5.96,"lo":636,"hi":704,"n":4,"rr":662,"mr":703},{"m":"gemma-3-1b-it","r":698,"s":5.84,"lo":659,"hi":720,"n":7,"rr":717,"mr":692},{"m":"codegen-6b","r":699,"s":5.8,"lo":650,"hi":707,"n":5,"rr":655,"mr":698},{"m":"qwen3.5-0.8b","r":700,"s":5.73,"lo":586,"hi":727,"n":3,"rr":688,"mr":700},{"m":"coda-1.7b-base","r":701,"s":5.7,"lo":651,"hi":712,"n":5,"rr":667,"mr":699},{"m":"codet5plus-6b","r":702,"s":5.68,"lo":648,"hi":710,"n":5,"rr":661,"mr":701},{"m":"granite-3.3-8b-base","r":703,"s":5.39,"lo":616,"hi":754,"n":5,"rr":721,"mr":711},{"m":"gemma-7b-it","r":704,"s":5.39,"lo":654,"hi":711,"n":5,"rr":674,"mr":706},{"m":"qwen2.5-coder-0.5b","r":705,"s":5.32,"lo":659,"hi":714,"n":8,"rr":693,"mr":702},{"m":"codegemma-2b","r":706,"s":5.21,"lo":651,"hi":720,"n":5,"rr":666,"mr":705},{"m":"qwen2.5-0.5b","r":707,"s":5.08,"lo":654,"hi":719,"n":6,"rr":700,"mr":704},{"m":"llama-3.2-1b-instruct","r":708,"s":5.05,"lo":668,"hi":729,"n":6,"rr":749,"mr":715},{"m":"starcoderbase-7b","r":709,"s":5.04,"lo":642,"hi":717,"n":5,"rr":697,"mr":708},{"m":"marin-8b-base","r":710,"s":5.03,"lo":649,"hi":715,"n":5,"rr":704,"mr":714},{"m":"zephyr-7b-beta","r":711,"s":5.02,"lo":657,"hi":715,"n":5,"rr":686,"mr":707},{"m":"llama-3.2-1b","r":712,"s":4.92,"lo":636,"hi":722,"n":4,"rr":683,"mr":716},{"m":"codet5-2b","r":713,"s":4.85,"lo":661,"hi":719,"n":5,"rr":682,"mr":709},{"m":"llama-3.2-1.24b-base","r":714,"s":4.81,"lo":606,"hi":732,"n":3,"rr":722,"mr":718},{"m":"codegen-2b","r":715,"s":4.77,"lo":664,"hi":718,"n":5,"rr":689,"mr":712},{"m":"smollm2-1.7b-instruct","r":716,"s":4.7,"lo":636,"hi":742,"n":3,"rr":740,"mr":710},{"m":"olmoe-1b-7b","r":717,"s":4.62,"lo":643,"hi":726,"n":5,"rr":708,"mr":713},{"m":"gemma-2b","r":718,"s":4.4,"lo":667,"hi":722,"n":5,"rr":695,"mr":719},{"m":"qwen2-0.5b-instruct","r":719,"s":4.35,"lo":654,"hi":736,"n":4,"rr":713,"mr":720},{"m":"gemma-3-1b","r":720,"s":4.26,"lo":594,"hi":735,"n":4,"rr":711,"mr":717},{"m":"map-neo-7b","r":721,"s":4.08,"lo":667,"hi":723,"n":4,"rr":701,"mr":722},{"m":"apertus-8b","r":722,"s":4.06,"lo":652,"hi":724,"n":5,"rr":710,"mr":721},{"m":"codegen2-7b","r":723,"s":3.61,"lo":678,"hi":726,"n":3,"rr":727,"mr":723},{"m":"olmo-2-0425-1b-instruct","r":724,"s":3.61,"lo":621,"hi":750,"n":3,"rr":736,"mr":725},{"m":"qwen2-0.5b","r":725,"s":3.54,"lo":676,"hi":735,"n":5,"rr":712,"mr":727},{"m":"codegen2-16b","r":726,"s":3.53,"lo":674,"hi":727,"n":3,"rr":728,"mr":726},{"m":"gemma-1.1-2b-it","r":727,"s":3.4,"lo":671,"hi":730,"n":5,"rr":716,"mr":724},{"m":"starcoderbase-3b","r":728,"s":3.32,"lo":677,"hi":731,"n":3,"rr":731,"mr":728},{"m":"gemma-2b-it","r":729,"s":3.23,"lo":679,"hi":734,"n":3,"rr":733,"mr":731},{"m":"gemma-2-2b","r":730,"s":3.06,"lo":675,"hi":742,"n":6,"rr":719,"mr":729},{"m":"olmo-1.7-7b","r":731,"s":3.05,"lo":677,"hi":734,"n":4,"rr":715,"mr":733},{"m":"vicuna-13b","r":732,"s":2.96,"lo":691,"hi":737,"n":4,"rr":734,"mr":730},{"m":"falcon3-1b","r":733,"s":2.89,"lo":619,"hi":750,"n":3,"rr":742,"mr":736},{"m":"santacoder-1.1b","r":734,"s":2.85,"lo":687,"hi":738,"n":3,"rr":737,"mr":732},{"m":"amberchat","r":735,"s":2.83,"lo":679,"hi":739,"n":4,"rr":720,"mr":738},{"m":"codegen2-3b","r":736,"s":2.77,"lo":683,"hi":741,"n":3,"rr":738,"mr":734},{"m":"incoder-6.7b","r":737,"s":2.69,"lo":685,"hi":742,"n":3,"rr":739,"mr":735},{"m":"starcoderbase-1b","r":738,"s":2.61,"lo":688,"hi":743,"n":3,"rr":741,"mr":737},{"m":"llama-2-7b-chat","r":739,"s":2.59,"lo":685,"hi":741,"n":4,"rr":723,"mr":740},{"m":"llama-2-7b","r":740,"s":2.47,"lo":686,"hi":744,"n":4,"rr":725,"mr":744},{"m":"vicuna-7b","r":741,"s":2.32,"lo":695,"hi":745,"n":3,"rr":745,"mr":741},{"m":"gpt-j-6b","r":742,"s":2.29,"lo":693,"hi":746,"n":3,"rr":746,"mr":742},{"m":"incoder-1.3b","r":743,"s":2.29,"lo":694,"hi":747,"n":3,"rr":747,"mr":743},{"m":"olmo-7b-instruct","r":744,"s":2.27,"lo":686,"hi":747,"n":4,"rr":732,"mr":739},{"m":"amber-7b","r":745,"s":2.23,"lo":690,"hi":747,"n":4,"rr":730,"mr":747},{"m":"gemma-3-270m-it","r":746,"s":2.07,"lo":628,"hi":751,"n":3,"rr":752,"mr":745},{"m":"olmo-7b","r":747,"s":2.07,"lo":692,"hi":749,"n":4,"rr":729,"mr":749},{"m":"olmo-2-1124-7b","r":748,"s":2.01,"lo":685,"hi":751,"n":5,"rr":743,"mr":750},{"m":"codegen2-1b","r":749,"s":1.96,"lo":696,"hi":750,"n":3,"rr":750,"mr":746},{"m":"smollm2-360m-instruct","r":750,"s":1.72,"lo":634,"hi":753,"n":3,"rr":751,"mr":748},{"m":"pythia-6.9b","r":751,"s":1.51,"lo":698,"hi":752,"n":4,"rr":744,"mr":752},{"m":"gpt-neo-2.7b","r":752,"s":1.45,"lo":698,"hi":753,"n":3,"rr":753,"mr":751},{"m":"pythia-12b","r":753,"s":1.39,"lo":699,"hi":754,"n":4,"rr":748,"mr":754},{"m":"polycoder-2.7b","r":754,"s":1.25,"lo":700,"hi":754,"n":3,"rr":754,"mr":753},{"m":"stablelm-7b","r":755,"s":0.53,"lo":691,"hi":755,"n":3,"rr":756,"mr":755},{"m":"zyte-1b","r":756,"s":0.41,"lo":705,"hi":756,"n":5,"rr":755,"mr":756}]},"faix-math":{"name":"Math","n":657,"nb":39,"acc":0.858,"raw_acc":0.7154,"rows":[{"m":"claude-fable-5","r":1,"s":99.16,"lo":1,"hi":214,"n":3,"rr":13,"mr":1},{"m":"gpt-5.6-sol","r":2,"s":98.14,"lo":1,"hi":37,"n":7,"rr":20,"mr":2},{"m":"claude-opus-5","r":3,"s":97.94,"lo":1,"hi":12,"n":4,"rr":76,"mr":3},{"m":"qwen3.8-max","r":4,"s":96.76,"lo":2,"hi":164,"n":3,"rr":151,"mr":6},{"m":"claude-opus-4.8","r":5,"s":96.67,"lo":2,"hi":9,"n":10,"rr":47,"mr":4},{"m":"gpt-5.5","r":6,"s":96.41,"lo":2,"hi":9,"n":14,"rr":34,"mr":5},{"m":"kimi-k3","r":7,"s":95.83,"lo":5,"hi":56,"n":4,"rr":142,"mr":8},{"m":"gpt-5.6-luna","r":8,"s":95.47,"lo":3,"hi":122,"n":5,"rr":77,"mr":12},{"m":"deepseek-v4-flash-0731","r":9,"s":95.33,"lo":7,"hi":18,"n":3,"rr":145,"mr":11},{"m":"gpt-5.2-high","r":10,"s":95.25,"lo":5,"hi":21,"n":8,"rr":57,"mr":7},{"m":"gemini-3.1-pro","r":11,"s":95.19,"lo":6,"hi":16,"n":15,"rr":187,"mr":9},{"m":"gpt-5.4","r":12,"s":94.83,"lo":3,"hi":21,"n":9,"rr":205,"mr":13},{"m":"gpt-5.2-thinking-xhigh","r":13,"s":94.7,"lo":6,"hi":50,"n":6,"rr":14,"mr":10},{"m":"ax-k2","r":14,"s":94.3,"lo":10,"hi":26,"n":3,"rr":184,"mr":15},{"m":"deepseek-v4-pro-thinking-max","r":15,"s":94.11,"lo":10,"hi":26,"n":7,"rr":167,"mr":14},{"m":"seed2.1-pro","r":16,"s":93.99,"lo":6,"hi":30,"n":9,"rr":234,"mr":20},{"m":"gemini-3-flash","r":17,"s":93.94,"lo":9,"hi":51,"n":8,"rr":24,"mr":17},{"m":"qwen3.7-max","r":18,"s":93.92,"lo":12,"hi":35,"n":8,"rr":197,"mr":18},{"m":"gpt-5.2","r":19,"s":93.84,"lo":8,"hi":44,"n":13,"rr":146,"mr":16},{"m":"gpt-5.2-thinking","r":20,"s":93.84,"lo":9,"hi":61,"n":5,"rr":297,"mr":24},{"m":"seed2.1-turbo","r":21,"s":93.82,"lo":13,"hi":32,"n":7,"rr":154,"mr":22},{"m":"deepseek-v4-flash-thinking-max","r":22,"s":93.57,"lo":15,"hi":31,"n":6,"rr":211,"mr":23},{"m":"hy3","r":23,"s":93.49,"lo":17,"hi":107,"n":3,"rr":393,"mr":28},{"m":"claude-opus-4.6","r":24,"s":93.47,"lo":14,"hi":32,"n":11,"rr":236,"mr":26},{"m":"longcat-flash-thinking-2601","r":25,"s":93.43,"lo":11,"hi":44,"n":3,"rr":3,"mr":19},{"m":"deepseek-v4-pro","r":26,"s":93.35,"lo":10,"hi":34,"n":6,"rr":98,"mr":27},{"m":"deepseek-v4-pro-thinking","r":27,"s":92.96,"lo":17,"hi":38,"n":4,"rr":233,"mr":30},{"m":"seed2.0-pro","r":28,"s":92.9,"lo":6,"hi":35,"n":8,"rr":18,"mr":25},{"m":"gemini-3-pro","r":29,"s":92.88,"lo":17,"hi":37,"n":20,"rr":155,"mr":29},{"m":"qwen3.8-27b","r":30,"s":92.88,"lo":11,"hi":92,"n":8,"rr":5,"mr":21},{"m":"ring-1t-2.5-heavy-thinking","r":31,"s":92.42,"lo":6,"hi":78,"n":3,"rr":4,"mr":31},{"m":"kimi-k2.6-thinking","r":32,"s":92.36,"lo":23,"hi":38,"n":7,"rr":157,"mr":32},{"m":"qwen3.7-plus","r":33,"s":92.15,"lo":23,"hi":41,"n":5,"rr":217,"mr":35},{"m":"deepseek-v4-flash","r":34,"s":92.07,"lo":16,"hi":234,"n":5,"rr":239,"mr":34},{"m":"glm-5.2","r":35,"s":91.84,"lo":8,"hi":44,"n":6,"rr":240,"mr":39},{"m":"step-3.5-flash-20260204","r":36,"s":91.76,"lo":22,"hi":46,"n":6,"rr":7,"mr":33},{"m":"kimi-k2.6","r":37,"s":91.58,"lo":30,"hi":53,"n":3,"rr":16,"mr":36},{"m":"ring-2.6-1t-xhigh","r":38,"s":91.53,"lo":30,"hi":52,"n":3,"rr":15,"mr":37},{"m":"claude-opus-4.7","r":39,"s":91.32,"lo":25,"hi":51,"n":10,"rr":237,"mr":40},{"m":"glm-5","r":40,"s":91.23,"lo":26,"hi":54,"n":7,"rr":28,"mr":38},{"m":"claude-opus-4.5-thinking","r":41,"s":91.2,"lo":12,"hi":80,"n":6,"rr":29,"mr":44},{"m":"deepseek-v3.2-speciale","r":42,"s":91.02,"lo":11,"hi":59,"n":3,"rr":6,"mr":41},{"m":"qwen3-max-thinking","r":43,"s":91.02,"lo":26,"hi":70,"n":5,"rr":41,"mr":42},{"m":"ring-1t-2.5","r":44,"s":90.8,"lo":14,"hi":74,"n":3,"rr":8,"mr":43},{"m":"deepseek-v4-flash-thinking","r":45,"s":90.72,"lo":33,"hi":55,"n":4,"rr":317,"mr":48},{"m":"glm-4.7-thinking","r":46,"s":90.43,"lo":22,"hi":65,"n":3,"rr":9,"mr":46},{"m":"glm-4.7","r":47,"s":90.37,"lo":34,"hi":62,"n":4,"rr":11,"mr":45},{"m":"qwen3.6-plus","r":48,"s":90.13,"lo":32,"hi":61,"n":11,"rr":103,"mr":47},{"m":"glm-5.1","r":49,"s":89.89,"lo":36,"hi":55,"n":7,"rr":223,"mr":50},{"m":"kimi-k2.5-thinking","r":50,"s":89.89,"lo":34,"hi":55,"n":10,"rr":32,"mr":49},{"m":"inkling-small","r":51,"s":89.83,"lo":40,"hi":68,"n":4,"rr":72,"mr":52},{"m":"openpangu-2.0-pro-thinking","r":52,"s":89.68,"lo":40,"hi":59,"n":4,"rr":271,"mr":53},{"m":"kimi-k2.5","r":53,"s":89.48,"lo":43,"hi":56,"n":11,"rr":69,"mr":51},{"m":"mai-thinking-1","r":54,"s":88.98,"lo":44,"hi":79,"n":3,"rr":10,"mr":54},{"m":"qwen3.5-397b-a17b","r":55,"s":88.94,"lo":41,"hi":62,"n":14,"rr":152,"mr":55},{"m":"kimi-k2-thinking","r":56,"s":88.57,"lo":16,"hi":77,"n":5,"rr":21,"mr":57},{"m":"hy3-preview","r":57,"s":88.57,"lo":46,"hi":122,"n":3,"rr":506,"mr":67},{"m":"gpt-5.6-terra","r":58,"s":88.57,"lo":3,"hi":206,"n":3,"rr":100,"mr":63},{"m":"claude-opus-4.5","r":59,"s":88.55,"lo":41,"hi":67,"n":14,"rr":196,"mr":56},{"m":"intern-s2-preview","r":60,"s":88.48,"lo":51,"hi":66,"n":3,"rr":70,"mr":61},{"m":"intern-s2-mobius","r":61,"s":88.35,"lo":51,"hi":81,"n":3,"rr":36,"mr":58},{"m":"longcat-flash-prover","r":62,"s":88.01,"lo":32,"hi":86,"n":3,"rr":30,"mr":66},{"m":"ling-3.0-flash","r":63,"s":87.98,"lo":54,"hi":71,"n":3,"rr":33,"mr":62},{"m":"deepseek-v3.2-thinking","r":64,"s":87.78,"lo":50,"hi":72,"n":8,"rr":22,"mr":60},{"m":"claude-sonnet-4.6","r":65,"s":87.75,"lo":56,"hi":168,"n":5,"rr":123,"mr":59},{"m":"gpt-5-thinking","r":66,"s":87.57,"lo":52,"hi":259,"n":3,"rr":144,"mr":65},{"m":"qwen3.6-27b","r":67,"s":87.52,"lo":54,"hi":71,"n":11,"rr":37,"mr":68},{"m":"ternary-bonsai-2-27b","r":68,"s":87.42,"lo":50,"hi":192,"n":4,"rr":1,"mr":64},{"m":"nemotron-3-super-120b-a12b","r":69,"s":86.76,"lo":53,"hi":85,"n":5,"rr":31,"mr":69},{"m":"gpt-5-mini-high","r":70,"s":86.74,"lo":23,"hi":103,"n":10,"rr":165,"mr":73},{"m":"seed2.0-lite","r":71,"s":86.7,"lo":18,"hi":84,"n":8,"rr":108,"mr":71},{"m":"nemotron-cascade-2-30b-a3b","r":72,"s":86.69,"lo":51,"hi":93,"n":4,"rr":23,"mr":72},{"m":"qwen3.5-122b-a10b","r":73,"s":86.64,"lo":52,"hi":79,"n":8,"rr":99,"mr":77},{"m":"step3-vl-10b-pacore","r":74,"s":86.57,"lo":59,"hi":131,"n":4,"rr":40,"mr":75},{"m":"gpt-5","r":75,"s":86.48,"lo":57,"hi":107,"n":11,"rr":170,"mr":70},{"m":"nemotron-3-ultra","r":76,"s":86.36,"lo":33,"hi":127,"n":5,"rr":300,"mr":78},{"m":"qwen3.5-27b","r":77,"s":86.19,"lo":59,"hi":93,"n":14,"rr":46,"mr":74},{"m":"gpt-5-high","r":78,"s":86,"lo":61,"hi":89,"n":13,"rr":90,"mr":76},{"m":"grok-4-fast","r":79,"s":85.83,"lo":60,"hi":236,"n":3,"rr":12,"mr":82},{"m":"gpt-5.1-thinking","r":80,"s":85.74,"lo":42,"hi":268,"n":3,"rr":519,"mr":91},{"m":"seed1.8","r":81,"s":85.57,"lo":65,"hi":257,"n":8,"rr":158,"mr":79},{"m":"mimo-v2-flash","r":82,"s":85.55,"lo":57,"hi":103,"n":4,"rr":35,"mr":80},{"m":"grok-4","r":83,"s":85.39,"lo":69,"hi":96,"n":8,"rr":169,"mr":83},{"m":"qwen3.5-35b-a3b","r":84,"s":85.39,"lo":64,"hi":92,"n":10,"rr":81,"mr":81},{"m":"vibethinker-3b","r":85,"s":85.38,"lo":68,"hi":94,"n":5,"rr":25,"mr":85},{"m":"qwen3.8-27b-ud-q4-k-xl","r":86,"s":85.36,"lo":67,"hi":191,"n":4,"rr":2,"mr":86},{"m":"k-exaone-2.0","r":87,"s":85.28,"lo":71,"hi":106,"n":4,"rr":141,"mr":88},{"m":"glm-4.6","r":88,"s":85.21,"lo":71,"hi":91,"n":5,"rr":42,"mr":87},{"m":"qwen3.6-35b-a3b","r":89,"s":85.02,"lo":66,"hi":105,"n":13,"rr":44,"mr":84},{"m":"exaone-4.5-33b-thinking","r":90,"s":84.84,"lo":81,"hi":111,"n":5,"rr":67,"mr":93},{"m":"k-exaone","r":91,"s":84.76,"lo":80,"hi":95,"n":6,"rr":122,"mr":89},{"m":"gpt-oss-120b-high","r":92,"s":84.7,"lo":74,"hi":95,"n":7,"rr":26,"mr":90},{"m":"gpt-5.4-mini","r":93,"s":84.59,"lo":66,"hi":173,"n":5,"rr":97,"mr":92},{"m":"spark-x2.6-4b","r":94,"s":84.34,"lo":82,"hi":111,"n":3,"rr":92,"mr":94},{"m":"intern-s1-pro","r":95,"s":84.27,"lo":82,"hi":108,"n":4,"rr":126,"mr":95},{"m":"openpangu-2.0-flash-thinking","r":96,"s":83.99,"lo":71,"hi":208,"n":5,"rr":303,"mr":97},{"m":"spark-x2.5-4b","r":97,"s":83.94,"lo":86,"hi":115,"n":3,"rr":104,"mr":99},{"m":"gpt-oss-120b","r":98,"s":83.88,"lo":72,"hi":130,"n":11,"rr":117,"mr":96},{"m":"nvidia-nemotron-3-nano-30b-a3b-bf16","r":99,"s":83.7,"lo":18,"hi":110,"n":4,"rr":51,"mr":100},{"m":"deepseek-v3.2","r":100,"s":83.28,"lo":69,"hi":151,"n":8,"rr":49,"mr":98},{"m":"gemma-4-26b-a4b-it","r":101,"s":83.25,"lo":76,"hi":123,"n":9,"rr":64,"mr":101},{"m":"k2-horizon-7b","r":102,"s":83.07,"lo":87,"hi":110,"n":4,"rr":45,"mr":103},{"m":"qwen3-235b-a22b-thinking-2507","r":103,"s":83.02,"lo":83,"hi":110,"n":8,"rr":201,"mr":102},{"m":"qwen3-vl-235b-a22b-thinking","r":104,"s":82.78,"lo":85,"hi":111,"n":8,"rr":94,"mr":105},{"m":"command-a-plus-05-2026","r":105,"s":82.71,"lo":56,"hi":145,"n":4,"rr":65,"mr":108},{"m":"sarvam-105b","r":106,"s":82.67,"lo":79,"hi":117,"n":5,"rr":58,"mr":107},{"m":"k2-horizon-3.7b","r":107,"s":82.59,"lo":91,"hi":117,"n":4,"rr":56,"mr":106},{"m":"gpt-5.4-nano","r":108,"s":82.54,"lo":92,"hi":137,"n":3,"rr":212,"mr":112},{"m":"deepseek-v3.1-terminus","r":109,"s":82.33,"lo":90,"hi":130,"n":3,"rr":138,"mr":109},{"m":"nemotron-3-nano-30b-a3b","r":110,"s":82.17,"lo":90,"hi":123,"n":8,"rr":101,"mr":104},{"m":"longcat-flash-thinking","r":111,"s":81.86,"lo":98,"hi":265,"n":3,"rr":59,"mr":114},{"m":"gpt-5-mini","r":112,"s":81.8,"lo":89,"hi":160,"n":11,"rr":112,"mr":111},{"m":"claude-sonnet-4.5","r":113,"s":81.57,"lo":38,"hi":129,"n":12,"rr":225,"mr":115},{"m":"gemma-4-31b-it","r":114,"s":81.43,"lo":93,"hi":150,"n":14,"rr":80,"mr":110},{"m":"qwen-3-235b-a22b-thinking","r":115,"s":81.36,"lo":72,"hi":189,"n":5,"rr":79,"mr":118},{"m":"gemini-2.5-pro","r":116,"s":81.34,"lo":91,"hi":135,"n":21,"rr":276,"mr":113},{"m":"qwen3.5-omni-plus","r":117,"s":81.19,"lo":90,"hi":155,"n":5,"rr":162,"mr":125},{"m":"zdtaichu5.0-9b","r":118,"s":80.76,"lo":105,"hi":131,"n":7,"rr":116,"mr":120},{"m":"seed2.0-mini","r":119,"s":80.67,"lo":35,"hi":142,"n":7,"rr":272,"mr":119},{"m":"glm-4.7-flash","r":120,"s":80.65,"lo":106,"hi":155,"n":7,"rr":84,"mr":117},{"m":"o3","r":121,"s":80.59,"lo":94,"hi":148,"n":8,"rr":256,"mr":116},{"m":"o3-high","r":122,"s":80.57,"lo":77,"hi":133,"n":7,"rr":147,"mr":121},{"m":"ernie-5.0","r":123,"s":80.29,"lo":107,"hi":150,"n":4,"rr":105,"mr":126},{"m":"qwen3-next-80b-a3b-thinking","r":124,"s":80.04,"lo":100,"hi":135,"n":10,"rr":173,"mr":123},{"m":"deepseek-r1-0528","r":125,"s":80.01,"lo":98,"hi":140,"n":6,"rr":68,"mr":124},{"m":"intellect-3","r":126,"s":79.84,"lo":113,"hi":136,"n":5,"rr":39,"mr":122},{"m":"ax-k1","r":127,"s":79.78,"lo":83,"hi":267,"n":3,"rr":505,"mr":140},{"m":"ling-2.6-1t","r":128,"s":79.65,"lo":116,"hi":173,"n":3,"rr":163,"mr":130},{"m":"deepseek-v3.2-exp","r":129,"s":79.15,"lo":114,"hi":437,"n":4,"rr":114,"mr":128},{"m":"step3-vl-10b-sere","r":130,"s":79.11,"lo":116,"hi":170,"n":4,"rr":140,"mr":132},{"m":"qwen3.5-9b","r":131,"s":79.08,"lo":106,"hi":146,"n":16,"rr":120,"mr":127},{"m":"deepseek-v3.1-thinking","r":132,"s":79.07,"lo":99,"hi":298,"n":5,"rr":262,"mr":129},{"m":"gpt-oss-20b-high","r":133,"s":78.95,"lo":111,"hi":180,"n":6,"rr":86,"mr":137},{"m":"mistral-medium-3.5","r":134,"s":78.91,"lo":111,"hi":180,"n":4,"rr":199,"mr":131},{"m":"step3-vl-10b","r":135,"s":78.66,"lo":119,"hi":149,"n":9,"rr":164,"mr":133},{"m":"ring-2.6-1t-high","r":136,"s":78.5,"lo":123,"hi":168,"n":3,"rr":229,"mr":135},{"m":"ling-2.5-1t","r":137,"s":78.46,"lo":125,"hi":194,"n":3,"rr":192,"mr":136},{"m":"solar-open-100b","r":138,"s":78.33,"lo":114,"hi":152,"n":6,"rr":124,"mr":134},{"m":"o4-mini","r":139,"s":78.28,"lo":94,"hi":207,"n":4,"rr":107,"mr":141},{"m":"granite-4.2-8b","r":140,"s":78,"lo":129,"hi":165,"n":3,"rr":183,"mr":143},{"m":"superapriel-15b-instruct","r":141,"s":77.97,"lo":101,"hi":311,"n":4,"rr":19,"mr":151},{"m":"exaone-4.0-32b-thinking","r":142,"s":77.93,"lo":130,"hi":163,"n":3,"rr":194,"mr":144},{"m":"mistral-small-4-thinking","r":143,"s":77.88,"lo":130,"hi":156,"n":3,"rr":137,"mr":138},{"m":"gemini-3.1-flash-lite","r":144,"s":77.85,"lo":125,"hi":174,"n":3,"rr":286,"mr":149},{"m":"zaya1-8b","r":145,"s":77.76,"lo":119,"hi":195,"n":4,"rr":361,"mr":147},{"m":"dots-vlm1","r":146,"s":77.49,"lo":133,"hi":202,"n":3,"rr":139,"mr":157},{"m":"apriel-1.6-15b-thinker","r":147,"s":77.22,"lo":127,"hi":278,"n":3,"rr":200,"mr":162},{"m":"openreasoning-nemotron-32b","r":148,"s":77.16,"lo":120,"hi":161,"n":3,"rr":95,"mr":146},{"m":"qwen3-30b-a3b-thinking-2507","r":149,"s":77.15,"lo":101,"hi":172,"n":9,"rr":203,"mr":145},{"m":"glm-4.5-air","r":150,"s":77.12,"lo":117,"hi":162,"n":11,"rr":88,"mr":142},{"m":"qwen3-235b-a22b","r":151,"s":77.1,"lo":112,"hi":194,"n":13,"rr":210,"mr":139},{"m":"sarvam-30b","r":152,"s":76.96,"lo":129,"hi":174,"n":5,"rr":166,"mr":148},{"m":"qwen3-vl-235b-a22b","r":153,"s":76.92,"lo":100,"hi":166,"n":7,"rr":150,"mr":154},{"m":"nanbeige4.1-3b","r":154,"s":76.55,"lo":131,"hi":251,"n":3,"rr":242,"mr":156},{"m":"minimax-m2.7","r":155,"s":76.49,"lo":113,"hi":177,"n":7,"rr":385,"mr":152},{"m":"openpangu-r-72b-2512-slow-thinking","r":156,"s":76.31,"lo":126,"hi":172,"n":3,"rr":111,"mr":159},{"m":"gemma-4-26b-a4b","r":157,"s":76.26,"lo":110,"hi":494,"n":4,"rr":257,"mr":172},{"m":"minicpm5-2b","r":158,"s":76.26,"lo":137,"hi":229,"n":4,"rr":89,"mr":150},{"m":"ministral-3-14b-reasoning","r":159,"s":76.12,"lo":127,"hi":171,"n":7,"rr":131,"mr":153},{"m":"openpangu-2.0-pro","r":160,"s":75.99,"lo":112,"hi":199,"n":4,"rr":462,"mr":167},{"m":"nanbeige4-3b-thinking-2511","r":161,"s":75.89,"lo":132,"hi":272,"n":5,"rr":241,"mr":155},{"m":"gpt-5-nano-high","r":162,"s":75.87,"lo":141,"hi":198,"n":3,"rr":129,"mr":169},{"m":"openreasoning-nemotron-14b","r":163,"s":75.84,"lo":132,"hi":171,"n":3,"rr":135,"mr":160},{"m":"claude-4.5-haiku","r":164,"s":75.63,"lo":134,"hi":184,"n":6,"rr":208,"mr":161},{"m":"qwen3.5-4b","r":165,"s":75.6,"lo":120,"hi":179,"n":17,"rr":185,"mr":158},{"m":"nemotron-32b","r":166,"s":75.59,"lo":134,"hi":172,"n":4,"rr":230,"mr":164},{"m":"falcon-h1r-7b","r":167,"s":75.49,"lo":134,"hi":179,"n":4,"rr":85,"mr":163},{"m":"gpt-oss-20b","r":168,"s":75.39,"lo":90,"hi":234,"n":11,"rr":255,"mr":165},{"m":"qwen3-vl-32b-thinking","r":169,"s":75.37,"lo":125,"hi":181,"n":8,"rr":180,"mr":166},{"m":"k2-high-70b","r":170,"s":75.33,"lo":93,"hi":248,"n":4,"rr":60,"mr":174},{"m":"minimax-m2.1","r":171,"s":75.24,"lo":157,"hi":183,"n":4,"rr":254,"mr":170},{"m":"motif-2-12.7b-reasoning","r":172,"s":74.98,"lo":95,"hi":211,"n":5,"rr":17,"mr":168},{"m":"openpangu-2.0-flash","r":173,"s":74.93,"lo":145,"hi":185,"n":4,"rr":279,"mr":173},{"m":"qwen3-30b-a3b-2507","r":174,"s":74.87,"lo":139,"hi":250,"n":3,"rr":270,"mr":182},{"m":"qwen3-vl-30b-a3b-thinking","r":175,"s":74.86,"lo":154,"hi":212,"n":3,"rr":309,"mr":178},{"m":"minicpm-v-4.7-35b-a3b","r":176,"s":74.85,"lo":70,"hi":205,"n":4,"rr":119,"mr":188},{"m":"glm-4.5","r":177,"s":74.7,"lo":151,"hi":197,"n":5,"rr":189,"mr":175},{"m":"k2-think","r":178,"s":74.41,"lo":135,"hi":185,"n":4,"rr":243,"mr":176},{"m":"apriel-1.5-15b-thinker","r":179,"s":74.24,"lo":135,"hi":231,"n":6,"rr":195,"mr":171},{"m":"granite-4.2-3b","r":180,"s":73.9,"lo":162,"hi":190,"n":5,"rr":176,"mr":177},{"m":"k2-think-v2","r":181,"s":73.74,"lo":117,"hi":357,"n":6,"rr":53,"mr":184},{"m":"minimax-m1-80k","r":182,"s":73.5,"lo":149,"hi":193,"n":3,"rr":43,"mr":181},{"m":"qwen3-30b-a3b","r":183,"s":73.37,"lo":142,"hi":280,"n":9,"rr":214,"mr":179},{"m":"seed-thinking-v1.5","r":184,"s":73.02,"lo":146,"hi":207,"n":3,"rr":54,"mr":185},{"m":"qwen3-4b-2507","r":185,"s":72.93,"lo":168,"hi":215,"n":5,"rr":244,"mr":183},{"m":"gemma-4-12b-it","r":186,"s":72.93,"lo":146,"hi":196,"n":8,"rr":209,"mr":180},{"m":"minimax-m2","r":187,"s":72.66,"lo":152,"hi":262,"n":4,"rr":127,"mr":191},{"m":"qwen3-14b-thinking","r":188,"s":72.39,"lo":155,"hi":210,"n":3,"rr":71,"mr":186},{"m":"openpangu-r-7b-2512-slow-thinking","r":189,"s":72.34,"lo":148,"hi":208,"n":3,"rr":222,"mr":195},{"m":"qwen3-vl-8b-thinking","r":190,"s":72.32,"lo":156,"hi":218,"n":8,"rr":228,"mr":190},{"m":"openreasoning-nemotron-7b","r":191,"s":72.14,"lo":164,"hi":199,"n":9,"rr":258,"mr":187},{"m":"o3-mini","r":192,"s":72.12,"lo":120,"hi":212,"n":4,"rr":50,"mr":193},{"m":"claude-opus-4.1","r":193,"s":72.08,"lo":174,"hi":261,"n":4,"rr":246,"mr":204},{"m":"zgcm-1-7b","r":194,"s":71.95,"lo":166,"hi":209,"n":6,"rr":204,"mr":189},{"m":"gemini-3.5-flash-lite","r":195,"s":71.74,"lo":113,"hi":320,"n":4,"rr":329,"mr":194},{"m":"qwen3-32b-thinking","r":196,"s":71.41,"lo":152,"hi":222,"n":7,"rr":268,"mr":192},{"m":"minimax-m1-40k","r":197,"s":71.31,"lo":169,"hi":208,"n":3,"rr":74,"mr":198},{"m":"ovis2.6-30b-a3b","r":198,"s":71.3,"lo":137,"hi":326,"n":4,"rr":269,"mr":224},{"m":"gemini-2.5-flash-thinking","r":199,"s":71.21,"lo":172,"hi":220,"n":5,"rr":283,"mr":199},{"m":"nvidia-nemotron-nano-9b-v2","r":200,"s":71.19,"lo":147,"hi":229,"n":5,"rr":172,"mr":196},{"m":"gpt-oss-120b-medium","r":201,"s":70.97,"lo":184,"hi":221,"n":6,"rr":249,"mr":197},{"m":"gpt-5.1","r":202,"s":70.84,"lo":79,"hi":270,"n":3,"rr":588,"mr":220},{"m":"ernie-4.5-vl-28b-a3b-thinking","r":203,"s":70.78,"lo":133,"hi":268,"n":3,"rr":219,"mr":233},{"m":"qwen3-4b-thinking-2507","r":204,"s":70.51,"lo":184,"hi":229,"n":10,"rr":373,"mr":201},{"m":"qwen3-next-80b-a3b-instruct","r":205,"s":70.04,"lo":147,"hi":237,"n":5,"rr":280,"mr":208},{"m":"olmo-3.1-think-32b","r":206,"s":70.04,"lo":183,"hi":229,"n":11,"rr":261,"mr":200},{"m":"deepseek-r1-0528-qwen3-8b","r":207,"s":70.03,"lo":177,"hi":233,"n":7,"rr":275,"mr":202},{"m":"o1","r":208,"s":69.94,"lo":171,"hi":241,"n":5,"rr":136,"mr":205},{"m":"ling-1t","r":209,"s":69.89,"lo":181,"hi":238,"n":5,"rr":296,"mr":209},{"m":"o1-2024-12-17","r":210,"s":69.64,"lo":178,"hi":253,"n":4,"rr":133,"mr":207},{"m":"gemini-2.5-flash","r":211,"s":69.62,"lo":182,"hi":232,"n":10,"rr":294,"mr":206},{"m":"olmo-3-think-32b","r":212,"s":69.61,"lo":178,"hi":249,"n":6,"rr":156,"mr":203},{"m":"olmo-3-think-32b-dpo","r":213,"s":69.38,"lo":133,"hi":230,"n":7,"rr":198,"mr":212},{"m":"glm-4.6v","r":214,"s":69.38,"lo":166,"hi":240,"n":7,"rr":302,"mr":222},{"m":"qwen3-omni-30b-a3b-thinking","r":215,"s":69.31,"lo":205,"hi":286,"n":3,"rr":322,"mr":226},{"m":"o3-mini-medium","r":216,"s":69.3,"lo":193,"hi":228,"n":3,"rr":289,"mr":214},{"m":"deepseek-r1","r":217,"s":69.23,"lo":173,"hi":244,"n":8,"rr":365,"mr":210},{"m":"instella-moe-16b-a3b-dpo","r":218,"s":69.15,"lo":179,"hi":227,"n":3,"rr":106,"mr":217},{"m":"vibethinker-1.5b","r":219,"s":68.98,"lo":185,"hi":236,"n":3,"rr":295,"mr":218},{"m":"instella-moe-16b-a3b-think","r":220,"s":68.98,"lo":186,"hi":229,"n":3,"rr":110,"mr":221},{"m":"gpt-oss-20b-medium","r":221,"s":68.83,"lo":197,"hi":244,"n":3,"rr":91,"mr":216},{"m":"claude-3.7-sonnet","r":222,"s":68.67,"lo":188,"hi":284,"n":3,"rr":186,"mr":234},{"m":"glm-4.5v","r":223,"s":68.6,"lo":165,"hi":297,"n":6,"rr":285,"mr":250},{"m":"instella-moe-16b-a3b-sft","r":224,"s":68.59,"lo":181,"hi":234,"n":3,"rr":121,"mr":225},{"m":"qwen3-32b","r":225,"s":68.42,"lo":193,"hi":247,"n":12,"rr":238,"mr":213},{"m":"qwen3-8b-thinking","r":226,"s":68.38,"lo":179,"hi":242,"n":5,"rr":193,"mr":211},{"m":"minicpm4.1-8b","r":227,"s":68.37,"lo":187,"hi":256,"n":6,"rr":274,"mr":215},{"m":"joyai-llm-flash","r":228,"s":68.31,"lo":172,"hi":267,"n":3,"rr":48,"mr":227},{"m":"qwq-32b","r":229,"s":68.31,"lo":176,"hi":252,"n":6,"rr":245,"mr":219},{"m":"nemotron-3-nano-4b-thinking","r":230,"s":68.22,"lo":185,"hi":333,"n":3,"rr":284,"mr":230},{"m":"motif-2-12.7b-instruct","r":231,"s":68.12,"lo":162,"hi":258,"n":5,"rr":62,"mr":223},{"m":"qwen3-vl-32b-instruct","r":232,"s":67.77,"lo":156,"hi":248,"n":7,"rr":260,"mr":228},{"m":"qwen3.5-omni-flash","r":233,"s":67.68,"lo":170,"hi":254,"n":5,"rr":306,"mr":243},{"m":"qwen3-vl-30b-a3b-instruct","r":234,"s":67.67,"lo":167,"hi":243,"n":9,"rr":315,"mr":238},{"m":"ovis2.6-80b-a3b","r":235,"s":67.43,"lo":157,"hi":384,"n":4,"rr":311,"mr":260},{"m":"olmo-3-think-7b-dpo","r":236,"s":67.37,"lo":181,"hi":253,"n":4,"rr":288,"mr":235},{"m":"telechat3-36b-thinking","r":237,"s":67.36,"lo":212,"hi":247,"n":3,"rr":130,"mr":229},{"m":"ling-2.6-flash","r":238,"s":67.21,"lo":213,"hi":265,"n":3,"rr":405,"mr":231},{"m":"olmo-3-think-32b-sft","r":239,"s":67.21,"lo":144,"hi":246,"n":7,"rr":232,"mr":232},{"m":"qwen3-30b-a3b-instruct-2507","r":240,"s":67.05,"lo":191,"hi":278,"n":12,"rr":171,"mr":236},{"m":"qwen3-vl-4b-thinking","r":241,"s":66.91,"lo":184,"hi":243,"n":4,"rr":227,"mr":239},{"m":"olmo-3-think-7b-sft","r":242,"s":66.75,"lo":183,"hi":256,"n":4,"rr":278,"mr":240},{"m":"deepseek-r1-0120","r":243,"s":66.61,"lo":192,"hi":269,"n":3,"rr":352,"mr":241},{"m":"longcat-flash-lite","r":244,"s":66.44,"lo":185,"hi":268,"n":3,"rr":178,"mr":245},{"m":"lg-exaone-32b","r":245,"s":66.22,"lo":145,"hi":279,"n":4,"rr":109,"mr":246},{"m":"seed1.5-vl-thinking","r":246,"s":66.13,"lo":155,"hi":335,"n":3,"rr":273,"mr":270},{"m":"claude-opus-4","r":247,"s":66.08,"lo":178,"hi":375,"n":8,"rr":455,"mr":248},{"m":"phi-4-reasoning-plus","r":248,"s":66.07,"lo":224,"hi":266,"n":8,"rr":330,"mr":237},{"m":"seed-1.5-vl","r":249,"s":65.88,"lo":167,"hi":360,"n":6,"rr":308,"mr":251},{"m":"mimo-7b-rl","r":250,"s":65.49,"lo":219,"hi":264,"n":7,"rr":375,"mr":242},{"m":"olmo-3-think-7b","r":251,"s":64.65,"lo":233,"hi":279,"n":12,"rr":290,"mr":244},{"m":"phi-4-reasoning","r":252,"s":64.58,"lo":222,"hi":270,"n":3,"rr":390,"mr":253},{"m":"apriel-nemotron-15b-thinker","r":253,"s":64.32,"lo":146,"hi":283,"n":4,"rr":143,"mr":249},{"m":"llada2.0-flash","r":254,"s":64.31,"lo":211,"hi":279,"n":7,"rr":134,"mr":261},{"m":"acereason-nemotron-1.1","r":255,"s":64.29,"lo":232,"hi":271,"n":3,"rr":399,"mr":256},{"m":"kimi-k2-instruct","r":256,"s":64.25,"lo":182,"hi":288,"n":9,"rr":370,"mr":254},{"m":"openpangu-r-72b-2512-fast-thinking","r":257,"s":64.13,"lo":220,"hi":283,"n":3,"rr":389,"mr":259},{"m":"k2-medium-70b","r":258,"s":64.09,"lo":135,"hi":316,"n":4,"rr":248,"mr":263},{"m":"qwen3-14b","r":259,"s":64.03,"lo":225,"hi":311,"n":8,"rr":226,"mr":247},{"m":"spark-x2.5-1.7b","r":260,"s":63.94,"lo":247,"hi":296,"n":3,"rr":453,"mr":255},{"m":"llada2.1-flash-q","r":261,"s":63.81,"lo":204,"hi":274,"n":5,"rr":202,"mr":267},{"m":"telechat3-105b-a4.7b-thinking","r":262,"s":63.77,"lo":234,"hi":298,"n":3,"rr":181,"mr":258},{"m":"magistral-small-2506","r":263,"s":63.67,"lo":242,"hi":274,"n":3,"rr":407,"mr":262},{"m":"ling-flash-2.0","r":264,"s":63.64,"lo":201,"hi":286,"n":7,"rr":132,"mr":266},{"m":"longcat-flash-lite-sparse","r":265,"s":63.59,"lo":235,"hi":302,"n":5,"rr":406,"mr":252},{"m":"kimi-linear-instruct","r":266,"s":63.52,"lo":239,"hi":281,"n":4,"rr":313,"mr":257},{"m":"llada2.1-flash-s","r":267,"s":63.27,"lo":213,"hi":277,"n":5,"rr":213,"mr":273},{"m":"openthinker3-7b","r":268,"s":62.99,"lo":201,"hi":292,"n":4,"rr":346,"mr":268},{"m":"granite-4.1-30b","r":269,"s":62.77,"lo":173,"hi":429,"n":4,"rr":102,"mr":282},{"m":"nemotron-research-goosereason-4b-instruct","r":270,"s":62.58,"lo":223,"hi":322,"n":6,"rr":231,"mr":271},{"m":"deepseek-r1-distill-qwen-32b","r":271,"s":62.39,"lo":222,"hi":290,"n":4,"rr":345,"mr":272},{"m":"questa-nemotron-1.5b","r":272,"s":62.24,"lo":238,"hi":283,"n":5,"rr":359,"mr":269},{"m":"kimi-k2-0905","r":273,"s":62.14,"lo":226,"hi":286,"n":4,"rr":479,"mr":275},{"m":"qwen3-8b","r":274,"s":61.82,"lo":242,"hi":312,"n":13,"rr":382,"mr":265},{"m":"qwen3-4b","r":275,"s":61.77,"lo":246,"hi":341,"n":9,"rr":177,"mr":264},{"m":"gpt-5.4-none","r":276,"s":61.67,"lo":237,"hi":324,"n":3,"rr":447,"mr":276},{"m":"gpt-5-nano","r":277,"s":61.59,"lo":200,"hi":322,"n":6,"rr":310,"mr":292},{"m":"llama-3.1-nemotron-nano-8b-v1","r":278,"s":61.58,"lo":176,"hi":306,"n":4,"rr":221,"mr":279},{"m":"olmo-hybrid-think-7b-sft","r":279,"s":61.54,"lo":217,"hi":300,"n":4,"rr":367,"mr":277},{"m":"qwen3-omni-30b-a3b-instruct","r":280,"s":60.76,"lo":255,"hi":325,"n":6,"rr":398,"mr":289},{"m":"nemotron-3-nano-4b","r":281,"s":60.65,"lo":259,"hi":298,"n":4,"rr":337,"mr":274},{"m":"olmo-3.1-instruct-32b","r":282,"s":60.27,"lo":246,"hi":348,"n":6,"rr":252,"mr":278},{"m":"o1-mini","r":283,"s":60.14,"lo":192,"hi":305,"n":4,"rr":216,"mr":280},{"m":"skywork-or1-7b","r":284,"s":60.04,"lo":247,"hi":309,"n":3,"rr":471,"mr":281},{"m":"gemini-2.5-flash-lite","r":285,"s":59.95,"lo":221,"hi":309,"n":8,"rr":344,"mr":285},{"m":"youtu-llm-2b","r":286,"s":59.5,"lo":254,"hi":316,"n":3,"rr":282,"mr":283},{"m":"openpangu-r-7b-2512-fast-thinking","r":287,"s":59.29,"lo":265,"hi":319,"n":3,"rr":474,"mr":284},{"m":"deepseek-r1-distill-32b","r":288,"s":59.09,"lo":254,"hi":309,"n":5,"rr":417,"mr":288},{"m":"hunyuan-4b-instruct","r":289,"s":58.97,"lo":265,"hi":329,"n":5,"rr":468,"mr":287},{"m":"step-3","r":290,"s":58.78,"lo":221,"hi":362,"n":5,"rr":358,"mr":307},{"m":"ling-mini-2.0","r":291,"s":58.51,"lo":239,"hi":308,"n":6,"rr":343,"mr":293},{"m":"nemotron-h-47b-reasoning","r":292,"s":58.43,"lo":269,"hi":312,"n":4,"rr":391,"mr":286},{"m":"granite-4.1-8b","r":293,"s":58.27,"lo":189,"hi":354,"n":4,"rr":82,"mr":302},{"m":"glm-4.1v","r":294,"s":58.25,"lo":222,"hi":415,"n":5,"rr":376,"mr":309},{"m":"marco-mini-instruct","r":295,"s":57.93,"lo":251,"hi":326,"n":4,"rr":149,"mr":297},{"m":"deepseek-v3-0324","r":296,"s":57.89,"lo":245,"hi":326,"n":6,"rr":360,"mr":290},{"m":"claude-3.7-sonnet-thinking","r":297,"s":57.83,"lo":202,"hi":335,"n":3,"rr":247,"mr":312},{"m":"ernie-4.5","r":298,"s":57.44,"lo":210,"hi":341,"n":5,"rr":206,"mr":300},{"m":"grok-3","r":299,"s":56.88,"lo":238,"hi":313,"n":3,"rr":334,"mr":295},{"m":"trinity-mini","r":300,"s":56.76,"lo":286,"hi":333,"n":3,"rr":364,"mr":294},{"m":"qwen3-vl-8b-instruct","r":301,"s":56.51,"lo":261,"hi":329,"n":10,"rr":435,"mr":296},{"m":"lfm2.5-8b-a1b","r":302,"s":56.47,"lo":281,"hi":333,"n":4,"rr":409,"mr":291},{"m":"gpt-oss-120b-low","r":303,"s":56.46,"lo":290,"hi":342,"n":3,"rr":527,"mr":303},{"m":"gemini-2.0-pro","r":304,"s":56.11,"lo":247,"hi":335,"n":5,"rr":235,"mr":306},{"m":"nemotron-1.5b","r":305,"s":56.09,"lo":278,"hi":326,"n":5,"rr":464,"mr":299},{"m":"k2-v2","r":306,"s":55.44,"lo":268,"hi":336,"n":3,"rr":188,"mr":301},{"m":"qwen3-4b-instruct-2507","r":307,"s":55.07,"lo":278,"hi":366,"n":11,"rr":380,"mr":304},{"m":"deepseek-v3","r":308,"s":54.89,"lo":264,"hi":376,"n":9,"rr":351,"mr":298},{"m":"claude-sonnet-4","r":309,"s":54.32,"lo":240,"hi":342,"n":11,"rr":457,"mr":314},{"m":"llada2.1-mini-q","r":310,"s":54.22,"lo":260,"hi":331,"n":5,"rr":319,"mr":315},{"m":"glm-4.6v-flash","r":311,"s":54.12,"lo":252,"hi":423,"n":4,"rr":397,"mr":326},{"m":"qwen3-vl-4b-instruct","r":312,"s":54.01,"lo":287,"hi":346,"n":8,"rr":444,"mr":313},{"m":"gemma-3-27b","r":313,"s":53.99,"lo":250,"hi":330,"n":5,"rr":75,"mr":316},{"m":"gemini-2.0-flash","r":314,"s":53.73,"lo":264,"hi":379,"n":3,"rr":338,"mr":323},{"m":"lfm2.5-2.6b","r":315,"s":53.29,"lo":299,"hi":371,"n":4,"rr":448,"mr":305},{"m":"openreasoning-nemotron-1.5b","r":316,"s":53.17,"lo":297,"hi":364,"n":5,"rr":410,"mr":310},{"m":"gemma-4-e4b-it","r":317,"s":52.82,"lo":287,"hi":365,"n":15,"rr":461,"mr":308},{"m":"llada2.1-mini-s","r":318,"s":52.3,"lo":271,"hi":346,"n":5,"rr":341,"mr":322},{"m":"qwen3.8-27b-iq2-xxs","r":319,"s":52.29,"lo":254,"hi":384,"n":4,"rr":224,"mr":311},{"m":"gpt-4.1","r":320,"s":51.98,"lo":289,"hi":351,"n":8,"rr":331,"mr":317},{"m":"deepseek-r1-distill-qwen-7b","r":321,"s":51.79,"lo":292,"hi":391,"n":5,"rr":418,"mr":318},{"m":"llada2.0-mini","r":322,"s":51.18,"lo":269,"hi":350,"n":6,"rr":386,"mr":325},{"m":"deepseek-r1-distill-llama-8b","r":323,"s":50.32,"lo":297,"hi":416,"n":4,"rr":368,"mr":320},{"m":"k2-horizon-0.9b","r":324,"s":49.89,"lo":316,"hi":396,"n":3,"rr":567,"mr":324},{"m":"openpangu-vl-7b","r":325,"s":49.88,"lo":287,"hi":359,"n":3,"rr":321,"mr":327},{"m":"smollm3-3b","r":326,"s":49.77,"lo":310,"hi":398,"n":12,"rr":445,"mr":319},{"m":"minicpm-v-4.6-thinking","r":327,"s":49.67,"lo":293,"hi":340,"n":4,"rr":372,"mr":334},{"m":"minicpm5-1b","r":328,"s":49.43,"lo":309,"hi":407,"n":4,"rr":489,"mr":321},{"m":"mistral-3.2-24b","r":329,"s":48.89,"lo":241,"hi":382,"n":3,"rr":27,"mr":337},{"m":"o1-preview","r":330,"s":48.06,"lo":307,"hi":361,"n":3,"rr":259,"mr":328},{"m":"gpt-4.5","r":331,"s":47.91,"lo":212,"hi":359,"n":3,"rr":392,"mr":336},{"m":"k2-low-70b","r":332,"s":47.59,"lo":197,"hi":377,"n":4,"rr":437,"mr":330},{"m":"nemotron-3-super-120b-a12b-base","r":333,"s":47.27,"lo":283,"hi":356,"n":7,"rr":220,"mr":332},{"m":"olmo-3-instruct-7b","r":334,"s":47.23,"lo":306,"hi":417,"n":7,"rr":366,"mr":329},{"m":"nemotron-3.5-super-vl-120b-a12b-base","r":335,"s":46.8,"lo":166,"hi":376,"n":4,"rr":38,"mr":338},{"m":"nemotron-3-nano-30b-a3b-base","r":336,"s":46.73,"lo":232,"hi":361,"n":5,"rr":63,"mr":333},{"m":"qwen2.5-14b-instruct","r":337,"s":45.45,"lo":270,"hi":370,"n":3,"rr":55,"mr":344},{"m":"kimi-vl-a3b-thinking-2506","r":338,"s":45.36,"lo":281,"hi":509,"n":5,"rr":469,"mr":354},{"m":"mobilellm-r1.5-950m","r":339,"s":45,"lo":327,"hi":421,"n":4,"rr":400,"mr":335},{"m":"olmo-3.1-instruct-32b-dpo","r":340,"s":44.97,"lo":270,"hi":409,"n":4,"rr":531,"mr":341},{"m":"gemma-4-e2b-it","r":341,"s":44.89,"lo":319,"hi":440,"n":13,"rr":494,"mr":331},{"m":"kimi-vl-a3b-thinking","r":342,"s":44.74,"lo":260,"hi":408,"n":3,"rr":404,"mr":359},{"m":"gemma-3-27b-it","r":343,"s":44.56,"lo":290,"hi":399,"n":9,"rr":446,"mr":339},{"m":"keye-vl-8b","r":344,"s":43.98,"lo":296,"hi":512,"n":3,"rr":507,"mr":365},{"m":"qwen2.5-math-72b-instruct","r":345,"s":43.91,"lo":302,"hi":416,"n":7,"rr":318,"mr":343},{"m":"gemma-3-12b","r":346,"s":43.82,"lo":312,"hi":555,"n":3,"rr":281,"mr":346},{"m":"gpt-5-minimal","r":347,"s":43.54,"lo":333,"hi":466,"n":4,"rr":509,"mr":350},{"m":"qwen3-1.7b","r":348,"s":43.49,"lo":332,"hi":461,"n":14,"rr":484,"mr":342},{"m":"ling-2.6-1t-base","r":349,"s":43.32,"lo":314,"hi":385,"n":4,"rr":326,"mr":352},{"m":"qwen3-8b-non-thinking","r":350,"s":43.08,"lo":306,"hi":407,"n":7,"rr":518,"mr":345},{"m":"ministral-3-8b-instruct","r":351,"s":42.9,"lo":318,"hi":450,"n":4,"rr":299,"mr":358},{"m":"nemotron-3-ultra-base","r":352,"s":42.71,"lo":300,"hi":411,"n":3,"rr":52,"mr":353},{"m":"lfm2.5-1.2b-thinking","r":353,"s":42.64,"lo":332,"hi":457,"n":5,"rr":476,"mr":340},{"m":"qwen3.5-35b-a3b-base","r":354,"s":42.59,"lo":322,"hi":394,"n":3,"rr":182,"mr":348},{"m":"minicpm-o-4.5","r":355,"s":41.85,"lo":258,"hi":412,"n":3,"rr":78,"mr":361},{"m":"mistral-large-instruct-2407","r":356,"s":41.77,"lo":272,"hi":405,"n":3,"rr":66,"mr":362},{"m":"qwen2.5-vl-72b-instruct","r":357,"s":41.7,"lo":305,"hi":406,"n":3,"rr":426,"mr":379},{"m":"ling-3.0-flash-base","r":358,"s":41.47,"lo":289,"hi":408,"n":3,"rr":415,"mr":364},{"m":"deepseek-v3.1","r":359,"s":41.43,"lo":343,"hi":452,"n":3,"rr":377,"mr":355},{"m":"mistral-medium-3","r":360,"s":41.19,"lo":296,"hi":426,"n":3,"rr":515,"mr":363},{"m":"claude-3.5-sonnet-20240620","r":361,"s":41.01,"lo":212,"hi":402,"n":3,"rr":148,"mr":370},{"m":"deepseek-r1-distill-qwen-1.5b","r":362,"s":40.91,"lo":337,"hi":439,"n":5,"rr":402,"mr":349},{"m":"granite-4.1-3b","r":363,"s":40.87,"lo":279,"hi":458,"n":4,"rr":251,"mr":372},{"m":"gpt-5.4-mini-none","r":364,"s":40.48,"lo":354,"hi":488,"n":3,"rr":622,"mr":347},{"m":"gemma-3-12b-it","r":365,"s":40.42,"lo":330,"hi":425,"n":10,"rr":413,"mr":351},{"m":"internvl3.5-8b","r":366,"s":40.42,"lo":258,"hi":490,"n":4,"rr":301,"mr":386},{"m":"qwen3-32b-nothinking","r":367,"s":40.23,"lo":344,"hi":438,"n":5,"rr":587,"mr":360},{"m":"llama-4-maverick","r":368,"s":39.87,"lo":208,"hi":431,"n":3,"rr":378,"mr":378},{"m":"mistral-small-3.1-24b-instruct","r":369,"s":39.84,"lo":329,"hi":426,"n":4,"rr":174,"mr":381},{"m":"gemini-1.5-flash","r":370,"s":39.73,"lo":346,"hi":402,"n":4,"rr":292,"mr":369},{"m":"qwen2.5-72b-instruct","r":371,"s":39.44,"lo":313,"hi":440,"n":7,"rr":339,"mr":357},{"m":"ling-2.6-flash-base","r":372,"s":39.43,"lo":340,"hi":407,"n":4,"rr":354,"mr":377},{"m":"lfm2-24b-a2b","r":373,"s":39.29,"lo":339,"hi":463,"n":4,"rr":316,"mr":380},{"m":"llada2.0-flash-preview","r":374,"s":39.21,"lo":350,"hi":414,"n":4,"rr":412,"mr":367},{"m":"qwen3-8b-instruct","r":375,"s":39.01,"lo":307,"hi":419,"n":3,"rr":96,"mr":374},{"m":"ling-1t-base","r":376,"s":38.86,"lo":346,"hi":411,"n":4,"rr":350,"mr":383},{"m":"kimi-k2-base","r":377,"s":38.84,"lo":313,"hi":414,"n":4,"rr":61,"mr":390},{"m":"minicpm-v-4.6","r":378,"s":38.81,"lo":321,"hi":425,"n":5,"rr":456,"mr":397},{"m":"nemotron-3.5-lightning-30b-a3b","r":379,"s":38.53,"lo":201,"hi":504,"n":3,"rr":153,"mr":392},{"m":"lfm2-350m-math","r":380,"s":38.52,"lo":352,"hi":424,"n":4,"rr":495,"mr":368},{"m":"qwen2-math-72b-instruct","r":381,"s":38.49,"lo":324,"hi":444,"n":7,"rr":371,"mr":375},{"m":"gpt-4o-2024-08-06","r":382,"s":38.42,"lo":307,"hi":487,"n":7,"rr":353,"mr":376},{"m":"llama-4-scout-17b","r":383,"s":38.35,"lo":342,"hi":466,"n":7,"rr":362,"mr":366},{"m":"olmo-3-instruct-7b-dpo","r":384,"s":38.34,"lo":336,"hi":432,"n":4,"rr":579,"mr":371},{"m":"gpt-4o-mini","r":385,"s":38.31,"lo":298,"hi":429,"n":4,"rr":207,"mr":388},{"m":"gpt-5-nano-minimal","r":386,"s":37.67,"lo":358,"hi":588,"n":4,"rr":602,"mr":405},{"m":"minicpm-v-4.7-1b","r":387,"s":37.58,"lo":304,"hi":446,"n":3,"rr":440,"mr":402},{"m":"deepseek-v4-flash-base","r":388,"s":37.53,"lo":335,"hi":471,"n":5,"rr":113,"mr":384},{"m":"nemotron-labs-twotower-30b-a3b-base","r":389,"s":37.52,"lo":356,"hi":406,"n":3,"rr":83,"mr":387},{"m":"qwen3.5-2b","r":390,"s":37.5,"lo":350,"hi":505,"n":15,"rr":525,"mr":356},{"m":"qwen2.5-32b-instruct","r":391,"s":37.32,"lo":308,"hi":452,"n":8,"rr":411,"mr":373},{"m":"marco-nano-instruct","r":392,"s":37.15,"lo":353,"hi":438,"n":4,"rr":298,"mr":396},{"m":"hunyuan-large","r":393,"s":37.13,"lo":325,"hi":419,"n":3,"rr":73,"mr":399},{"m":"qwen2.5-math-7b-instruct","r":394,"s":37.1,"lo":332,"hi":451,"n":7,"rr":384,"mr":389},{"m":"qwen3-1.7b-thinking","r":395,"s":36.94,"lo":349,"hi":521,"n":6,"rr":549,"mr":382},{"m":"hy3-preview-base","r":396,"s":36.92,"lo":326,"hi":433,"n":6,"rr":328,"mr":398},{"m":"falcon-h1-34b-instruct","r":397,"s":36.74,"lo":349,"hi":449,"n":5,"rr":441,"mr":385},{"m":"qwen2.5-coder-32b-instruct","r":398,"s":36.37,"lo":354,"hi":448,"n":5,"rr":422,"mr":395},{"m":"llama-3.1-405b-instruct","r":399,"s":36.34,"lo":201,"hi":432,"n":4,"rr":323,"mr":393},{"m":"joyai-llm-flash-base","r":400,"s":36.21,"lo":365,"hi":429,"n":3,"rr":118,"mr":391},{"m":"claude-3.5-sonnet","r":401,"s":35.83,"lo":266,"hi":434,"n":8,"rr":342,"mr":401},{"m":"deepseek-v4-pro-base","r":402,"s":35.62,"lo":328,"hi":439,"n":4,"rr":87,"mr":410},{"m":"gemini-1.5-pro","r":403,"s":35.35,"lo":316,"hi":502,"n":9,"rr":460,"mr":403},{"m":"ling-2.5-flash-base","r":404,"s":35.32,"lo":347,"hi":449,"n":3,"rr":486,"mr":409},{"m":"gemma-3-4b","r":405,"s":35.17,"lo":361,"hi":635,"n":3,"rr":470,"mr":416},{"m":"apertus-v1.5-70b-thinking","r":406,"s":35.14,"lo":382,"hi":457,"n":5,"rr":459,"mr":394},{"m":"qwen2-72b-instruct","r":407,"s":34.88,"lo":359,"hi":469,"n":6,"rr":305,"mr":408},{"m":"ling-flash-base-2.0","r":408,"s":34.77,"lo":359,"hi":442,"n":6,"rr":332,"mr":414},{"m":"lfm2-8b-a1b","r":409,"s":34.65,"lo":375,"hi":456,"n":7,"rr":387,"mr":406},{"m":"deepseek-v3.2-base","r":410,"s":34.43,"lo":344,"hi":460,"n":4,"rr":115,"mr":417},{"m":"qwen-2.5-72b","r":411,"s":34.32,"lo":305,"hi":453,"n":7,"rr":395,"mr":407},{"m":"skywork-o1-open-llama-3.1-8b","r":412,"s":34.31,"lo":356,"hi":462,"n":5,"rr":433,"mr":411},{"m":"deepseek-v2.5","r":413,"s":34.15,"lo":278,"hi":447,"n":4,"rr":336,"mr":412},{"m":"wedlm-8b-instruct","r":414,"s":34.07,"lo":309,"hi":442,"n":3,"rr":161,"mr":413},{"m":"granite-4.0-h-small","r":415,"s":33.9,"lo":313,"hi":525,"n":7,"rr":419,"mr":418},{"m":"apertus-v1.5-8b-thinking","r":416,"s":33.73,"lo":391,"hi":467,"n":5,"rr":472,"mr":404},{"m":"claude-3.5-sonnet-20241022","r":417,"s":33.63,"lo":251,"hi":576,"n":6,"rr":388,"mr":400},{"m":"internvl3.5-4b","r":418,"s":33.47,"lo":321,"hi":504,"n":6,"rr":466,"mr":441},{"m":"qwen2.5-math-72b","r":419,"s":33.29,"lo":359,"hi":438,"n":3,"rr":93,"mr":424},{"m":"gpt-5-mini-minimal","r":420,"s":33.17,"lo":327,"hi":508,"n":3,"rr":508,"mr":443},{"m":"qwen2-math-7b-instruct","r":421,"s":33.13,"lo":377,"hi":461,"n":7,"rr":421,"mr":415},{"m":"deepseek-coder-v2-instruct","r":422,"s":33.12,"lo":335,"hi":471,"n":5,"rr":450,"mr":419},{"m":"qwen3-30b-a3b-base","r":423,"s":32.69,"lo":356,"hi":452,"n":3,"rr":175,"mr":421},{"m":"gpt-4o","r":424,"s":32.67,"lo":310,"hi":473,"n":11,"rr":394,"mr":420},{"m":"deepseek-v3.2-exp-base","r":425,"s":32.48,"lo":341,"hi":463,"n":3,"rr":160,"mr":429},{"m":"deepseek-v4.1-flash-base","r":426,"s":32.23,"lo":313,"hi":469,"n":3,"rr":168,"mr":431},{"m":"granite-4.0-h-micro","r":427,"s":31.87,"lo":305,"hi":554,"n":4,"rr":430,"mr":446},{"m":"deepseek-v3-base","r":428,"s":31.77,"lo":369,"hi":454,"n":4,"rr":128,"mr":430},{"m":"glm-4.5-base","r":429,"s":31.64,"lo":367,"hi":455,"n":4,"rr":125,"mr":438},{"m":"kanana-1.5-o-9.8b-instruct-2602","r":430,"s":31.39,"lo":343,"hi":473,"n":3,"rr":480,"mr":449},{"m":"mistral-large-3-base","r":431,"s":31.19,"lo":355,"hi":470,"n":4,"rr":253,"mr":432},{"m":"llama-3.3-70b-instruct","r":432,"s":31.09,"lo":267,"hi":468,"n":3,"rr":191,"mr":433},{"m":"gpt-4-turbo-2024-04-09","r":433,"s":30.85,"lo":247,"hi":480,"n":5,"rr":335,"mr":426},{"m":"qwen2.5-math-1.5b-instruct","r":434,"s":30.68,"lo":387,"hi":493,"n":7,"rr":442,"mr":428},{"m":"falcon-h1-7b","r":435,"s":30.57,"lo":415,"hi":483,"n":5,"rr":501,"mr":427},{"m":"qwen3-6b","r":436,"s":30.54,"lo":404,"hi":474,"n":4,"rr":565,"mr":425},{"m":"gemma-3-4b-it","r":437,"s":30.43,"lo":392,"hi":490,"n":8,"rr":416,"mr":423},{"m":"gpt-4","r":438,"s":30.4,"lo":377,"hi":493,"n":4,"rr":381,"mr":439},{"m":"qwen2.5-coder-14b-instruct","r":439,"s":30.34,"lo":353,"hi":489,"n":5,"rr":473,"mr":436},{"m":"internlm2-math-plus-mixtral8x22b","r":440,"s":30.3,"lo":291,"hi":485,"n":3,"rr":369,"mr":451},{"m":"gpt-4o-2024-05-13","r":441,"s":30.29,"lo":347,"hi":489,"n":9,"rr":423,"mr":435},{"m":"mobilellm-r1-950m","r":442,"s":30.16,"lo":411,"hi":524,"n":6,"rr":503,"mr":422},{"m":"llama-3.1-70b-instruct","r":443,"s":30.11,"lo":395,"hi":472,"n":6,"rr":347,"mr":444},{"m":"mimo-v2.5-base","r":444,"s":30.05,"lo":414,"hi":475,"n":5,"rr":428,"mr":437},{"m":"falcon-h1-1.5b-deep","r":445,"s":29.81,"lo":399,"hi":492,"n":5,"rr":499,"mr":434},{"m":"step-3.5-flash-base","r":446,"s":29.7,"lo":398,"hi":486,"n":5,"rr":434,"mr":442},{"m":"mistral-small-3.2-24b-instruct","r":447,"s":29.49,"lo":379,"hi":479,"n":3,"rr":293,"mr":454},{"m":"falcon-h1-3b","r":448,"s":29.46,"lo":419,"hi":481,"n":5,"rr":502,"mr":440},{"m":"qwen3-vl-2b-instruct","r":449,"s":28.99,"lo":381,"hi":508,"n":8,"rr":424,"mr":459},{"m":"qwen2.5-7b-instruct","r":450,"s":28.72,"lo":386,"hi":527,"n":8,"rr":536,"mr":445},{"m":"olmo-hybrid-instruct-7b-dpo","r":451,"s":28.57,"lo":372,"hi":508,"n":4,"rr":614,"mr":447},{"m":"claude-3.5-haiku-20241022","r":452,"s":28.53,"lo":297,"hi":620,"n":3,"rr":403,"mr":476},{"m":"olmo-3.1-instruct-32b-sft","r":453,"s":28.42,"lo":384,"hi":522,"n":4,"rr":616,"mr":448},{"m":"qwen2-math-72b","r":454,"s":28.29,"lo":386,"hi":476,"n":3,"rr":159,"mr":456},{"m":"qwen3-8b-base","r":455,"s":27.88,"lo":410,"hi":489,"n":3,"rr":396,"mr":460},{"m":"ling-3.0-tiny-base","r":456,"s":27.62,"lo":394,"hi":497,"n":3,"rr":558,"mr":458},{"m":"ling-2.5-mini-base","r":457,"s":27.55,"lo":398,"hi":491,"n":3,"rr":557,"mr":461},{"m":"qvq-72b","r":458,"s":27.55,"lo":334,"hi":501,"n":3,"rr":546,"mr":473},{"m":"numinamath-72b-cot","r":459,"s":27.52,"lo":418,"hi":535,"n":7,"rr":478,"mr":453},{"m":"gpt-4o-mini-2024-07-18","r":460,"s":27.41,"lo":304,"hi":515,"n":3,"rr":477,"mr":464},{"m":"lfm2.5-1.2b-instruct","r":461,"s":27.23,"lo":426,"hi":579,"n":3,"rr":512,"mr":450},{"m":"qwen2.5-omni-7b","r":462,"s":27.19,"lo":387,"hi":516,"n":4,"rr":438,"mr":480},{"m":"qwen2.5-math-7b","r":463,"s":26.89,"lo":345,"hi":497,"n":3,"rr":179,"mr":468},{"m":"llama-3.3-70b","r":464,"s":26.84,"lo":290,"hi":588,"n":6,"rr":467,"mr":457},{"m":"gemma-3-27b-vl","r":465,"s":26.42,"lo":386,"hi":582,"n":5,"rr":553,"mr":488},{"m":"qwen2.5-7b","r":466,"s":26.22,"lo":436,"hi":518,"n":7,"rr":522,"mr":455},{"m":"falcon-h1-1.5b","r":467,"s":26.03,"lo":443,"hi":530,"n":5,"rr":545,"mr":462},{"m":"kimi-linear-base","r":468,"s":26.02,"lo":421,"hi":489,"n":3,"rr":190,"mr":471},{"m":"qwen3-0.6b","r":469,"s":25.76,"lo":450,"hi":573,"n":10,"rr":612,"mr":452},{"m":"qwen2.5-coder-7b-instruct","r":470,"s":25.63,"lo":428,"hi":551,"n":6,"rr":562,"mr":463},{"m":"ministral-3-3b-instruct","r":471,"s":25.4,"lo":344,"hi":565,"n":4,"rr":432,"mr":483},{"m":"qwen2-math-1.5b-instruct","r":472,"s":25.37,"lo":430,"hi":532,"n":7,"rr":490,"mr":465},{"m":"lfm2-2.6b","r":473,"s":25.34,"lo":443,"hi":509,"n":5,"rr":414,"mr":475},{"m":"claude-3-opus-20240229","r":474,"s":25.3,"lo":239,"hi":512,"n":4,"rr":357,"mr":466},{"m":"qwen2-72b","r":475,"s":25.29,"lo":380,"hi":507,"n":3,"rr":215,"mr":472},{"m":"gemini-1.0-ultra","r":476,"s":25.23,"lo":285,"hi":510,"n":3,"rr":325,"mr":477},{"m":"deepseek-coder-v2-lite-instruct","r":477,"s":25.17,"lo":440,"hi":515,"n":7,"rr":493,"mr":469},{"m":"olmo-hybrid-instruct-7b-sft","r":478,"s":24.86,"lo":414,"hi":537,"n":4,"rr":623,"mr":467},{"m":"deepseek-v2-chat-sft","r":479,"s":24.44,"lo":358,"hi":513,"n":3,"rr":218,"mr":484},{"m":"gemma-2-9b-it","r":480,"s":24.33,"lo":375,"hi":529,"n":3,"rr":264,"mr":491},{"m":"claude-3-opus","r":481,"s":24.23,"lo":295,"hi":524,"n":6,"rr":449,"mr":479},{"m":"glm-4.5-air-base","r":482,"s":24.18,"lo":398,"hi":518,"n":5,"rr":349,"mr":490},{"m":"falcon3-10b","r":483,"s":23.99,"lo":448,"hi":540,"n":5,"rr":541,"mr":474},{"m":"internlm2-math-plus-20b","r":484,"s":23.88,"lo":440,"hi":532,"n":6,"rr":475,"mr":485},{"m":"deepseek-math-7b-rl","r":485,"s":23.71,"lo":435,"hi":529,"n":5,"rr":458,"mr":478},{"m":"granite-3.3-8b-instruct","r":486,"s":23.69,"lo":449,"hi":546,"n":6,"rr":559,"mr":470},{"m":"olmo-3-7b-sft","r":487,"s":23.67,"lo":430,"hi":547,"n":4,"rr":625,"mr":481},{"m":"apertus-v1.5-70b","r":488,"s":23.26,"lo":426,"hi":507,"n":3,"rr":312,"mr":487},{"m":"gpt-4-1106-preview","r":489,"s":23.22,"lo":249,"hi":570,"n":3,"rr":452,"mr":486},{"m":"falcon3-7b","r":490,"s":23.14,"lo":465,"hi":542,"n":5,"rr":552,"mr":482},{"m":"qwen3.5-9b-base","r":491,"s":23.06,"lo":441,"hi":550,"n":3,"rr":594,"mr":493},{"m":"kanana-2-3b-instruct","r":492,"s":22.7,"lo":434,"hi":531,"n":3,"rr":492,"mr":492},{"m":"qwen2.5-vl-7b","r":493,"s":22.65,"lo":407,"hi":576,"n":5,"rr":574,"mr":516},{"m":"moonlight-base","r":494,"s":22.57,"lo":417,"hi":538,"n":4,"rr":356,"mr":502},{"m":"kimi-vl-a3b-instruct","r":495,"s":22.48,"lo":373,"hi":548,"n":3,"rr":538,"mr":519},{"m":"qwen2-57b-a14b-instruct","r":496,"s":22.4,"lo":418,"hi":524,"n":3,"rr":287,"mr":501},{"m":"internvl2.5-38b","r":497,"s":22.35,"lo":355,"hi":540,"n":4,"rr":550,"mr":513},{"m":"internvl2.5-78b","r":498,"s":22.34,"lo":348,"hi":541,"n":4,"rr":547,"mr":514},{"m":"internlm2-math-plus-7b","r":499,"s":22.19,"lo":458,"hi":545,"n":6,"rr":483,"mr":494},{"m":"llava-onevision-72b","r":500,"s":22.19,"lo":407,"hi":549,"n":4,"rr":511,"mr":525},{"m":"llama-3.1-405b-base","r":501,"s":22.16,"lo":414,"hi":533,"n":4,"rr":250,"mr":505},{"m":"qwen3.5-4b-base","r":502,"s":22.1,"lo":408,"hi":548,"n":5,"rr":534,"mr":499},{"m":"qwen2.5-coder-3b-instruct","r":503,"s":21.95,"lo":473,"hi":564,"n":5,"rr":566,"mr":497},{"m":"mathstral-7b","r":504,"s":21.95,"lo":471,"hi":564,"n":6,"rr":487,"mr":495},{"m":"qwen2-7b-instruct","r":505,"s":21.8,"lo":466,"hi":551,"n":6,"rr":463,"mr":498},{"m":"kanana-2-1.3b-instruct","r":506,"s":21.67,"lo":449,"hi":540,"n":3,"rr":510,"mr":503},{"m":"granite-4.0-h-tiny","r":507,"s":21.61,"lo":421,"hi":551,"n":10,"rr":514,"mr":496},{"m":"glm-4-9b-chat","r":508,"s":21.47,"lo":422,"hi":525,"n":3,"rr":314,"mr":507},{"m":"gpt-4v","r":509,"s":21.44,"lo":455,"hi":540,"n":4,"rr":595,"mr":523},{"m":"deepseek-math-7b-instruct","r":510,"s":21.4,"lo":438,"hi":528,"n":3,"rr":263,"mr":489},{"m":"ouro-1.4b","r":511,"s":21.35,"lo":372,"hi":600,"n":3,"rr":383,"mr":517},{"m":"qwen2-math-7b","r":512,"s":21.11,"lo":456,"hi":525,"n":3,"rr":265,"mr":508},{"m":"qwen1.5-72b-chat","r":513,"s":20.97,"lo":436,"hi":537,"n":4,"rr":267,"mr":515},{"m":"glm4-9b","r":514,"s":20.97,"lo":447,"hi":535,"n":3,"rr":427,"mr":509},{"m":"granite-4.0-micro","r":515,"s":20.95,"lo":323,"hi":617,"n":5,"rr":532,"mr":526},{"m":"mixtral-8x22b-instruct-v0.1","r":516,"s":20.92,"lo":385,"hi":545,"n":3,"rr":266,"mr":518},{"m":"hyperclovax-seed-omni-8b","r":517,"s":20.59,"lo":412,"hi":588,"n":4,"rr":513,"mr":528},{"m":"qwen2-vl-72b","r":518,"s":20.51,"lo":344,"hi":550,"n":4,"rr":555,"mr":532},{"m":"qwen2.5-vl-3b","r":519,"s":20.38,"lo":398,"hi":558,"n":3,"rr":496,"mr":539},{"m":"numinamath-7b-cot","r":520,"s":20.31,"lo":484,"hi":561,"n":5,"rr":488,"mr":510},{"m":"llama-3.1-8b","r":521,"s":20.21,"lo":426,"hi":544,"n":3,"rr":291,"mr":529},{"m":"mobilellm-r1.5-360m","r":522,"s":20.2,"lo":465,"hi":586,"n":4,"rr":599,"mr":504},{"m":"internvl3-8b","r":523,"s":20.18,"lo":428,"hi":602,"n":3,"rr":613,"mr":544},{"m":"deepseek-v2-chat","r":524,"s":20.16,"lo":395,"hi":543,"n":5,"rr":420,"mr":500},{"m":"gemma-2-27b","r":525,"s":20.11,"lo":458,"hi":569,"n":3,"rr":482,"mr":520},{"m":"qwen2-7b","r":526,"s":20.09,"lo":482,"hi":551,"n":4,"rr":374,"mr":512},{"m":"qwen2.5-math-1.5b","r":527,"s":20.05,"lo":458,"hi":543,"n":3,"rr":277,"mr":522},{"m":"qwen2-vl-72b-instruct","r":528,"s":19.7,"lo":349,"hi":556,"n":3,"rr":581,"mr":537},{"m":"minicpm-o-2.6","r":529,"s":19.66,"lo":367,"hi":571,"n":4,"rr":564,"mr":546},{"m":"moonlight-instruct","r":530,"s":19.44,"lo":466,"hi":580,"n":4,"rr":601,"mr":511},{"m":"qwen2.5-3b","r":531,"s":19.3,"lo":479,"hi":568,"n":7,"rr":533,"mr":506},{"m":"eurollm-22b","r":532,"s":18.89,"lo":420,"hi":558,"n":4,"rr":355,"mr":527},{"m":"internvl2.5-26b","r":533,"s":18.74,"lo":472,"hi":567,"n":6,"rr":517,"mr":535},{"m":"olmo-2-32b-base","r":534,"s":18.73,"lo":328,"hi":634,"n":4,"rr":408,"mr":541},{"m":"qwen1.5-32b-chat","r":535,"s":18.72,"lo":442,"hi":552,"n":3,"rr":348,"mr":543},{"m":"llama-3.1-70b-base","r":536,"s":18.33,"lo":436,"hi":560,"n":3,"rr":307,"mr":538},{"m":"gpt-4-turbo","r":537,"s":18.31,"lo":309,"hi":566,"n":3,"rr":554,"mr":542},{"m":"llama-3-70b-instruct","r":538,"s":18.11,"lo":354,"hi":565,"n":4,"rr":431,"mr":524},{"m":"mixtral-8x22b","r":539,"s":18,"lo":398,"hi":569,"n":3,"rr":304,"mr":536},{"m":"llama-3.1-8b-instruct","r":540,"s":17.9,"lo":495,"hi":578,"n":10,"rr":561,"mr":530},{"m":"qwen1.5-72b","r":541,"s":17.84,"lo":482,"hi":555,"n":3,"rr":320,"mr":521},{"m":"gemma-2-27b-it","r":542,"s":17.79,"lo":434,"hi":614,"n":5,"rr":603,"mr":531},{"m":"deepseek-v2","r":543,"s":17.71,"lo":484,"hi":554,"n":4,"rr":324,"mr":534},{"m":"llama-3-70b-base","r":544,"s":17.5,"lo":468,"hi":562,"n":3,"rr":327,"mr":540},{"m":"minicpm-v-2_6","r":545,"s":17.49,"lo":426,"hi":585,"n":3,"rr":580,"mr":561},{"m":"falcon-h1-0.5b-instruct","r":546,"s":17.3,"lo":510,"hi":582,"n":5,"rr":592,"mr":533},{"m":"deepseek-llm-67b-chat","r":547,"s":17.2,"lo":456,"hi":573,"n":3,"rr":333,"mr":551},{"m":"apertus-v1.5-8b","r":548,"s":16.87,"lo":494,"hi":558,"n":3,"rr":425,"mr":545},{"m":"qwen2-math-1.5b","r":549,"s":16.86,"lo":485,"hi":567,"n":3,"rr":340,"mr":548},{"m":"olmo-3-7b","r":550,"s":16.53,"lo":410,"hi":580,"n":4,"rr":528,"mr":555},{"m":"llama-3-8b","r":551,"s":16.46,"lo":486,"hi":585,"n":3,"rr":504,"mr":554},{"m":"granite-3.3-2b-instruct","r":552,"s":16.41,"lo":499,"hi":580,"n":3,"rr":530,"mr":550},{"m":"deepseek-math-7b","r":553,"s":16.28,"lo":506,"hi":576,"n":5,"rr":481,"mr":553},{"m":"olmo-2-0325-32b-instruct","r":554,"s":16.23,"lo":497,"hi":623,"n":4,"rr":644,"mr":547},{"m":"llama-3.1-70b","r":555,"s":16.11,"lo":283,"hi":615,"n":4,"rr":436,"mr":559},{"m":"falcon3-3b","r":556,"s":15.69,"lo":522,"hi":590,"n":5,"rr":597,"mr":549},{"m":"apertus-70b","r":557,"s":15.65,"lo":478,"hi":575,"n":4,"rr":465,"mr":562},{"m":"dream-7b-instruct","r":558,"s":15.59,"lo":461,"hi":577,"n":3,"rr":454,"mr":557},{"m":"internvl2-llama-3-76b","r":559,"s":15.58,"lo":388,"hi":587,"n":5,"rr":570,"mr":574},{"m":"granite-4.0-1b","r":560,"s":15.5,"lo":534,"hi":584,"n":3,"rr":556,"mr":552},{"m":"granite-3.2-8b-instruct","r":561,"s":15.5,"lo":477,"hi":586,"n":3,"rr":524,"mr":556},{"m":"internvl2.5-8b","r":562,"s":15.35,"lo":485,"hi":591,"n":6,"rr":544,"mr":570},{"m":"gpt-3.5","r":563,"s":15.21,"lo":490,"hi":578,"n":3,"rr":363,"mr":564},{"m":"mobilemoe-l","r":564,"s":15.09,"lo":487,"hi":584,"n":3,"rr":443,"mr":560},{"m":"gemma-2-9b","r":565,"s":15.06,"lo":511,"hi":601,"n":5,"rr":578,"mr":563},{"m":"qwen2-vl-7b","r":566,"s":14.91,"lo":435,"hi":595,"n":4,"rr":577,"mr":581},{"m":"deepseek-coder-v2-lite-base","r":567,"s":14.9,"lo":493,"hi":580,"n":3,"rr":379,"mr":566},{"m":"aquila-vl-2b","r":568,"s":14.46,"lo":429,"hi":599,"n":3,"rr":583,"mr":585},{"m":"llama-3.2-3b","r":569,"s":14.42,"lo":509,"hi":599,"n":4,"rr":537,"mr":571},{"m":"gemini-pro","r":570,"s":14.41,"lo":432,"hi":587,"n":4,"rr":523,"mr":578},{"m":"qwen2.5-1.5b-instruct","r":571,"s":14.07,"lo":508,"hi":614,"n":5,"rr":576,"mr":558},{"m":"internlm2-20b","r":572,"s":14.04,"lo":352,"hi":585,"n":3,"rr":529,"mr":565},{"m":"granite-3.1-8b-instruct","r":573,"s":13.93,"lo":496,"hi":592,"n":3,"rr":539,"mr":572},{"m":"llama3.0-70b","r":574,"s":13.74,"lo":463,"hi":619,"n":3,"rr":548,"mr":580},{"m":"llama-3.2-3b-base","r":575,"s":13.73,"lo":472,"hi":607,"n":5,"rr":608,"mr":569},{"m":"marin-8b-instruct","r":576,"s":13.5,"lo":470,"hi":591,"n":3,"rr":485,"mr":576},{"m":"internlm2-math-plus-1.8b","r":577,"s":13.49,"lo":290,"hi":602,"n":3,"rr":526,"mr":579},{"m":"metamath-70b","r":578,"s":13.32,"lo":475,"hi":595,"n":3,"rr":401,"mr":567},{"m":"mixtral-8x7b","r":579,"s":13.07,"lo":366,"hi":592,"n":3,"rr":543,"mr":577},{"m":"qwen3-0.8b","r":580,"s":13.05,"lo":539,"hi":610,"n":5,"rr":627,"mr":573},{"m":"llama-3-8b-instruct","r":581,"s":12.97,"lo":477,"hi":594,"n":3,"rr":451,"mr":583},{"m":"internvl2-8b","r":582,"s":12.62,"lo":516,"hi":626,"n":7,"rr":568,"mr":587},{"m":"qwen2.5-1.5b","r":583,"s":12.47,"lo":536,"hi":607,"n":7,"rr":620,"mr":575},{"m":"skywork-13b-math","r":584,"s":12.17,"lo":499,"hi":623,"n":3,"rr":439,"mr":568},{"m":"internvl2-26b","r":585,"s":11.86,"lo":526,"hi":610,"n":7,"rr":571,"mr":590},{"m":"internvl2-40b","r":586,"s":11.57,"lo":463,"hi":609,"n":5,"rr":600,"mr":595},{"m":"internlm2-math-base-20b","r":587,"s":11.44,"lo":522,"hi":599,"n":4,"rr":497,"mr":582},{"m":"llama-3.1-8b-base","r":588,"s":11.36,"lo":544,"hi":618,"n":8,"rr":604,"mr":586},{"m":"wizardmath-70b-v1.0","r":589,"s":11.32,"lo":481,"hi":612,"n":3,"rr":429,"mr":584},{"m":"llama-3.2-3b-instruct","r":590,"s":11.06,"lo":523,"hi":610,"n":5,"rr":535,"mr":591},{"m":"granite-4.0-h-1b","r":591,"s":10.97,"lo":538,"hi":619,"n":3,"rr":563,"mr":593},{"m":"eurollm-9b-instruct-2512","r":592,"s":10.97,"lo":531,"hi":603,"n":3,"rr":540,"mr":588},{"m":"internvl2.5-4b","r":593,"s":10.7,"lo":447,"hi":617,"n":4,"rr":609,"mr":609},{"m":"phi-3.5-vision-instruct","r":594,"s":10.51,"lo":446,"hi":619,"n":3,"rr":615,"mr":616},{"m":"mobilemoe-m","r":595,"s":10.51,"lo":529,"hi":613,"n":3,"rr":521,"mr":592},{"m":"gemma-3-1b-it","r":596,"s":10.29,"lo":544,"hi":621,"n":7,"rr":606,"mr":589},{"m":"deepseek-coder-7b-base-v1.5","r":597,"s":9.94,"lo":336,"hi":607,"n":3,"rr":569,"mr":596},{"m":"qwen3.5-0.8b","r":598,"s":9.79,"lo":514,"hi":629,"n":10,"rr":575,"mr":598},{"m":"olmo-2-1124-7b-instruct","r":599,"s":9.64,"lo":565,"hi":627,"n":4,"rr":649,"mr":597},{"m":"internlm2-7b","r":600,"s":9.62,"lo":371,"hi":622,"n":3,"rr":573,"mr":601},{"m":"deepseek-v2-lite-chat","r":601,"s":9.6,"lo":542,"hi":621,"n":5,"rr":586,"mr":594},{"m":"granite-3.2-2b-instruct","r":602,"s":9.57,"lo":549,"hi":620,"n":3,"rr":585,"mr":602},{"m":"granite-3.1-2b-instruct","r":603,"s":9.57,"lo":549,"hi":619,"n":3,"rr":584,"mr":603},{"m":"lfm2.5-vl-1.6b","r":604,"s":9.31,"lo":490,"hi":629,"n":5,"rr":610,"mr":618},{"m":"apertus-70b-instruct","r":605,"s":9.24,"lo":546,"hi":634,"n":7,"rr":631,"mr":599},{"m":"qwen2.5-0.5b-instruct","r":606,"s":9.03,"lo":570,"hi":637,"n":5,"rr":626,"mr":600},{"m":"qwen2-1.5b-instruct","r":607,"s":8.97,"lo":573,"hi":618,"n":5,"rr":598,"mr":608},{"m":"qwen2-vl-2b","r":608,"s":8.86,"lo":454,"hi":633,"n":3,"rr":618,"mr":628},{"m":"mobilellm-r1-360m","r":609,"s":8.82,"lo":533,"hi":643,"n":3,"rr":621,"mr":606},{"m":"qwen3.5-0.8b-thinking","r":610,"s":8.62,"lo":477,"hi":637,"n":8,"rr":611,"mr":604},{"m":"qwen1.5-7b-chat","r":611,"s":8.53,"lo":520,"hi":625,"n":3,"rr":551,"mr":619},{"m":"deepseek-llm-67b-base","r":612,"s":8.52,"lo":554,"hi":626,"n":3,"rr":500,"mr":607},{"m":"deepseek-llm-7b-chat","r":613,"s":8.44,"lo":535,"hi":628,"n":3,"rr":491,"mr":605},{"m":"qwen2-1.5b","r":614,"s":8.42,"lo":559,"hi":625,"n":3,"rr":516,"mr":612},{"m":"codellama-34b","r":615,"s":8.38,"lo":370,"hi":622,"n":3,"rr":589,"mr":621},{"m":"llama-3.2-1.24b","r":616,"s":8.34,"lo":535,"hi":641,"n":4,"rr":628,"mr":615},{"m":"llama-3.2-1b-instruct","r":617,"s":8.31,"lo":587,"hi":636,"n":4,"rr":643,"mr":620},{"m":"internvl2-4b","r":618,"s":8.28,"lo":480,"hi":640,"n":4,"rr":619,"mr":630},{"m":"llemma-34b","r":619,"s":8.24,"lo":549,"hi":627,"n":4,"rr":560,"mr":610},{"m":"internvl2.5-2b","r":620,"s":8.2,"lo":565,"hi":635,"n":6,"rr":607,"mr":625},{"m":"deepseek-moe-16b-chat","r":621,"s":8.2,"lo":537,"hi":631,"n":3,"rr":498,"mr":611},{"m":"apertus-8b-instruct","r":622,"s":8.06,"lo":576,"hi":634,"n":6,"rr":639,"mr":622},{"m":"internlm2-math-base-7b","r":623,"s":8.05,"lo":331,"hi":629,"n":3,"rr":591,"mr":623},{"m":"olmo-2-0425-1b-instruct","r":624,"s":7.94,"lo":570,"hi":634,"n":6,"rr":629,"mr":617},{"m":"qwen2.5-0.5b","r":625,"s":7.92,"lo":586,"hi":637,"n":7,"rr":647,"mr":613},{"m":"deepseek-v2-lite","r":626,"s":7.86,"lo":547,"hi":634,"n":4,"rr":596,"mr":614},{"m":"smollm2-1.7b-instruct","r":627,"s":7.54,"lo":593,"hi":639,"n":6,"rr":638,"mr":624},{"m":"olmoe-1b-7b","r":628,"s":7.49,"lo":592,"hi":639,"n":6,"rr":640,"mr":627},{"m":"llama-2-70b","r":629,"s":7.28,"lo":559,"hi":639,"n":3,"rr":520,"mr":631},{"m":"falcon3-1b","r":630,"s":7.18,"lo":596,"hi":643,"n":5,"rr":648,"mr":633},{"m":"internvl2.5-1b","r":631,"s":6.94,"lo":523,"hi":638,"n":4,"rr":632,"mr":639},{"m":"wizardmath-13b-v1.0","r":632,"s":6.69,"lo":571,"hi":640,"n":3,"rr":542,"mr":636},{"m":"t5gemma-2-4b-4b","r":633,"s":6.65,"lo":510,"hi":637,"n":3,"rr":582,"mr":635},{"m":"mobilemoe-s","r":634,"s":6.62,"lo":542,"hi":639,"n":3,"rr":593,"mr":634},{"m":"internvl-chat-v1.5","r":635,"s":6.61,"lo":512,"hi":642,"n":4,"rr":624,"mr":642},{"m":"deepseek-vl-7b","r":636,"s":6.08,"lo":419,"hi":642,"n":3,"rr":572,"mr":638},{"m":"llama-3.2-1.24b-base","r":637,"s":5.87,"lo":595,"hi":646,"n":6,"rr":654,"mr":640},{"m":"mistral-7b-v0.1","r":638,"s":5.84,"lo":569,"hi":644,"n":4,"rr":590,"mr":637},{"m":"llemma-7b","r":639,"s":5.72,"lo":560,"hi":645,"n":4,"rr":605,"mr":641},{"m":"llava-1.5-7b","r":640,"s":5.19,"lo":470,"hi":649,"n":3,"rr":641,"mr":644},{"m":"codellama-7b","r":641,"s":4.89,"lo":391,"hi":644,"n":3,"rr":633,"mr":645},{"m":"gemma-2-2b","r":642,"s":4.81,"lo":548,"hi":652,"n":3,"rr":635,"mr":629},{"m":"internvl2-1b","r":643,"s":4.79,"lo":571,"hi":649,"n":4,"rr":642,"mr":648},{"m":"smollm2-1.7b-base","r":644,"s":4.57,"lo":547,"hi":645,"n":3,"rr":646,"mr":626},{"m":"internvl2-2b","r":645,"s":4.23,"lo":588,"hi":648,"n":6,"rr":630,"mr":650},{"m":"mobilellm-p1","r":646,"s":3.27,"lo":545,"hi":648,"n":3,"rr":637,"mr":647},{"m":"baichuan-13b-base","r":647,"s":3.16,"lo":583,"hi":649,"n":3,"rr":617,"mr":646},{"m":"deepseek-llm-7b-base","r":648,"s":2.9,"lo":587,"hi":651,"n":3,"rr":636,"mr":652},{"m":"mobilellm-r1-140m","r":649,"s":2.72,"lo":529,"hi":652,"n":3,"rr":652,"mr":649},{"m":"deepseek-moe-16b-base","r":650,"s":2.7,"lo":589,"hi":652,"n":3,"rr":634,"mr":653},{"m":"llama-2-7b","r":651,"s":2.5,"lo":586,"hi":653,"n":3,"rr":645,"mr":656},{"m":"gemma-3-270m-it","r":652,"s":2.41,"lo":584,"hi":654,"n":4,"rr":651,"mr":654},{"m":"t5gemma-2-1b-1b","r":653,"s":2.05,"lo":497,"hi":655,"n":3,"rr":650,"mr":655},{"m":"smollm2-135m-instruct","r":654,"s":1.45,"lo":527,"hi":656,"n":3,"rr":655,"mr":632},{"m":"smollm2-360m-instruct","r":655,"s":1.42,"lo":590,"hi":655,"n":4,"rr":653,"mr":657},{"m":"smollm2-360m-base","r":656,"s":1.35,"lo":543,"hi":656,"n":3,"rr":656,"mr":643},{"m":"t5gemma-2-270m-270m","r":657,"s":0.94,"lo":493,"hi":657,"n":3,"rr":657,"mr":651}]},"faix-ocr":{"name":"OCR","n":335,"nb":18,"acc":0.8077,"raw_acc":0.6779,"rows":[{"m":"claude-fable-5","r":1,"s":93.22,"lo":1,"hi":99,"n":5,"rr":68,"mr":2},{"m":"qwen3.8-max","r":2,"s":92.7,"lo":1,"hi":74,"n":5,"rr":33,"mr":1},{"m":"gpt-5.6-sol","r":3,"s":91.75,"lo":2,"hi":90,"n":5,"rr":64,"mr":3},{"m":"qwen3.8-flash-next","r":4,"s":90.1,"lo":2,"hi":18,"n":6,"rr":121,"mr":4},{"m":"gemini-3.1-pro","r":5,"s":89.29,"lo":2,"hi":10,"n":9,"rr":81,"mr":6},{"m":"qwen3.8-27b","r":6,"s":89.01,"lo":3,"hi":125,"n":5,"rr":30,"mr":5},{"m":"kimi-k3","r":7,"s":88.9,"lo":3,"hi":152,"n":3,"rr":7,"mr":7},{"m":"claude-mythos-5","r":8,"s":88.9,"lo":1,"hi":61,"n":3,"rr":53,"mr":8},{"m":"claude-opus-4.8","r":9,"s":88.57,"lo":4,"hi":39,"n":7,"rr":128,"mr":9},{"m":"seed2.1-pro","r":10,"s":87.93,"lo":3,"hi":13,"n":4,"rr":31,"mr":10},{"m":"qwen3.7-plus","r":11,"s":87.63,"lo":6,"hi":55,"n":4,"rr":95,"mr":11},{"m":"gpt-5.5","r":12,"s":87.4,"lo":5,"hi":22,"n":6,"rr":40,"mr":12},{"m":"gpt-5.4","r":13,"s":86.87,"lo":9,"hi":47,"n":6,"rr":83,"mr":13},{"m":"seed2.1-turbo","r":14,"s":86.69,"lo":6,"hi":16,"n":4,"rr":37,"mr":14},{"m":"gemini-3-flash","r":15,"s":86.47,"lo":3,"hi":25,"n":6,"rr":82,"mr":15},{"m":"seed2.0-lite-0428","r":16,"s":86.37,"lo":9,"hi":24,"n":3,"rr":11,"mr":17},{"m":"qwen3.6-plus","r":17,"s":86.27,"lo":11,"hi":26,"n":7,"rr":112,"mr":16},{"m":"qwen3.5-397b-a17b","r":18,"s":86.2,"lo":8,"hi":20,"n":7,"rr":65,"mr":18},{"m":"qwen3.5-122b-a10b","r":19,"s":85.95,"lo":6,"hi":22,"n":9,"rr":102,"mr":19},{"m":"seed2.0-pro","r":20,"s":85.53,"lo":15,"hi":30,"n":3,"rr":19,"mr":21},{"m":"gemini-3-pro","r":21,"s":85.21,"lo":5,"hi":33,"n":15,"rr":54,"mr":20},{"m":"seed2.0-lite","r":22,"s":84.79,"lo":19,"hi":35,"n":3,"rr":29,"mr":22},{"m":"qwen3.5-27b","r":23,"s":84.71,"lo":19,"hi":33,"n":7,"rr":84,"mr":24},{"m":"kimi-k2.5-thinking","r":24,"s":84.65,"lo":12,"hi":33,"n":5,"rr":23,"mr":23},{"m":"glm-5.3-flash","r":25,"s":84.55,"lo":12,"hi":36,"n":6,"rr":195,"mr":25},{"m":"claude-opus-4.7","r":26,"s":84.5,"lo":16,"hi":31,"n":5,"rr":47,"mr":26},{"m":"qwen3.5-35b-a3b","r":27,"s":84.04,"lo":23,"hi":42,"n":6,"rr":72,"mr":28},{"m":"kimi-k2.5","r":28,"s":83.98,"lo":23,"hi":46,"n":8,"rr":129,"mr":27},{"m":"qwen3.6-27b","r":29,"s":83.85,"lo":23,"hi":82,"n":5,"rr":41,"mr":30},{"m":"nemotron-3.5-super-vl-120b-a12b","r":30,"s":83.84,"lo":11,"hi":42,"n":6,"rr":194,"mr":29},{"m":"o3-high","r":31,"s":83.44,"lo":11,"hi":61,"n":3,"rr":99,"mr":33},{"m":"gemma-4-31b-it","r":32,"s":83.34,"lo":20,"hi":75,"n":7,"rr":67,"mr":31},{"m":"qwen3.6-35b-a3b","r":33,"s":83.24,"lo":26,"hi":40,"n":7,"rr":57,"mr":32},{"m":"gpt-5.2-thinking-xhigh","r":34,"s":82.68,"lo":28,"hi":136,"n":5,"rr":45,"mr":34},{"m":"o4-mini-high","r":35,"s":82.17,"lo":14,"hi":67,"n":3,"rr":125,"mr":42},{"m":"gpt-5-high","r":36,"s":82.03,"lo":19,"hi":52,"n":7,"rr":46,"mr":36},{"m":"inkling-small","r":37,"s":81.97,"lo":33,"hi":85,"n":6,"rr":264,"mr":40},{"m":"gemini-2.5-pro","r":38,"s":81.84,"lo":14,"hi":53,"n":17,"rr":104,"mr":35},{"m":"nemotron-3.5-super-vl-120b-a12b-nvfp4","r":39,"s":81.8,"lo":18,"hi":57,"n":6,"rr":226,"mr":39},{"m":"gemma-4-26b-a4b-it","r":40,"s":81.75,"lo":26,"hi":104,"n":6,"rr":173,"mr":43},{"m":"seed1.8","r":41,"s":81.73,"lo":32,"hi":120,"n":3,"rr":77,"mr":45},{"m":"gpt-5.4-mini","r":42,"s":81.65,"lo":28,"hi":159,"n":3,"rr":178,"mr":52},{"m":"ovis2.6-80b-a3b","r":43,"s":81.62,"lo":14,"hi":66,"n":11,"rr":101,"mr":37},{"m":"minicpm-v-4.7-35b-a3b","r":44,"s":81.57,"lo":37,"hi":68,"n":5,"rr":61,"mr":41},{"m":"qwen3.5-omni-plus","r":45,"s":81.46,"lo":33,"hi":58,"n":6,"rr":100,"mr":46},{"m":"qwen3-vl-235b-a22b-thinking","r":46,"s":81.41,"lo":16,"hi":54,"n":14,"rr":93,"mr":38},{"m":"ovis2.6-30b-a3b","r":47,"s":81.31,"lo":16,"hi":60,"n":12,"rr":91,"mr":44},{"m":"comet-60b-a12b","r":48,"s":80.82,"lo":27,"hi":68,"n":6,"rr":246,"mr":48},{"m":"qwen3.5-9b","r":49,"s":80.78,"lo":37,"hi":60,"n":11,"rr":78,"mr":47},{"m":"gemini-3.1-flash-lite","r":50,"s":80.77,"lo":29,"hi":70,"n":3,"rr":180,"mr":53},{"m":"comet-60b-a12b-fp8","r":51,"s":80.65,"lo":33,"hi":67,"n":6,"rr":247,"mr":49},{"m":"claude-opus-4.5","r":52,"s":80.55,"lo":36,"hi":71,"n":7,"rr":143,"mr":51},{"m":"intern-s1-pro","r":53,"s":80.46,"lo":37,"hi":74,"n":4,"rr":240,"mr":56},{"m":"comet-60b-a12b-nvfp4","r":54,"s":80.41,"lo":34,"hi":70,"n":6,"rr":248,"mr":50},{"m":"claude-opus-4.6","r":55,"s":80.4,"lo":40,"hi":130,"n":4,"rr":239,"mr":54},{"m":"qwen3-vl-235b-a22b","r":56,"s":80.04,"lo":45,"hi":81,"n":7,"rr":103,"mr":57},{"m":"exaone-4.5-33b-thinking","r":57,"s":80.02,"lo":44,"hi":166,"n":5,"rr":162,"mr":60},{"m":"gpt-5-mini-high","r":58,"s":79.63,"lo":37,"hi":85,"n":6,"rr":205,"mr":63},{"m":"seed1.5-vl-thinking","r":59,"s":79.57,"lo":27,"hi":73,"n":10,"rr":88,"mr":58},{"m":"glm-4.6v","r":60,"s":79.53,"lo":33,"hi":73,"n":13,"rr":141,"mr":55},{"m":"ernie-5.0","r":61,"s":79.38,"lo":38,"hi":72,"n":6,"rr":35,"mr":62},{"m":"dots-vlm1","r":62,"s":79.37,"lo":23,"hi":85,"n":8,"rr":71,"mr":59},{"m":"claude-3.7-sonnet-thinking","r":63,"s":79.24,"lo":24,"hi":136,"n":5,"rr":164,"mr":70},{"m":"qianfan-ocr","r":64,"s":79.22,"lo":21,"hi":126,"n":10,"rr":109,"mr":65},{"m":"claude-opus-4.5-thinking","r":65,"s":79.13,"lo":42,"hi":142,"n":5,"rr":86,"mr":68},{"m":"qwen3-vl-32b-instruct","r":66,"s":79.01,"lo":38,"hi":77,"n":12,"rr":111,"mr":61},{"m":"nemotron-3-nano-omni-30b-a3b-reasoning","r":67,"s":78.83,"lo":39,"hi":95,"n":4,"rr":269,"mr":74},{"m":"ovisocr3","r":68,"s":78.65,"lo":44,"hi":113,"n":3,"rr":165,"mr":71},{"m":"qwen3.5-4b","r":69,"s":78.64,"lo":51,"hi":88,"n":12,"rr":117,"mr":64},{"m":"gpt-5.2","r":70,"s":78.54,"lo":28,"hi":143,"n":12,"rr":107,"mr":67},{"m":"glm-4.5v","r":71,"s":78.46,"lo":43,"hi":80,"n":8,"rr":188,"mr":69},{"m":"gpt-5-mini","r":72,"s":78.39,"lo":44,"hi":112,"n":15,"rr":160,"mr":66},{"m":"qwen3.5-omni-flash","r":73,"s":78.28,"lo":58,"hi":88,"n":6,"rr":148,"mr":72},{"m":"step3-vl-10b","r":74,"s":78.16,"lo":61,"hi":118,"n":3,"rr":52,"mr":76},{"m":"qwen3-vl-32b-thinking","r":75,"s":77.9,"lo":58,"hi":103,"n":6,"rr":133,"mr":73},{"m":"claude-sonnet-4.6","r":76,"s":77.74,"lo":59,"hi":177,"n":4,"rr":174,"mr":86},{"m":"infinity-parser2-pro","r":77,"s":77.1,"lo":54,"hi":103,"n":5,"rr":10,"mr":81},{"m":"claude-4.5-haiku","r":78,"s":77.02,"lo":72,"hi":101,"n":3,"rr":274,"mr":87},{"m":"ming-flash-omni-2.0","r":79,"s":76.95,"lo":70,"hi":106,"n":4,"rr":49,"mr":84},{"m":"longcat-next","r":80,"s":76.79,"lo":59,"hi":90,"n":9,"rr":122,"mr":75},{"m":"glm-4.6v-flash","r":81,"s":76.67,"lo":48,"hi":99,"n":9,"rr":245,"mr":82},{"m":"qwen3-vl-30b-a3b-instruct","r":82,"s":76.55,"lo":55,"hi":98,"n":16,"rr":167,"mr":77},{"m":"pelican-vl-72b","r":83,"s":76.47,"lo":58,"hi":129,"n":4,"rr":5,"mr":93},{"m":"gpt-5","r":84,"s":76.42,"lo":50,"hi":154,"n":12,"rr":147,"mr":78},{"m":"gpt-4.1-mini","r":85,"s":76.4,"lo":56,"hi":107,"n":3,"rr":228,"mr":89},{"m":"ernie-4.5-vl-28b-a3b-thinking","r":86,"s":76.36,"lo":41,"hi":105,"n":6,"rr":74,"mr":83},{"m":"mimo-vl-7b-rl","r":87,"s":76.32,"lo":53,"hi":108,"n":8,"rr":66,"mr":79},{"m":"claude-3.7-sonnet","r":88,"s":76.05,"lo":55,"hi":182,"n":9,"rr":120,"mr":80},{"m":"apriel-1.6-15b-thinker","r":89,"s":76.01,"lo":63,"hi":125,"n":4,"rr":152,"mr":88},{"m":"mimo-vl-7b-sft","r":90,"s":75.83,"lo":53,"hi":112,"n":8,"rr":75,"mr":85},{"m":"gpt-4.1","r":91,"s":75.59,"lo":65,"hi":112,"n":3,"rr":242,"mr":97},{"m":"mimo-vl-7b-rl-2508","r":92,"s":75.56,"lo":77,"hi":150,"n":4,"rr":70,"mr":94},{"m":"rynnbrain-30b-a3b","r":93,"s":75.55,"lo":66,"hi":127,"n":4,"rr":9,"mr":100},{"m":"claude-opus-4.1","r":94,"s":75.38,"lo":76,"hi":165,"n":10,"rr":232,"mr":91},{"m":"o1","r":95,"s":75.22,"lo":77,"hi":121,"n":3,"rr":220,"mr":95},{"m":"qwen2.5-vl-72b-instruct","r":96,"s":74.96,"lo":50,"hi":142,"n":12,"rr":200,"mr":92},{"m":"qwen3-vl-8b-instruct","r":97,"s":74.92,"lo":67,"hi":123,"n":14,"rr":169,"mr":90},{"m":"openpangu-vl-7b","r":98,"s":74.92,"lo":62,"hi":127,"n":7,"rr":42,"mr":99},{"m":"glm-4.1v","r":99,"s":74.84,"lo":69,"hi":119,"n":6,"rr":249,"mr":103},{"m":"mistral-small-3.2-24b-instruct","r":100,"s":74.8,"lo":62,"hi":125,"n":3,"rr":1,"mr":109},{"m":"rynnbrain-8b","r":101,"s":74.71,"lo":76,"hi":140,"n":4,"rr":15,"mr":106},{"m":"gemini-2.5-flash","r":102,"s":74.43,"lo":83,"hi":122,"n":9,"rr":110,"mr":101},{"m":"plm-8b","r":103,"s":74.41,"lo":64,"hi":127,"n":4,"rr":8,"mr":112},{"m":"gemini-2.5-flash-lite","r":104,"s":74.31,"lo":80,"hi":137,"n":12,"rr":179,"mr":98},{"m":"claude-3.5-sonnet","r":105,"s":74.16,"lo":63,"hi":155,"n":9,"rr":140,"mr":96},{"m":"step-3","r":106,"s":74.16,"lo":77,"hi":165,"n":6,"rr":276,"mr":113},{"m":"qwen2-vl-72b-instruct","r":107,"s":74.08,"lo":60,"hi":211,"n":7,"rr":80,"mr":104},{"m":"gpt-4.5","r":108,"s":73.86,"lo":50,"hi":144,"n":3,"rr":243,"mr":117},{"m":"molmopoint-8b","r":109,"s":73.73,"lo":15,"hi":139,"n":4,"rr":3,"mr":125},{"m":"minicpm-o-4.5","r":110,"s":73.65,"lo":89,"hi":135,"n":4,"rr":12,"mr":121},{"m":"minicpm-v-4.5-8b","r":111,"s":73.62,"lo":81,"hi":137,"n":5,"rr":18,"mr":118},{"m":"qwen3-omni-30b-a3b-instruct","r":112,"s":73.61,"lo":84,"hi":137,"n":11,"rr":134,"mr":102},{"m":"mistral-medium-3","r":113,"s":73.54,"lo":53,"hi":170,"n":3,"rr":4,"mr":129},{"m":"claude-3.5-sonnet-20240620","r":114,"s":73.51,"lo":75,"hi":155,"n":8,"rr":59,"mr":105},{"m":"claude-sonnet-4.5","r":115,"s":73.39,"lo":54,"hi":226,"n":9,"rr":115,"mr":111},{"m":"manzano-30b","r":116,"s":73.28,"lo":94,"hi":132,"n":6,"rr":24,"mr":116},{"m":"hunyuanocr-1.5","r":117,"s":73.22,"lo":92,"hi":153,"n":3,"rr":235,"mr":132},{"m":"mistral-small-3.1-24b-instruct","r":118,"s":73.11,"lo":50,"hi":141,"n":3,"rr":2,"mr":130},{"m":"qwen3-vl-8b-thinking","r":119,"s":73.07,"lo":96,"hi":172,"n":7,"rr":137,"mr":114},{"m":"apriel-1.5-15b-thinker","r":120,"s":73.01,"lo":82,"hi":162,"n":4,"rr":208,"mr":123},{"m":"keye-vl-1.5-8b","r":121,"s":72.98,"lo":61,"hi":148,"n":5,"rr":16,"mr":128},{"m":"internvl3.5-30b-a3b-flash","r":122,"s":72.85,"lo":98,"hi":133,"n":9,"rr":183,"mr":107},{"m":"qwen2.5-vl-72b","r":123,"s":72.78,"lo":68,"hi":153,"n":9,"rr":151,"mr":120},{"m":"penguin-vl-8b","r":124,"s":72.7,"lo":70,"hi":166,"n":7,"rr":79,"mr":127},{"m":"doubao-1.5-vision-pro","r":125,"s":72.65,"lo":100,"hi":139,"n":3,"rr":255,"mr":124},{"m":"molmo2-8b","r":126,"s":72.65,"lo":23,"hi":153,"n":4,"rr":6,"mr":133},{"m":"claude-sonnet-4","r":127,"s":72.48,"lo":92,"hi":244,"n":12,"rr":287,"mr":115},{"m":"qwen3-vl-4b-instruct","r":128,"s":72.46,"lo":97,"hi":138,"n":15,"rr":212,"mr":108},{"m":"rynnbrain-4b","r":129,"s":72.22,"lo":101,"hi":164,"n":4,"rr":26,"mr":134},{"m":"pixtral-large-2411","r":130,"s":72.22,"lo":61,"hi":152,"n":4,"rr":96,"mr":136},{"m":"qwen2-vl-72b","r":131,"s":72.18,"lo":72,"hi":195,"n":9,"rr":127,"mr":110},{"m":"plm-3b","r":132,"s":72.14,"lo":91,"hi":151,"n":4,"rr":17,"mr":138},{"m":"gemma-4-12b-it","r":133,"s":71.6,"lo":44,"hi":225,"n":8,"rr":150,"mr":126},{"m":"pelican-vl-7b","r":134,"s":71.54,"lo":113,"hi":168,"n":4,"rr":27,"mr":139},{"m":"gpt-4o","r":135,"s":71.53,"lo":91,"hi":178,"n":12,"rr":159,"mr":119},{"m":"gemini-2.0-pro","r":136,"s":71.46,"lo":118,"hi":172,"n":3,"rr":154,"mr":141},{"m":"qwen3-omni-30b-a3b-thinking","r":137,"s":71.45,"lo":115,"hi":156,"n":4,"rr":25,"mr":145},{"m":"glm-4.1v-9b-thinking","r":138,"s":71.24,"lo":116,"hi":191,"n":5,"rr":113,"mr":140},{"m":"internvl2.5-78b","r":139,"s":71.23,"lo":85,"hi":173,"n":9,"rr":126,"mr":122},{"m":"eagle2.5-8b","r":140,"s":71.12,"lo":118,"hi":165,"n":4,"rr":21,"mr":149},{"m":"minicpm-o-4.5-thinking","r":141,"s":70.99,"lo":97,"hi":168,"n":4,"rr":22,"mr":157},{"m":"internvl2-pro","r":142,"s":70.68,"lo":104,"hi":167,"n":7,"rr":87,"mr":135},{"m":"kimi-vl-a3b-thinking-2506","r":143,"s":70.67,"lo":106,"hi":214,"n":7,"rr":302,"mr":147},{"m":"internvl3-78b","r":144,"s":70.56,"lo":108,"hi":166,"n":4,"rr":306,"mr":144},{"m":"qwen3-vl-4b-thinking","r":145,"s":70.28,"lo":134,"hi":170,"n":6,"rr":263,"mr":156},{"m":"internvl2.5-38b","r":146,"s":70.27,"lo":99,"hi":179,"n":9,"rr":132,"mr":131},{"m":"gpt-4o-0513","r":147,"s":70.26,"lo":51,"hi":184,"n":4,"rr":20,"mr":159},{"m":"internvl3.5-gpt-oss-20b-a4b","r":148,"s":70.24,"lo":123,"hi":163,"n":6,"rr":36,"mr":148},{"m":"mimo-embodied-7b","r":149,"s":70.13,"lo":113,"hi":195,"n":6,"rr":90,"mr":146},{"m":"cosmos-reason2-8b","r":150,"s":70.04,"lo":105,"hi":176,"n":6,"rr":97,"mr":153},{"m":"qwen3.5-2b","r":151,"s":70.01,"lo":121,"hi":175,"n":12,"rr":177,"mr":137},{"m":"youtu-vl-4b-instruct","r":152,"s":69.69,"lo":132,"hi":167,"n":8,"rr":94,"mr":143},{"m":"molmo-72b","r":153,"s":69.66,"lo":95,"hi":184,"n":7,"rr":85,"mr":150},{"m":"gemini-2.5-flash-thinking","r":154,"s":69.63,"lo":118,"hi":191,"n":4,"rr":34,"mr":167},{"m":"manzano-3b","r":155,"s":69.6,"lo":129,"hi":185,"n":6,"rr":38,"mr":158},{"m":"mage-vl","r":156,"s":69.47,"lo":117,"hi":190,"n":6,"rr":130,"mr":161},{"m":"internvl3.5-8b","r":157,"s":69.28,"lo":132,"hi":183,"n":10,"rr":176,"mr":142},{"m":"molmo2-o-7b","r":158,"s":69.2,"lo":56,"hi":196,"n":4,"rr":13,"mr":172},{"m":"molmopoint-o-7b","r":159,"s":69.2,"lo":57,"hi":197,"n":4,"rr":14,"mr":173},{"m":"deepseek-vl2","r":160,"s":69,"lo":137,"hi":188,"n":6,"rr":39,"mr":162},{"m":"aria","r":161,"s":68.99,"lo":142,"hi":173,"n":3,"rr":28,"mr":174},{"m":"gpt-5-mini-minimal","r":162,"s":68.89,"lo":145,"hi":191,"n":10,"rr":203,"mr":152},{"m":"glm-4v-plus","r":163,"s":68.77,"lo":121,"hi":181,"n":5,"rr":32,"mr":171},{"m":"internvl3-38b","r":164,"s":68.64,"lo":99,"hi":196,"n":4,"rr":308,"mr":169},{"m":"internvl3-14b","r":165,"s":68.63,"lo":115,"hi":188,"n":3,"rr":299,"mr":168},{"m":"gpt-4o-2024-05-13","r":166,"s":68.41,"lo":114,"hi":197,"n":9,"rr":146,"mr":154},{"m":"gpt-5-minimal","r":167,"s":68.34,"lo":137,"hi":211,"n":10,"rr":230,"mr":151},{"m":"internvl2-llama-3-76b","r":168,"s":68.33,"lo":118,"hi":214,"n":9,"rr":153,"mr":155},{"m":"xiaomi-ocr-0","r":169,"s":68.16,"lo":136,"hi":215,"n":3,"rr":288,"mr":177},{"m":"dots.mocr","r":170,"s":68.07,"lo":135,"hi":205,"n":9,"rr":157,"mr":164},{"m":"glm-ocr","r":171,"s":67.82,"lo":130,"hi":252,"n":4,"rr":268,"mr":191},{"m":"infinity-parser2-flash","r":172,"s":67.64,"lo":150,"hi":212,"n":5,"rr":43,"mr":178},{"m":"gemini-1.5-pro","r":173,"s":67.63,"lo":130,"hi":229,"n":10,"rr":198,"mr":160},{"m":"deepseek-vl2-small","r":174,"s":67.61,"lo":148,"hi":198,"n":6,"rr":44,"mr":175},{"m":"qwen2.5-vl-7b","r":175,"s":67.5,"lo":114,"hi":223,"n":10,"rr":213,"mr":166},{"m":"glm-4.1v-9b","r":176,"s":67.42,"lo":134,"hi":260,"n":4,"rr":50,"mr":188},{"m":"qwen2-vl-7b-instruct","r":177,"s":67.33,"lo":131,"hi":270,"n":7,"rr":135,"mr":176},{"m":"minicpm-v-4.7-1b","r":178,"s":67.31,"lo":130,"hi":212,"n":4,"rr":267,"mr":170},{"m":"internvl3.5-4b","r":179,"s":67.2,"lo":166,"hi":196,"n":10,"rr":184,"mr":163},{"m":"nemotron-nano-12b-v2-vl","r":180,"s":67.04,"lo":138,"hi":201,"n":4,"rr":325,"mr":192},{"m":"internvl2.5-26b","r":181,"s":66.9,"lo":135,"hi":228,"n":9,"rr":166,"mr":165},{"m":"molmo2-4b","r":182,"s":66.83,"lo":78,"hi":252,"n":6,"rr":51,"mr":184},{"m":"zaya1-vl-8b","r":183,"s":66.62,"lo":159,"hi":201,"n":6,"rr":58,"mr":181},{"m":"robobrain-2.0-7b","r":184,"s":66.61,"lo":154,"hi":268,"n":4,"rr":73,"mr":196},{"m":"gemini-1.0-ultra","r":185,"s":66.22,"lo":136,"hi":218,"n":5,"rr":48,"mr":189},{"m":"internvl-8b","r":186,"s":66.21,"lo":145,"hi":208,"n":7,"rr":119,"mr":180},{"m":"fastvlm-7b","r":187,"s":66.14,"lo":162,"hi":219,"n":6,"rr":69,"mr":187},{"m":"penguin-vl-2b","r":188,"s":65.97,"lo":153,"hi":221,"n":7,"rr":139,"mr":183},{"m":"nvlm-d-72b","r":189,"s":65.79,"lo":145,"hi":220,"n":7,"rr":124,"mr":185},{"m":"kanana-1.5-o-9.8b-instruct-2602","r":190,"s":65.71,"lo":145,"hi":214,"n":3,"rr":237,"mr":198},{"m":"gemini-1.5-flash","r":191,"s":65.52,"lo":135,"hi":220,"n":6,"rr":201,"mr":190},{"m":"grok-4-fast-thinking","r":192,"s":65.51,"lo":142,"hi":231,"n":4,"rr":285,"mr":200},{"m":"minicpm-v-4.6","r":193,"s":65.46,"lo":171,"hi":216,"n":8,"rr":252,"mr":179},{"m":"minicpm-v-4.6-thinking","r":194,"s":65.43,"lo":153,"hi":248,"n":6,"rr":256,"mr":197},{"m":"llama-3.2v-90b-instruct","r":195,"s":65.39,"lo":112,"hi":213,"n":6,"rr":123,"mr":194},{"m":"lfm2.5-vl-3b","r":196,"s":65.2,"lo":161,"hi":213,"n":5,"rr":136,"mr":203},{"m":"rynnbrain-2b","r":197,"s":65.18,"lo":166,"hi":231,"n":4,"rr":62,"mr":206},{"m":"kimi-vl-a3b-thinking","r":198,"s":64.93,"lo":175,"hi":241,"n":4,"rr":210,"mr":207},{"m":"internvl2-40b","r":199,"s":64.86,"lo":139,"hi":259,"n":9,"rr":187,"mr":182},{"m":"gpt-4o-mini","r":200,"s":64.62,"lo":172,"hi":228,"n":3,"rr":254,"mr":210},{"m":"gemma-3-27b-vl","r":201,"s":64.48,"lo":171,"hi":244,"n":6,"rr":316,"mr":212},{"m":"qwen3-vl-2b-thinking","r":202,"s":64.47,"lo":186,"hi":225,"n":6,"rr":297,"mr":208},{"m":"qwen3-vl-2b-instruct","r":203,"s":64.39,"lo":180,"hi":238,"n":15,"rr":281,"mr":186},{"m":"internvl3-8b","r":204,"s":64.35,"lo":188,"hi":221,"n":4,"rr":324,"mr":201},{"m":"cogvlm2-llama3-chat-19b","r":205,"s":64.07,"lo":157,"hi":256,"n":5,"rr":63,"mr":219},{"m":"qwen3.5-ocr","r":206,"s":63.93,"lo":181,"hi":222,"n":3,"rr":295,"mr":232},{"m":"llava-onevision-72b","r":207,"s":63.9,"lo":185,"hi":226,"n":9,"rr":191,"mr":193},{"m":"kimi-vl-a3b-instruct","r":208,"s":63.89,"lo":116,"hi":248,"n":4,"rr":186,"mr":221},{"m":"internvl3-9b","r":209,"s":63.82,"lo":187,"hi":227,"n":3,"rr":318,"mr":209},{"m":"qwen2.5-omni-7b","r":210,"s":63.65,"lo":132,"hi":266,"n":8,"rr":170,"mr":204},{"m":"robobrain-2.0","r":211,"s":63.56,"lo":173,"hi":285,"n":4,"rr":89,"mr":223},{"m":"internvl2.5-8b","r":212,"s":63.55,"lo":178,"hi":245,"n":9,"rr":193,"mr":195},{"m":"pixtral-12b","r":213,"s":63.5,"lo":153,"hi":270,"n":7,"rr":168,"mr":205},{"m":"gpt-4v","r":214,"s":63.05,"lo":167,"hi":241,"n":9,"rr":199,"mr":199},{"m":"bagel-7b-mot","r":215,"s":63.04,"lo":132,"hi":262,"n":6,"rr":114,"mr":217},{"m":"lfm2-vl-3b","r":216,"s":63,"lo":182,"hi":235,"n":5,"rr":156,"mr":229},{"m":"claude-3-sonnet","r":217,"s":62.97,"lo":173,"hi":247,"n":6,"rr":171,"mr":214},{"m":"internvl2-26b","r":218,"s":62.78,"lo":179,"hi":260,"n":9,"rr":202,"mr":202},{"m":"llada-o","r":219,"s":62.55,"lo":188,"hi":275,"n":6,"rr":118,"mr":227},{"m":"phi-4-multimodal-instruct","r":220,"s":62.42,"lo":175,"hi":311,"n":7,"rr":251,"mr":231},{"m":"jina-vlm-2.4b-20251117","r":221,"s":62.34,"lo":200,"hi":237,"n":8,"rr":158,"mr":215},{"m":"llada2.0-uni","r":222,"s":62.26,"lo":209,"hi":232,"n":6,"rr":106,"mr":226},{"m":"internlm-xcomposer2.5","r":223,"s":62.18,"lo":200,"hi":244,"n":6,"rr":92,"mr":230},{"m":"qwen2-vl-7b","r":224,"s":62.08,"lo":160,"hi":272,"n":10,"rr":236,"mr":211},{"m":"cogvlm2-llama3-chinese-chat-19b","r":225,"s":61.98,"lo":165,"hi":246,"n":4,"rr":60,"mr":241},{"m":"gemma-3-27b-it","r":226,"s":61.9,"lo":173,"hi":249,"n":8,"rr":216,"mr":213},{"m":"internvl3.5-2b","r":227,"s":61.87,"lo":204,"hi":242,"n":9,"rr":192,"mr":216},{"m":"minicpm-v-2_6","r":228,"s":61.58,"lo":203,"hi":248,"n":8,"rr":215,"mr":220},{"m":"qwen2.5-vl-3b","r":229,"s":61.4,"lo":191,"hi":260,"n":10,"rr":250,"mr":218},{"m":"mm1.5-30b","r":230,"s":61.39,"lo":201,"hi":261,"n":6,"rr":108,"mr":237},{"m":"llama-3.2v-11b-instruct","r":231,"s":61.15,"lo":141,"hi":253,"n":6,"rr":163,"mr":236},{"m":"deepseek-vl2-tiny","r":232,"s":61.11,"lo":190,"hi":260,"n":6,"rr":98,"mr":240},{"m":"ovis1.6-gemma2-9b","r":233,"s":60.97,"lo":161,"hi":262,"n":3,"rr":261,"mr":245},{"m":"molmo-7b-d","r":234,"s":60.89,"lo":154,"hi":271,"n":8,"rr":172,"mr":234},{"m":"grok-1.5v","r":235,"s":60.73,"lo":140,"hi":264,"n":4,"rr":55,"mr":253},{"m":"internvl2.5-4b","r":236,"s":60.72,"lo":205,"hi":265,"n":9,"rr":225,"mr":225},{"m":"north-micro-vision-instruct","r":237,"s":60.57,"lo":205,"hi":261,"n":7,"rr":182,"mr":238},{"m":"qwen3.5-0.8b-thinking","r":238,"s":60.51,"lo":205,"hi":279,"n":6,"rr":277,"mr":246},{"m":"claude-3-opus","r":239,"s":60.48,"lo":212,"hi":271,"n":9,"rr":241,"mr":222},{"m":"internvl2-8b","r":240,"s":60.47,"lo":204,"hi":266,"n":9,"rr":227,"mr":228},{"m":"gemma-4-e4b-it","r":241,"s":60.18,"lo":119,"hi":277,"n":8,"rr":229,"mr":235},{"m":"ministral-3-3b-instruct","r":242,"s":60.12,"lo":193,"hi":276,"n":7,"rr":181,"mr":244},{"m":"gpt-4-turbo-2024-04-09","r":243,"s":60.01,"lo":126,"hi":267,"n":4,"rr":76,"mr":255},{"m":"gpt-5-nano","r":244,"s":59.99,"lo":150,"hi":287,"n":10,"rr":275,"mr":224},{"m":"claude-3-haiku","r":245,"s":59.85,"lo":204,"hi":266,"n":7,"rr":189,"mr":243},{"m":"hyperclovax-seed-omni-8b","r":246,"s":59.84,"lo":214,"hi":265,"n":5,"rr":222,"mr":249},{"m":"qwen3.5-0.8b","r":247,"s":59.67,"lo":210,"hi":280,"n":10,"rr":298,"mr":239},{"m":"llava-next-110b","r":248,"s":59.46,"lo":206,"hi":264,"n":3,"rr":56,"mr":260},{"m":"bagel-14b","r":249,"s":59.32,"lo":170,"hi":288,"n":6,"rr":116,"mr":257},{"m":"baichuan-omni","r":250,"s":59.3,"lo":198,"hi":268,"n":3,"rr":138,"mr":271},{"m":"molmo-7b-o","r":251,"s":59.26,"lo":157,"hi":287,"n":7,"rr":196,"mr":250},{"m":"minicpm-o-2.6","r":252,"s":59.05,"lo":195,"hi":273,"n":4,"rr":310,"mr":251},{"m":"internvl-chat-v1.5","r":253,"s":58.73,"lo":218,"hi":283,"n":9,"rr":234,"mr":242},{"m":"gemma-4-e2b-it","r":254,"s":58.65,"lo":167,"hi":289,"n":11,"rr":289,"mr":233},{"m":"llm-jp-4-vl-9b-beta","r":255,"s":58.44,"lo":226,"hi":278,"n":8,"rr":282,"mr":252},{"m":"gpt-4-1106-vision-preview","r":256,"s":58.36,"lo":204,"hi":274,"n":4,"rr":105,"mr":269},{"m":"gemma-3-12b-it","r":257,"s":58.09,"lo":200,"hi":284,"n":3,"rr":233,"mr":276},{"m":"llm-jp-4-vl-9b","r":258,"s":58.05,"lo":219,"hi":285,"n":8,"rr":280,"mr":254},{"m":"internvl3-2b","r":259,"s":57.78,"lo":238,"hi":285,"n":10,"rr":279,"mr":247},{"m":"internlm-xcomposer2-4khd-7b","r":260,"s":57.71,"lo":234,"hi":277,"n":8,"rr":207,"mr":248},{"m":"internvl-u","r":261,"s":57.4,"lo":218,"hi":281,"n":6,"rr":144,"mr":265},{"m":"gemini-pro","r":262,"s":57.07,"lo":235,"hi":284,"n":7,"rr":214,"mr":261},{"m":"fastvlm-1.5b","r":263,"s":57,"lo":241,"hi":279,"n":6,"rr":142,"mr":273},{"m":"vita","r":264,"s":56.75,"lo":215,"hi":280,"n":3,"rr":161,"mr":280},{"m":"glm-4v-9b","r":265,"s":56.59,"lo":227,"hi":281,"n":7,"rr":197,"mr":266},{"m":"llava-onevision-7b","r":266,"s":56.56,"lo":226,"hi":286,"n":7,"rr":218,"mr":264},{"m":"qwen2-vl-2b-instruct","r":267,"s":56.54,"lo":225,"hi":295,"n":7,"rr":206,"mr":267},{"m":"qwen-vl-max","r":268,"s":56.48,"lo":226,"hi":294,"n":9,"rr":259,"mr":256},{"m":"internvl2-4b","r":269,"s":56.39,"lo":240,"hi":291,"n":9,"rr":260,"mr":258},{"m":"phi-4-reasoning-vision-15b","r":270,"s":56.24,"lo":213,"hi":293,"n":7,"rr":204,"mr":278},{"m":"aquila-vl-2b","r":271,"s":56.17,"lo":252,"hi":282,"n":7,"rr":221,"mr":268},{"m":"phi-3.5-vision-instruct","r":272,"s":55.8,"lo":255,"hi":288,"n":10,"rr":284,"mr":259},{"m":"lfm2.5-vl-1.6b","r":273,"s":55.54,"lo":252,"hi":294,"n":11,"rr":293,"mr":262},{"m":"minicpm-llama3-v2.5","r":274,"s":55.45,"lo":254,"hi":283,"n":7,"rr":217,"mr":270},{"m":"gemini-1.0-pro","r":275,"s":55.42,"lo":233,"hi":291,"n":8,"rr":224,"mr":274},{"m":"mm1.5-7b","r":276,"s":55.41,"lo":249,"hi":291,"n":6,"rr":155,"mr":279},{"m":"qwen2-vl-2b","r":277,"s":55.4,"lo":246,"hi":295,"n":9,"rr":262,"mr":263},{"m":"phi-3.5-vision-4b","r":278,"s":55.06,"lo":210,"hi":310,"n":4,"rr":131,"mr":288},{"m":"internvl2.5-2b","r":279,"s":54.61,"lo":256,"hi":299,"n":9,"rr":271,"mr":272},{"m":"phi-3-vision-4b","r":280,"s":54.46,"lo":263,"hi":296,"n":8,"rr":238,"mr":275},{"m":"deepseek-ocr","r":281,"s":54.32,"lo":163,"hi":317,"n":5,"rr":312,"mr":293},{"m":"internvl3-1b","r":282,"s":53.98,"lo":256,"hi":300,"n":3,"rr":333,"mr":283},{"m":"mm1.5-3b","r":283,"s":53.89,"lo":251,"hi":302,"n":6,"rr":175,"mr":285},{"m":"llada-v","r":284,"s":53.68,"lo":254,"hi":296,"n":6,"rr":190,"mr":282},{"m":"gpt-5-nano-minimal","r":285,"s":53.55,"lo":236,"hi":307,"n":11,"rr":313,"mr":277},{"m":"mini-gemini-hd-34b","r":286,"s":52.05,"lo":258,"hi":301,"n":6,"rr":270,"mr":289},{"m":"gemma-3n-e2b-it","r":287,"s":52.02,"lo":270,"hi":298,"n":7,"rr":266,"mr":286},{"m":"internvl2-2b","r":288,"s":51.86,"lo":273,"hi":309,"n":9,"rr":286,"mr":281},{"m":"cambrian-34b","r":289,"s":51.7,"lo":268,"hi":306,"n":8,"rr":253,"mr":287},{"m":"molmoe-1b","r":290,"s":51.07,"lo":240,"hi":309,"n":8,"rr":258,"mr":290},{"m":"cambrian-1-34b","r":291,"s":51.03,"lo":228,"hi":304,"n":5,"rr":149,"mr":295},{"m":"internvl2.5-1b","r":292,"s":50.95,"lo":277,"hi":312,"n":9,"rr":292,"mr":284},{"m":"cambrian-1-8b","r":293,"s":50.9,"lo":243,"hi":298,"n":4,"rr":145,"mr":297},{"m":"step-1v-32k","r":294,"s":50.86,"lo":230,"hi":307,"n":4,"rr":211,"mr":298},{"m":"llava-next-34b","r":295,"s":50.36,"lo":278,"hi":306,"n":8,"rr":272,"mr":292},{"m":"qwen-vl-plus","r":296,"s":50.33,"lo":255,"hi":319,"n":8,"rr":291,"mr":291},{"m":"fastvlm-0.5b","r":297,"s":48.47,"lo":279,"hi":314,"n":6,"rr":219,"mr":300},{"m":"emu3-8b","r":298,"s":48.42,"lo":234,"hi":308,"n":4,"rr":185,"mr":305},{"m":"mm1-30b","r":299,"s":48.04,"lo":277,"hi":310,"n":6,"rr":209,"mr":302},{"m":"vila1.5-40b","r":300,"s":47.29,"lo":280,"hi":316,"n":6,"rr":303,"mr":304},{"m":"internvl2-1b","r":301,"s":47.25,"lo":289,"hi":323,"n":9,"rr":304,"mr":294},{"m":"smolvlm2-2.2b","r":302,"s":47.08,"lo":286,"hi":320,"n":8,"rr":300,"mr":299},{"m":"mm1.5-1b","r":303,"s":46.75,"lo":288,"hi":320,"n":6,"rr":231,"mr":306},{"m":"docowl-1.5-chat","r":304,"s":46.52,"lo":287,"hi":320,"n":7,"rr":294,"mr":301},{"m":"cogagent-18b","r":305,"s":46.19,"lo":291,"hi":320,"n":7,"rr":296,"mr":303},{"m":"sphinx-v2","r":306,"s":45.74,"lo":288,"hi":325,"n":3,"rr":334,"mr":307},{"m":"paddleocr-vl-1.6","r":307,"s":45.62,"lo":220,"hi":323,"n":3,"rr":327,"mr":311},{"m":"idefics2-8b","r":308,"s":45.27,"lo":273,"hi":322,"n":4,"rr":309,"mr":308},{"m":"internlm-xcomposer2-vl-7b","r":309,"s":45.04,"lo":290,"hi":324,"n":9,"rr":311,"mr":296},{"m":"deepseek-vl-7b","r":310,"s":43.96,"lo":284,"hi":325,"n":5,"rr":321,"mr":310},{"m":"gemini-nano-2","r":311,"s":43.42,"lo":277,"hi":328,"n":5,"rr":278,"mr":312},{"m":"t5gemma-2-4b-4b","r":312,"s":42.96,"lo":282,"hi":322,"n":5,"rr":265,"mr":313},{"m":"xgen-mm-interleave-4b","r":313,"s":42.84,"lo":248,"hi":319,"n":4,"rr":223,"mr":317},{"m":"internvl-chat-v1.2","r":314,"s":42.19,"lo":267,"hi":325,"n":6,"rr":257,"mr":315},{"m":"minicpm-v-2.0-3b","r":315,"s":42.11,"lo":304,"hi":326,"n":8,"rr":305,"mr":309},{"m":"cogvlm-17b-chat","r":316,"s":41.89,"lo":257,"hi":323,"n":5,"rr":283,"mr":316},{"m":"qwen-vl","r":317,"s":40.98,"lo":257,"hi":322,"n":4,"rr":244,"mr":318},{"m":"llava-onevision-0.5b","r":318,"s":40.2,"lo":307,"hi":329,"n":7,"rr":315,"mr":314},{"m":"qwen-vl-chat","r":319,"s":38.17,"lo":263,"hi":326,"n":5,"rr":273,"mr":320},{"m":"mplug-docowl-7b","r":320,"s":38.04,"lo":216,"hi":327,"n":3,"rr":290,"mr":322},{"m":"llava-1.5-7b","r":321,"s":37.69,"lo":293,"hi":331,"n":5,"rr":329,"mr":321},{"m":"ureader","r":322,"s":36.92,"lo":302,"hi":333,"n":6,"rr":323,"mr":319},{"m":"paligemma-mix-3b","r":323,"s":36.47,"lo":251,"hi":332,"n":4,"rr":314,"mr":324},{"m":"llava-1.5-13b","r":324,"s":36.06,"lo":295,"hi":332,"n":6,"rr":328,"mr":323},{"m":"t5gemma-2-1b-1b","r":325,"s":34.63,"lo":287,"hi":332,"n":5,"rr":307,"mr":325},{"m":"deepseek-vl-1.3b","r":326,"s":31.7,"lo":233,"hi":330,"n":3,"rr":319,"mr":327},{"m":"textmonkey","r":327,"s":30.81,"lo":307,"hi":334,"n":7,"rr":322,"mr":326},{"m":"minicpm-v","r":328,"s":29.75,"lo":233,"hi":331,"n":3,"rr":320,"mr":329},{"m":"janus-pro-7b","r":329,"s":29.03,"lo":296,"hi":332,"n":6,"rr":317,"mr":328},{"m":"deepseek-ocr-2","r":330,"s":27.82,"lo":201,"hi":333,"n":6,"rr":301,"mr":330},{"m":"yi-vl-6b","r":331,"s":25.37,"lo":232,"hi":334,"n":3,"rr":330,"mr":332},{"m":"yi-vl-34b","r":332,"s":23.84,"lo":231,"hi":335,"n":3,"rr":332,"mr":333},{"m":"janus-pro-1.5b","r":333,"s":22.51,"lo":297,"hi":334,"n":6,"rr":326,"mr":331},{"m":"t5gemma-2-270m-270m","r":334,"s":21.99,"lo":283,"hi":335,"n":5,"rr":331,"mr":334},{"m":"lumina-dimoo","r":335,"s":18.07,"lo":316,"hi":335,"n":6,"rr":335,"mr":335}]},"faix-stem":{"name":"STEM","n":1218,"nb":59,"acc":0.8532,"raw_acc":0.6723,"rows":[{"m":"claude-fable-5","r":1,"s":97.29,"lo":1,"hi":22,"n":6,"rr":101,"mr":2},{"m":"gpt-5.6-sol","r":2,"s":96.48,"lo":2,"hi":9,"n":14,"rr":121,"mr":1},{"m":"claude-opus-5","r":3,"s":96.33,"lo":1,"hi":12,"n":9,"rr":65,"mr":3},{"m":"veriloop-e2","r":4,"s":95.93,"lo":1,"hi":152,"n":3,"rr":6,"mr":6},{"m":"darwin-180b-rsi","r":5,"s":95.63,"lo":1,"hi":47,"n":3,"rr":1,"mr":4},{"m":"claude-mythos-5","r":6,"s":95.49,"lo":2,"hi":389,"n":3,"rr":26,"mr":8},{"m":"gpt-5.5","r":7,"s":95.17,"lo":4,"hi":13,"n":24,"rr":110,"mr":5},{"m":"claude-opus-4.8","r":8,"s":94.94,"lo":5,"hi":12,"n":18,"rr":85,"mr":7},{"m":"hy4-preview","r":9,"s":94.41,"lo":6,"hi":29,"n":6,"rr":419,"mr":9},{"m":"qwen3.8-max","r":10,"s":94.39,"lo":5,"hi":29,"n":8,"rr":428,"mr":10},{"m":"claude-mythos-preview","r":11,"s":94.34,"lo":6,"hi":386,"n":3,"rr":77,"mr":11},{"m":"qwen3.8-flash-next","r":12,"s":93.71,"lo":6,"hi":76,"n":5,"rr":251,"mr":14},{"m":"kimi-k3","r":13,"s":93.57,"lo":9,"hi":38,"n":10,"rr":317,"mr":12},{"m":"gpt-6-astra","r":14,"s":93.55,"lo":1,"hi":147,"n":3,"rr":2,"mr":13},{"m":"deepseek-v4-pro-0813","r":15,"s":93.49,"lo":11,"hi":44,"n":6,"rr":576,"mr":16},{"m":"deepseek-v4-flash-0731","r":16,"s":93.39,"lo":9,"hi":38,"n":7,"rr":455,"mr":17},{"m":"deepseek-v4.1-flash","r":17,"s":93.38,"lo":12,"hi":168,"n":4,"rr":655,"mr":19},{"m":"gpt-5.6-luna","r":18,"s":93.33,"lo":6,"hi":140,"n":9,"rr":171,"mr":15},{"m":"gpt-5.6-terra","r":19,"s":93.22,"lo":5,"hi":102,"n":9,"rr":283,"mr":20},{"m":"gemini-3.1-pro","r":20,"s":93.1,"lo":10,"hi":27,"n":24,"rr":341,"mr":18},{"m":"gpt-5.2-high","r":21,"s":92.69,"lo":9,"hi":36,"n":14,"rr":261,"mr":21},{"m":"bigbang-v1","r":22,"s":92.61,"lo":7,"hi":359,"n":3,"rr":767,"mr":34},{"m":"gpt-5.4","r":23,"s":92.45,"lo":11,"hi":33,"n":14,"rr":365,"mr":23},{"m":"intern-s2-397b","r":24,"s":92.36,"lo":4,"hi":120,"n":4,"rr":356,"mr":30},{"m":"gpt-5.2-thinking-xhigh","r":25,"s":92.31,"lo":12,"hi":47,"n":9,"rr":88,"mr":22},{"m":"gpt-5.4-pro","r":26,"s":92.05,"lo":13,"hi":147,"n":4,"rr":834,"mr":27},{"m":"agents-a1","r":27,"s":91.85,"lo":14,"hi":298,"n":4,"rr":758,"mr":33},{"m":"qwen3.7-max","r":28,"s":91.66,"lo":19,"hi":43,"n":15,"rr":426,"mr":26},{"m":"seed2.1-pro","r":29,"s":91.54,"lo":16,"hi":42,"n":17,"rr":514,"mr":31},{"m":"deepseek-v4-pro-thinking-max","r":30,"s":91.51,"lo":19,"hi":42,"n":14,"rr":447,"mr":28},{"m":"gpt-5.2-thinking","r":31,"s":91.44,"lo":16,"hi":59,"n":8,"rr":302,"mr":24},{"m":"seed2.1-turbo","r":32,"s":91.44,"lo":19,"hi":42,"n":13,"rr":444,"mr":35},{"m":"glm-5.2","r":33,"s":91.4,"lo":9,"hi":51,"n":13,"rr":344,"mr":29},{"m":"gpt-5.2","r":34,"s":91.36,"lo":17,"hi":49,"n":22,"rr":335,"mr":25},{"m":"deepseek-v4-pro","r":35,"s":91.25,"lo":18,"hi":46,"n":13,"rr":226,"mr":32},{"m":"ax-k2","r":36,"s":91.19,"lo":22,"hi":102,"n":6,"rr":586,"mr":36},{"m":"glm-5.3","r":37,"s":91.07,"lo":21,"hi":92,"n":6,"rr":572,"mr":40},{"m":"gemini-3-flash","r":38,"s":90.95,"lo":18,"hi":71,"n":15,"rr":273,"mr":39},{"m":"claude-opus-4.6","r":39,"s":90.85,"lo":23,"hi":50,"n":17,"rr":477,"mr":37},{"m":"hy3","r":40,"s":90.6,"lo":29,"hi":56,"n":9,"rr":774,"mr":45},{"m":"deepseek-v4-flash-thinking-max","r":41,"s":90.56,"lo":28,"hi":53,"n":12,"rr":608,"mr":41},{"m":"gemini-3-pro","r":42,"s":90.54,"lo":23,"hi":57,"n":32,"rr":274,"mr":38},{"m":"beam","r":43,"s":90.5,"lo":29,"hi":132,"n":4,"rr":433,"mr":42},{"m":"deepseek-v4-flash","r":44,"s":90.27,"lo":24,"hi":110,"n":11,"rr":409,"mr":43},{"m":"seed2.0-pro","r":45,"s":90.27,"lo":24,"hi":55,"n":14,"rr":196,"mr":44},{"m":"deepseek-v4-pro-thinking","r":46,"s":90.2,"lo":28,"hi":56,"n":5,"rr":186,"mr":47},{"m":"longcat-flash-thinking-2601","r":47,"s":90.2,"lo":22,"hi":93,"n":5,"rr":136,"mr":48},{"m":"kimi-k2.7-code","r":48,"s":89.85,"lo":10,"hi":154,"n":4,"rr":518,"mr":52},{"m":"kimi-k2.6-thinking","r":49,"s":89.81,"lo":32,"hi":55,"n":14,"rr":370,"mr":49},{"m":"ring-1t-2.5-heavy-thinking","r":50,"s":89.73,"lo":9,"hi":99,"n":3,"rr":5,"mr":54},{"m":"gpt-5.4-thinking","r":51,"s":89.66,"lo":22,"hi":229,"n":3,"rr":815,"mr":55},{"m":"qwen3.7-plus","r":52,"s":89.47,"lo":37,"hi":59,"n":8,"rr":268,"mr":51},{"m":"nemotron-3.5-super-vl-120b-a12b","r":53,"s":89.42,"lo":20,"hi":135,"n":5,"rr":479,"mr":56},{"m":"qwen3.8-27b","r":54,"s":89.27,"lo":22,"hi":103,"n":12,"rr":72,"mr":46},{"m":"kimi-k2.6","r":55,"s":89.07,"lo":46,"hi":69,"n":4,"rr":11,"mr":50},{"m":"claude-opus-4.7","r":56,"s":89.02,"lo":33,"hi":69,"n":19,"rr":574,"mr":53},{"m":"claude-opus-4.5-thinking","r":57,"s":88.98,"lo":22,"hi":97,"n":9,"rr":162,"mr":64},{"m":"glm-5.3-flash","r":58,"s":88.66,"lo":45,"hi":106,"n":5,"rr":446,"mr":59},{"m":"seed2.0-lite-0428","r":59,"s":88.46,"lo":46,"hi":82,"n":7,"rr":436,"mr":62},{"m":"ring-2.6-1t-xhigh","r":60,"s":88.33,"lo":46,"hi":94,"n":4,"rr":16,"mr":57},{"m":"qwen3-max-thinking","r":61,"s":88.25,"lo":41,"hi":104,"n":8,"rr":151,"mr":65},{"m":"solar-open-2-250b","r":62,"s":88.19,"lo":46,"hi":104,"n":4,"rr":201,"mr":58},{"m":"glm-5","r":63,"s":88.03,"lo":45,"hi":84,"n":11,"rr":132,"mr":60},{"m":"gemini-3.5-flash","r":64,"s":87.87,"lo":39,"hi":131,"n":5,"rr":38,"mr":61},{"m":"ring-1t-2.5","r":65,"s":87.76,"lo":27,"hi":116,"n":3,"rr":9,"mr":75},{"m":"step-3.5-flash-20260204","r":66,"s":87.74,"lo":38,"hi":93,"n":11,"rr":315,"mr":63},{"m":"deepseek-v4-flash-thinking","r":67,"s":87.64,"lo":52,"hi":82,"n":5,"rr":339,"mr":69},{"m":"deepseek-v3.2-speciale","r":68,"s":87.58,"lo":22,"hi":100,"n":4,"rr":12,"mr":68},{"m":"inkling","r":69,"s":87.26,"lo":49,"hi":111,"n":5,"rr":390,"mr":67},{"m":"inkling-small","r":70,"s":87.2,"lo":60,"hi":80,"n":7,"rr":281,"mr":66},{"m":"motif-3","r":71,"s":86.98,"lo":53,"hi":153,"n":5,"rr":596,"mr":79},{"m":"qwen3.6-plus","r":72,"s":86.98,"lo":53,"hi":84,"n":15,"rr":108,"mr":70},{"m":"glm-4.7","r":73,"s":86.92,"lo":54,"hi":100,"n":5,"rr":15,"mr":71},{"m":"step-3.7-flash","r":74,"s":86.91,"lo":30,"hi":104,"n":4,"rr":408,"mr":84},{"m":"glm-4.7-thinking","r":75,"s":86.87,"lo":45,"hi":104,"n":5,"rr":160,"mr":74},{"m":"kimi-k2.5-thinking","r":76,"s":86.86,"lo":57,"hi":84,"n":14,"rr":117,"mr":72},{"m":"glm-5.1","r":77,"s":86.8,"lo":56,"hi":80,"n":15,"rr":557,"mr":73},{"m":"gpt-5-pro","r":78,"s":86.8,"lo":59,"hi":181,"n":3,"rr":325,"mr":76},{"m":"openpangu-2.0-pro-thinking","r":79,"s":86.66,"lo":58,"hi":89,"n":6,"rr":503,"mr":77},{"m":"grm-3.2-sky","r":80,"s":86.64,"lo":56,"hi":106,"n":3,"rr":13,"mr":78},{"m":"longcat-flash-thinking-zigzag","r":81,"s":86.39,"lo":25,"hi":161,"n":4,"rr":225,"mr":87},{"m":"hy3-preview","r":82,"s":86.38,"lo":61,"hi":93,"n":8,"rr":937,"mr":86},{"m":"qwen3.5-397b-a17b","r":83,"s":86.38,"lo":59,"hi":88,"n":23,"rr":305,"mr":81},{"m":"kimi-k2-thinking","r":84,"s":86.07,"lo":32,"hi":110,"n":8,"rr":155,"mr":88},{"m":"kolibri-1","r":85,"s":86.06,"lo":62,"hi":132,"n":4,"rr":228,"mr":80},{"m":"claude-opus-4.5","r":86,"s":86.04,"lo":56,"hi":98,"n":25,"rr":481,"mr":83},{"m":"kimi-k2.5","r":87,"s":85.85,"lo":65,"hi":98,"n":17,"rr":164,"mr":82},{"m":"claude-sonnet-4.6","r":88,"s":85.67,"lo":67,"hi":98,"n":9,"rr":387,"mr":85},{"m":"mai-thinking-1","r":89,"s":85.27,"lo":67,"hi":120,"n":4,"rr":17,"mr":90},{"m":"gpt-5.1-high","r":90,"s":85.23,"lo":64,"hi":126,"n":3,"rr":8,"mr":91},{"m":"intern-s2-preview","r":91,"s":85.16,"lo":68,"hi":121,"n":7,"rr":792,"mr":93},{"m":"gemini-3-pro-preview","r":92,"s":85.14,"lo":65,"hi":217,"n":3,"rr":7,"mr":89},{"m":"nemotron-3.5-bolt-74b-a9b","r":93,"s":84.95,"lo":75,"hi":269,"n":3,"rr":851,"mr":97},{"m":"k2-horizon-375b-a23b","r":94,"s":84.86,"lo":75,"hi":286,"n":3,"rr":852,"mr":101},{"m":"nemotron-3-ultra","r":95,"s":84.48,"lo":58,"hi":136,"n":9,"rr":546,"mr":92},{"m":"seed2.0-lite","r":96,"s":84.35,"lo":47,"hi":123,"n":14,"rr":407,"mr":95},{"m":"ling-3.0-flash","r":97,"s":84.29,"lo":80,"hi":136,"n":3,"rr":20,"mr":100},{"m":"intern-s2-mobius","r":98,"s":84.27,"lo":82,"hi":137,"n":4,"rr":36,"mr":99},{"m":"longcat-flash-prover","r":99,"s":84.26,"lo":56,"hi":158,"n":4,"rr":31,"mr":105},{"m":"deepseek-v3.2-thinking","r":100,"s":84.19,"lo":79,"hi":107,"n":11,"rr":133,"mr":94},{"m":"ornith-1.5-35b-a3b","r":101,"s":84.11,"lo":67,"hi":371,"n":3,"rr":512,"mr":117},{"m":"gemini-3.8-flash","r":102,"s":84.1,"lo":4,"hi":168,"n":5,"rr":39,"mr":103},{"m":"qwen3.6-27b","r":103,"s":83.88,"lo":81,"hi":118,"n":15,"rr":147,"mr":96},{"m":"gpt-5-thinking","r":104,"s":83.75,"lo":82,"hi":294,"n":3,"rr":119,"mr":104},{"m":"gpt-5","r":105,"s":83.58,"lo":86,"hi":122,"n":17,"rr":246,"mr":98},{"m":"qwen3.5-122b-a10b","r":106,"s":83.47,"lo":81,"hi":116,"n":14,"rr":208,"mr":102},{"m":"minimax-m3","r":107,"s":83.37,"lo":49,"hi":143,"n":5,"rr":413,"mr":111},{"m":"gpt-5-mini-high","r":108,"s":82.93,"lo":70,"hi":140,"n":18,"rr":510,"mr":109},{"m":"nex-n2-mini","r":109,"s":82.82,"lo":60,"hi":247,"n":6,"rr":1024,"mr":128},{"m":"mimo-v2.5","r":110,"s":82.8,"lo":99,"hi":136,"n":5,"rr":527,"mr":107},{"m":"mai-code-1-flash","r":111,"s":82.75,"lo":66,"hi":174,"n":4,"rr":618,"mr":118},{"m":"step3-vl-10b-pacore","r":112,"s":82.67,"lo":92,"hi":208,"n":4,"rr":27,"mr":112},{"m":"claude-sonnet-5","r":113,"s":82.62,"lo":8,"hi":201,"n":6,"rr":549,"mr":131},{"m":"nemotron-3-super-120b-a12b","r":114,"s":82.61,"lo":88,"hi":132,"n":9,"rr":253,"mr":106},{"m":"grok-4","r":115,"s":82.57,"lo":95,"hi":126,"n":15,"rr":389,"mr":110},{"m":"ternary-bonsai-2-27b","r":116,"s":82.53,"lo":80,"hi":346,"n":4,"rr":3,"mr":115},{"m":"gemini-3.7-flash","r":117,"s":82.53,"lo":5,"hi":406,"n":4,"rr":75,"mr":127},{"m":"gemini-3.6-flash","r":118,"s":82.53,"lo":13,"hi":409,"n":4,"rr":116,"mr":125},{"m":"gpt-5-high","r":119,"s":82.49,"lo":91,"hi":129,"n":19,"rr":134,"mr":108},{"m":"grok-4-fast","r":120,"s":82.45,"lo":88,"hi":170,"n":6,"rr":80,"mr":113},{"m":"gpt-5.1-thinking","r":121,"s":82.43,"lo":55,"hi":146,"n":3,"rr":998,"mr":130},{"m":"raon-1-mini-preview","r":122,"s":82.14,"lo":100,"hi":192,"n":4,"rr":219,"mr":116},{"m":"nemotron-3.5-super-vl-120b-a12b-nvfp4","r":123,"s":82.1,"lo":74,"hi":233,"n":4,"rr":741,"mr":134},{"m":"seed1.8","r":124,"s":82.07,"lo":97,"hi":155,"n":13,"rr":181,"mr":114},{"m":"gpt-5.4-mini","r":125,"s":81.89,"lo":90,"hi":212,"n":10,"rr":418,"mr":122},{"m":"nemotron-cascade-2-30b-a3b","r":126,"s":81.86,"lo":89,"hi":153,"n":7,"rr":400,"mr":121},{"m":"mimo-v2-flash","r":127,"s":81.62,"lo":94,"hi":147,"n":6,"rr":204,"mr":120},{"m":"qwen3.6-35b-a3b","r":128,"s":81.38,"lo":93,"hi":143,"n":21,"rr":227,"mr":124},{"m":"muse-glimmer-30b","r":129,"s":81.24,"lo":93,"hi":181,"n":5,"rr":610,"mr":123},{"m":"qwen3.5-27b","r":130,"s":81.19,"lo":102,"hi":151,"n":22,"rr":107,"mr":119},{"m":"qwen3.5-35b-a3b","r":131,"s":81.11,"lo":105,"hi":140,"n":17,"rr":349,"mr":126},{"m":"glm-4.6","r":132,"s":81.09,"lo":106,"hi":141,"n":8,"rr":195,"mr":132},{"m":"k-exaone-2.0","r":133,"s":80.89,"lo":103,"hi":158,"n":7,"rr":536,"mr":129},{"m":"comet-60b-a12b","r":134,"s":80.76,"lo":91,"hi":246,"n":4,"rr":768,"mr":145},{"m":"vibethinker-3b","r":135,"s":80.73,"lo":104,"hi":151,"n":6,"rr":34,"mr":133},{"m":"comet-60b-a12b-fp8","r":136,"s":80.59,"lo":95,"hi":243,"n":4,"rr":773,"mr":146},{"m":"nemotron-labs-3-puzzle-75b-a9b","r":137,"s":80.53,"lo":98,"hi":182,"n":5,"rr":607,"mr":137},{"m":"comet-60b-a12b-nvfp4","r":138,"s":80.5,"lo":97,"hi":253,"n":4,"rr":777,"mr":147},{"m":"qwen3.8-27b-ud-q4-k-xl","r":139,"s":80.4,"lo":108,"hi":345,"n":4,"rr":4,"mr":136},{"m":"intern-s1-pro","r":140,"s":80.37,"lo":109,"hi":150,"n":8,"rr":803,"mr":140},{"m":"claude-sonnet-4.5","r":141,"s":80.22,"lo":84,"hi":174,"n":23,"rr":486,"mr":144},{"m":"exaone-4.5-33b-thinking","r":142,"s":80.16,"lo":118,"hi":160,"n":7,"rr":46,"mr":135},{"m":"k-exaone","r":143,"s":79.9,"lo":119,"hi":159,"n":9,"rr":441,"mr":138},{"m":"gpt-oss-120b-high","r":144,"s":79.87,"lo":118,"hi":155,"n":10,"rr":95,"mr":139},{"m":"k2-horizon-32b","r":145,"s":79.73,"lo":115,"hi":367,"n":3,"rr":952,"mr":155},{"m":"openpangu-2.0-flash-thinking","r":146,"s":79.71,"lo":110,"hi":185,"n":7,"rr":621,"mr":143},{"m":"snowdon-1.1-small","r":147,"s":79.67,"lo":108,"hi":425,"n":3,"rr":18,"mr":157},{"m":"nanbeige4.2-3b","r":148,"s":79.47,"lo":117,"hi":235,"n":5,"rr":751,"mr":152},{"m":"deepseek-v3.2","r":149,"s":79.42,"lo":108,"hi":191,"n":13,"rr":220,"mr":141},{"m":"gpt-oss-120b","r":150,"s":79.29,"lo":114,"hi":179,"n":17,"rr":247,"mr":142},{"m":"k2-horizon-mova-36b-a4b","r":151,"s":79.01,"lo":117,"hi":342,"n":3,"rr":957,"mr":170},{"m":"hy-2.0-thinking","r":152,"s":78.88,"lo":126,"hi":201,"n":4,"rr":725,"mr":156},{"m":"spark-x2.6-4b","r":153,"s":78.78,"lo":124,"hi":197,"n":6,"rr":313,"mr":148},{"m":"qwen3-vl-235b-a22b-thinking","r":154,"s":78.7,"lo":122,"hi":168,"n":10,"rr":60,"mr":154},{"m":"qwen3-235b-a22b-thinking-2507","r":155,"s":78.68,"lo":126,"hi":165,"n":13,"rr":352,"mr":149},{"m":"k2-horizon-7b","r":156,"s":78.34,"lo":132,"hi":179,"n":7,"rr":453,"mr":150},{"m":"gemma-4-26b-a4b-it","r":157,"s":78.24,"lo":121,"hi":186,"n":16,"rr":384,"mr":151},{"m":"qwen3.5-omni-plus","r":158,"s":78.23,"lo":128,"hi":191,"n":8,"rr":126,"mr":166},{"m":"deepseek-v3.1-terminus","r":159,"s":78.2,"lo":132,"hi":204,"n":5,"rr":295,"mr":163},{"m":"deepseek-v3.1-terminus-thinking","r":160,"s":78.12,"lo":131,"hi":180,"n":3,"rr":560,"mr":164},{"m":"gpt-5-mini","r":161,"s":77.99,"lo":128,"hi":191,"n":16,"rr":248,"mr":162},{"m":"sarvam-105b","r":162,"s":77.95,"lo":133,"hi":178,"n":7,"rr":41,"mr":153},{"m":"gpt-5-2025-08-07","r":163,"s":77.82,"lo":116,"hi":1024,"n":4,"rr":872,"mr":176},{"m":"qwen3-235b-2507","r":164,"s":77.8,"lo":140,"hi":358,"n":3,"rr":354,"mr":174},{"m":"nvidia-nemotron-3-nano-30b-a3b-bf16","r":165,"s":77.8,"lo":113,"hi":197,"n":8,"rr":476,"mr":161},{"m":"claude-4.5-sonnet-thinking","r":166,"s":77.73,"lo":107,"hi":180,"n":5,"rr":631,"mr":172},{"m":"spark-x2.5-4b","r":167,"s":77.72,"lo":129,"hi":240,"n":6,"rr":375,"mr":160},{"m":"longcat-flash-thinking","r":168,"s":77.58,"lo":143,"hi":205,"n":4,"rr":49,"mr":167},{"m":"o3","r":169,"s":77.47,"lo":123,"hi":186,"n":13,"rr":539,"mr":159},{"m":"cogito-671b-v2.1","r":170,"s":77.36,"lo":142,"hi":197,"n":3,"rr":19,"mr":158},{"m":"ernie-5.0","r":171,"s":77.27,"lo":135,"hi":179,"n":6,"rr":42,"mr":173},{"m":"gemini-2.5-pro","r":172,"s":77.02,"lo":138,"hi":181,"n":30,"rr":484,"mr":168},{"m":"command-a-plus-05-2026","r":173,"s":76.95,"lo":116,"hi":212,"n":7,"rr":502,"mr":171},{"m":"k2-horizon-3.7b","r":174,"s":76.87,"lo":141,"hi":222,"n":7,"rr":578,"mr":169},{"m":"nemotron-3-nano-30b-a3b","r":175,"s":76.77,"lo":138,"hi":195,"n":11,"rr":213,"mr":175},{"m":"mercury-2","r":176,"s":76.68,"lo":144,"hi":400,"n":3,"rr":460,"mr":177},{"m":"o3-high","r":177,"s":76.62,"lo":130,"hi":185,"n":10,"rr":383,"mr":178},{"m":"gemma-4-31b-it","r":178,"s":76.57,"lo":141,"hi":206,"n":22,"rr":130,"mr":165},{"m":"gpt-5.4-nano","r":179,"s":76.42,"lo":137,"hi":284,"n":8,"rr":948,"mr":184},{"m":"qwen-3-235b-a22b-thinking","r":180,"s":76.32,"lo":131,"hi":277,"n":7,"rr":83,"mr":180},{"m":"granite-4.2-30b","r":181,"s":76.17,"lo":136,"hi":333,"n":6,"rr":709,"mr":185},{"m":"zdtaichu5.0-9b","r":182,"s":76.14,"lo":149,"hi":192,"n":8,"rr":66,"mr":181},{"m":"deepseek-r1-0528","r":183,"s":75.6,"lo":152,"hi":192,"n":11,"rr":244,"mr":179},{"m":"qwen3-next-80b-a3b-thinking","r":184,"s":75.39,"lo":146,"hi":196,"n":15,"rr":278,"mr":183},{"m":"hypernova-60b-2605","r":185,"s":75.37,"lo":157,"hi":427,"n":3,"rr":523,"mr":190},{"m":"deepseek-v3-0528","r":186,"s":75.07,"lo":163,"hi":200,"n":3,"rr":29,"mr":187},{"m":"intellect-3","r":187,"s":74.92,"lo":164,"hi":203,"n":7,"rr":57,"mr":182},{"m":"step3-vl-10b-sere","r":188,"s":74.78,"lo":171,"hi":258,"n":4,"rr":106,"mr":193},{"m":"ling-2.6-1t","r":189,"s":74.73,"lo":170,"hi":234,"n":5,"rr":257,"mr":195},{"m":"deepseek-v3.1-thinking","r":190,"s":74.54,"lo":152,"hi":362,"n":8,"rr":487,"mr":188},{"m":"glm-4.7-flash","r":191,"s":74.53,"lo":157,"hi":256,"n":12,"rr":467,"mr":186},{"m":"o3-mini-high","r":192,"s":74.09,"lo":185,"hi":379,"n":3,"rr":452,"mr":202},{"m":"minimax-m2.7","r":193,"s":74.08,"lo":126,"hi":232,"n":11,"rr":664,"mr":194},{"m":"seed2.0-mini","r":194,"s":74.07,"lo":125,"hi":223,"n":13,"rr":831,"mr":191},{"m":"g9v3-39a5b","r":195,"s":74.01,"lo":170,"hi":425,"n":3,"rr":1022,"mr":219},{"m":"golongrl-30b-a3b","r":196,"s":73.99,"lo":168,"hi":296,"n":3,"rr":56,"mr":199},{"m":"mistral-medium-3.5","r":197,"s":73.99,"lo":168,"hi":224,"n":6,"rr":526,"mr":189},{"m":"step3-vl-10b","r":198,"s":73.97,"lo":176,"hi":223,"n":10,"rr":123,"mr":198},{"m":"ring-flash-2.0","r":199,"s":73.95,"lo":181,"hi":271,"n":3,"rr":252,"mr":204},{"m":"magistral-medium-1.2","r":200,"s":73.95,"lo":161,"hi":244,"n":4,"rr":282,"mr":197},{"m":"gpt-5.1","r":201,"s":73.92,"lo":105,"hi":308,"n":5,"rr":1029,"mr":212},{"m":"qwen3.5-9b","r":202,"s":73.62,"lo":168,"hi":229,"n":24,"rr":200,"mr":192},{"m":"qwenlong-l1.5-30b-a3b","r":203,"s":73.61,"lo":174,"hi":290,"n":3,"rr":58,"mr":196},{"m":"ring-2.6-1t-high","r":204,"s":73.56,"lo":178,"hi":257,"n":4,"rr":232,"mr":206},{"m":"gemini-3.1-flash-lite","r":205,"s":73.37,"lo":164,"hi":265,"n":8,"rr":916,"mr":203},{"m":"gpt-oss-20b-high","r":206,"s":73.2,"lo":163,"hi":318,"n":8,"rr":79,"mr":210},{"m":"o4-mini","r":207,"s":73.02,"lo":159,"hi":285,"n":6,"rr":648,"mr":220},{"m":"ling-2.5-1t","r":208,"s":72.99,"lo":179,"hi":255,"n":6,"rr":634,"mr":208},{"m":"dots-vlm1","r":209,"s":72.82,"lo":190,"hi":271,"n":5,"rr":100,"mr":225},{"m":"solar-open-100b","r":210,"s":72.81,"lo":170,"hi":237,"n":9,"rr":288,"mr":201},{"m":"qwen3-vl-235b-a22b","r":211,"s":72.71,"lo":156,"hi":239,"n":8,"rr":99,"mr":227},{"m":"openreasoning-nemotron-32b","r":212,"s":72.68,"lo":184,"hi":228,"n":5,"rr":312,"mr":211},{"m":"qwen3-235b-a22b","r":213,"s":72.68,"lo":169,"hi":260,"n":19,"rr":337,"mr":200},{"m":"nanbeige4.1-3b","r":214,"s":72.67,"lo":170,"hi":279,"n":5,"rr":625,"mr":215},{"m":"exaone-4.0-32b-thinking","r":215,"s":72.5,"lo":190,"hi":240,"n":5,"rr":623,"mr":216},{"m":"o3-2025-04-16","r":216,"s":72.44,"lo":180,"hi":870,"n":3,"rr":683,"mr":233},{"m":"zaya1-8b","r":217,"s":72.42,"lo":174,"hi":278,"n":5,"rr":570,"mr":230},{"m":"mistral-small-4-thinking","r":218,"s":72.38,"lo":186,"hi":242,"n":5,"rr":532,"mr":205},{"m":"qwen3-30b-a3b-thinking-2507","r":219,"s":72.33,"lo":182,"hi":242,"n":14,"rr":306,"mr":209},{"m":"qwen3-next-80b-a3b","r":220,"s":72.32,"lo":208,"hi":388,"n":3,"rr":508,"mr":229},{"m":"superapriel-15b-instruct","r":221,"s":72.31,"lo":164,"hi":483,"n":5,"rr":25,"mr":224},{"m":"openpangu-r-72b-2512-slow-thinking","r":222,"s":72.26,"lo":178,"hi":237,"n":5,"rr":146,"mr":207},{"m":"seed-oss-36b-instruct","r":223,"s":72.16,"lo":203,"hi":298,"n":3,"rr":293,"mr":234},{"m":"granite-4.2-8b","r":224,"s":72.13,"lo":192,"hi":299,"n":6,"rr":784,"mr":217},{"m":"openpangu-2.0-pro","r":225,"s":72.06,"lo":161,"hi":287,"n":6,"rr":919,"mr":231},{"m":"ring-flash-linear-2.0","r":226,"s":72.04,"lo":203,"hi":303,"n":3,"rr":328,"mr":236},{"m":"ling-3.0-tiny","r":227,"s":72,"lo":176,"hi":389,"n":4,"rr":713,"mr":235},{"m":"claude-4.5-haiku","r":228,"s":72,"lo":90,"hi":276,"n":13,"rr":749,"mr":218},{"m":"deepseek-v3.2-exp","r":229,"s":71.95,"lo":165,"hi":553,"n":9,"rr":127,"mr":232},{"m":"minicpm-v-4.7-35b-a3b","r":230,"s":71.79,"lo":114,"hi":324,"n":5,"rr":173,"mr":264},{"m":"apriel-1.6-15b-thinker","r":231,"s":71.72,"lo":191,"hi":382,"n":6,"rr":355,"mr":241},{"m":"glm-4.5-air","r":232,"s":71.68,"lo":188,"hi":244,"n":16,"rr":237,"mr":213},{"m":"minimax-m2.1","r":233,"s":71.36,"lo":201,"hi":246,"n":6,"rr":425,"mr":226},{"m":"gemini-2.5-pro-preview-06-05","r":234,"s":71.32,"lo":137,"hi":276,"n":3,"rr":589,"mr":253},{"m":"hypernova-60b-2602","r":235,"s":71.28,"lo":194,"hi":467,"n":3,"rr":660,"mr":242},{"m":"nanbeige4-3b-thinking-2511","r":236,"s":71.28,"lo":190,"hi":375,"n":8,"rr":599,"mr":222},{"m":"sarvam-30b","r":237,"s":71.22,"lo":199,"hi":287,"n":7,"rr":169,"mr":223},{"m":"openreasoning-nemotron-14b","r":238,"s":71.13,"lo":201,"hi":252,"n":5,"rr":420,"mr":239},{"m":"ernie-4.5-vl-28b-a3b-thinking","r":239,"s":71.12,"lo":119,"hi":369,"n":4,"rr":105,"mr":276},{"m":"nemotron-cascade-14b-thinking","r":240,"s":71.09,"lo":192,"hi":384,"n":4,"rr":78,"mr":221},{"m":"nemotron-32b","r":241,"s":71.08,"lo":199,"hi":251,"n":6,"rr":449,"mr":240},{"m":"o4-mini-2025-04-16","r":242,"s":71.07,"lo":213,"hi":265,"n":3,"rr":641,"mr":255},{"m":"claude-4.5-haiku-thinking","r":243,"s":71.06,"lo":203,"hi":418,"n":3,"rr":568,"mr":251},{"m":"ministral-3-14b-reasoning","r":244,"s":71.04,"lo":199,"hi":263,"n":8,"rr":124,"mr":228},{"m":"gemini-3.5-flash-lite","r":245,"s":70.89,"lo":161,"hi":446,"n":8,"rr":642,"mr":214},{"m":"apriel-1.5-15b-thinker-self-reported","r":246,"s":70.84,"lo":223,"hi":424,"n":3,"rr":612,"mr":250},{"m":"gpt-5-nano-high","r":247,"s":70.8,"lo":208,"hi":306,"n":4,"rr":157,"mr":254},{"m":"qwen3-vl-32b-thinking","r":248,"s":70.62,"lo":199,"hi":272,"n":11,"rr":141,"mr":237},{"m":"qwen3-vl-30b-a3b-thinking","r":249,"s":70.43,"lo":216,"hi":267,"n":6,"rr":382,"mr":256},{"m":"claude-opus-4.1","r":250,"s":70.39,"lo":183,"hi":288,"n":9,"rr":371,"mr":262},{"m":"glm-4.5","r":251,"s":70.36,"lo":208,"hi":269,"n":9,"rr":541,"mr":238},{"m":"gpt-oss-20b","r":252,"s":70.29,"lo":180,"hi":322,"n":17,"rr":516,"mr":245},{"m":"minicpm5-2b","r":253,"s":70.13,"lo":201,"hi":344,"n":6,"rr":265,"mr":248},{"m":"falcon-h1r-7b","r":254,"s":70.06,"lo":206,"hi":270,"n":6,"rr":369,"mr":244},{"m":"ax-k1","r":255,"s":69.88,"lo":128,"hi":363,"n":6,"rr":1055,"mr":274},{"m":"k2-think","r":256,"s":69.84,"lo":204,"hi":270,"n":6,"rr":488,"mr":257},{"m":"gka-primed-hqwen3-32b-reasoner","r":257,"s":69.83,"lo":212,"hi":391,"n":4,"rr":645,"mr":252},{"m":"qwen3-max-instruct-preview","r":258,"s":69.8,"lo":216,"hi":339,"n":3,"rr":129,"mr":271},{"m":"qwen3.5-4b","r":259,"s":69.79,"lo":196,"hi":286,"n":25,"rr":412,"mr":246},{"m":"nemotron-cascade-8b-thinking","r":260,"s":69.76,"lo":203,"hi":432,"n":4,"rr":103,"mr":243},{"m":"nemotron-cascade-8b","r":261,"s":69.7,"lo":196,"hi":437,"n":4,"rr":111,"mr":247},{"m":"openpangu-2.0-flash","r":262,"s":69.6,"lo":215,"hi":297,"n":6,"rr":674,"mr":260},{"m":"qwen3-30b-a3b-2507","r":263,"s":69.59,"lo":197,"hi":319,"n":5,"rr":716,"mr":272},{"m":"k2-high-70b","r":264,"s":69.51,"lo":194,"hi":430,"n":5,"rr":76,"mr":258},{"m":"magistral-small-1.2","r":265,"s":69.36,"lo":226,"hi":329,"n":4,"rr":451,"mr":263},{"m":"apriel-1.5-15b-thinker","r":266,"s":69.19,"lo":220,"hi":290,"n":9,"rr":308,"mr":261},{"m":"exaone-4.0-32b","r":267,"s":69.15,"lo":252,"hi":452,"n":3,"rr":636,"mr":278},{"m":"motif-2-12.7b-reasoning","r":268,"s":69.05,"lo":180,"hi":313,"n":7,"rr":22,"mr":249},{"m":"gemma-4-12b-it","r":269,"s":68.76,"lo":219,"hi":287,"n":13,"rr":427,"mr":259},{"m":"seed-thinking-v1.5","r":270,"s":68.69,"lo":217,"hi":296,"n":4,"rr":54,"mr":265},{"m":"kolibri-origin","r":271,"s":68.65,"lo":240,"hi":354,"n":4,"rr":695,"mr":268},{"m":"minimax-m1-80k","r":272,"s":68.55,"lo":224,"hi":286,"n":4,"rr":68,"mr":267},{"m":"ministral-3-8b-reasoning","r":273,"s":68.49,"lo":226,"hi":378,"n":3,"rr":177,"mr":266},{"m":"ministral-3-r-8b","r":274,"s":68.49,"lo":227,"hi":379,"n":3,"rr":178,"mr":269},{"m":"golongrl-4b","r":275,"s":68.45,"lo":239,"hi":363,"n":3,"rr":167,"mr":270},{"m":"grok-3-mini","r":276,"s":68.31,"lo":122,"hi":355,"n":3,"rr":50,"mr":294},{"m":"minimax-m2","r":277,"s":68.24,"lo":233,"hi":397,"n":6,"rr":287,"mr":280},{"m":"gemini-2.5-flash-thinking","r":278,"s":68.21,"lo":192,"hi":296,"n":10,"rr":391,"mr":277},{"m":"ring-mini-sparse-2.0-exp","r":279,"s":68.1,"lo":238,"hi":323,"n":3,"rr":193,"mr":275},{"m":"openpangu-r-7b-2512-slow-thinking","r":280,"s":67.72,"lo":233,"hi":304,"n":5,"rr":367,"mr":273},{"m":"ovis2.6-30b-a3b","r":281,"s":67.64,"lo":194,"hi":497,"n":5,"rr":224,"mr":311},{"m":"llama-nemotron-super-49b-v1.5","r":282,"s":67.61,"lo":255,"hi":457,"n":3,"rr":657,"mr":295},{"m":"o3-mini","r":283,"s":67.6,"lo":184,"hi":314,"n":4,"rr":32,"mr":288},{"m":"gemini-2.5-flash-preview-09-2025","r":284,"s":67.42,"lo":185,"hi":367,"n":3,"rr":585,"mr":297},{"m":"qwen3-14b-thinking","r":285,"s":67.29,"lo":234,"hi":309,"n":4,"rr":104,"mr":282},{"m":"zgcm-1-7b","r":286,"s":67.01,"lo":249,"hi":309,"n":6,"rr":205,"mr":285},{"m":"gemini-2.5-flash","r":287,"s":67,"lo":240,"hi":318,"n":17,"rr":462,"mr":286},{"m":"jev-1.13","r":288,"s":66.98,"lo":199,"hi":434,"n":4,"rr":10,"mr":303},{"m":"qwen3-vl-8b-thinking","r":289,"s":66.77,"lo":250,"hi":336,"n":12,"rr":236,"mr":287},{"m":"qwen3-4b-2507","r":290,"s":66.65,"lo":256,"hi":372,"n":9,"rr":789,"mr":296},{"m":"qwen3-32b-thinking","r":291,"s":66.59,"lo":235,"hi":320,"n":12,"rr":517,"mr":284},{"m":"minimax-m1","r":292,"s":66.58,"lo":253,"hi":344,"n":3,"rr":207,"mr":298},{"m":"qwen3-next-80b-a3b-instruct","r":293,"s":66.52,"lo":226,"hi":322,"n":9,"rr":324,"mr":289},{"m":"minimax-m1-40k","r":294,"s":66.51,"lo":257,"hi":308,"n":4,"rr":93,"mr":293},{"m":"qwen3-30b-a3b","r":295,"s":66.48,"lo":236,"hi":375,"n":15,"rr":289,"mr":281},{"m":"gpt-oss-120b-medium","r":296,"s":66.44,"lo":260,"hi":306,"n":9,"rr":241,"mr":290},{"m":"qwen3-32b-thinking-2504","r":297,"s":66.38,"lo":274,"hi":351,"n":3,"rr":496,"mr":304},{"m":"openreasoning-nemotron-7b","r":298,"s":66.37,"lo":259,"hi":319,"n":13,"rr":483,"mr":291},{"m":"granite-4.2-3b","r":299,"s":66.33,"lo":251,"hi":359,"n":10,"rr":781,"mr":283},{"m":"qwen3-omni-flash-thinking","r":300,"s":66.22,"lo":237,"hi":318,"n":3,"rr":548,"mr":310},{"m":"deepseek-tng-r1t2-chimera","r":301,"s":66,"lo":246,"hi":343,"n":3,"rr":191,"mr":299},{"m":"llama-3.1-nemotron-ultra-253b-v1","r":302,"s":65.86,"lo":263,"hi":328,"n":3,"rr":197,"mr":300},{"m":"k2-think-v2","r":303,"s":65.82,"lo":170,"hi":485,"n":11,"rr":360,"mr":279},{"m":"nvidia-nemotron-nano-9b-v2","r":304,"s":65.75,"lo":246,"hi":342,"n":8,"rr":218,"mr":292},{"m":"lfm2.5-24b-a2b","r":305,"s":65.71,"lo":272,"hi":463,"n":3,"rr":456,"mr":312},{"m":"jev-1.14","r":306,"s":65.67,"lo":214,"hi":433,"n":4,"rr":14,"mr":323},{"m":"ming-flash-omni-2.0","r":307,"s":65.65,"lo":224,"hi":441,"n":3,"rr":188,"mr":348},{"m":"qwen3-4b-thinking-2507","r":308,"s":65.37,"lo":271,"hi":332,"n":12,"rr":665,"mr":301},{"m":"qwen3-omni-30b-a3b-thinking","r":309,"s":65.34,"lo":259,"hi":372,"n":5,"rr":309,"mr":331},{"m":"o3-mini-medium","r":310,"s":65.29,"lo":269,"hi":323,"n":4,"rr":343,"mr":309},{"m":"gemini-2.5-flash-preview-05-20","r":311,"s":65.21,"lo":287,"hi":419,"n":3,"rr":736,"mr":333},{"m":"glm-4.6v","r":312,"s":65.14,"lo":263,"hi":357,"n":8,"rr":372,"mr":314},{"m":"qwen3.5-omni-flash","r":313,"s":65.07,"lo":228,"hi":351,"n":8,"rr":394,"mr":330},{"m":"ovis2.6-80b-a3b","r":314,"s":64.95,"lo":222,"hi":609,"n":5,"rr":311,"mr":364},{"m":"gka-primed-hqwen3-8b-reasoner","r":315,"s":64.95,"lo":273,"hi":460,"n":4,"rr":809,"mr":307},{"m":"nemotron-labs-dory1.0-4b","r":316,"s":64.9,"lo":274,"hi":432,"n":3,"rr":1085,"mr":332},{"m":"gdn-primed-hqwen3-8b-reasoner","r":317,"s":64.84,"lo":274,"hi":463,"n":4,"rr":832,"mr":308},{"m":"deepseek-r1","r":318,"s":64.81,"lo":251,"hi":341,"n":12,"rr":727,"mr":306},{"m":"ling-1t","r":319,"s":64.8,"lo":259,"hi":350,"n":8,"rr":708,"mr":313},{"m":"deepseek-r1-0528-qwen3-8b","r":320,"s":64.8,"lo":273,"hi":343,"n":9,"rr":593,"mr":305},{"m":"glm-4.5v","r":321,"s":64.79,"lo":247,"hi":438,"n":7,"rr":304,"mr":354},{"m":"nemotron-labs-dory1.0-4b-4loop","r":322,"s":64.32,"lo":279,"hi":438,"n":3,"rr":1089,"mr":337},{"m":"olmo-3.1-think-32b","r":323,"s":64.08,"lo":274,"hi":357,"n":14,"rr":346,"mr":302},{"m":"gpt-oss-20b-medium","r":324,"s":64.06,"lo":295,"hi":365,"n":4,"rr":150,"mr":318},{"m":"qwq-32b","r":325,"s":64.02,"lo":256,"hi":378,"n":8,"rr":468,"mr":322},{"m":"instella-moe-16b-a3b-dpo","r":326,"s":64.01,"lo":280,"hi":367,"n":5,"rr":159,"mr":328},{"m":"kanana-2-30b-a3b-thinking-2601","r":327,"s":63.99,"lo":285,"hi":481,"n":3,"rr":376,"mr":315},{"m":"clef-flash","r":328,"s":63.93,"lo":177,"hi":501,"n":4,"rr":44,"mr":378},{"m":"qwen3-vl-30b-a3b-instruct","r":329,"s":63.76,"lo":250,"hi":349,"n":13,"rr":414,"mr":342},{"m":"vibethinker-1.5b","r":330,"s":63.76,"lo":281,"hi":374,"n":4,"rr":629,"mr":326},{"m":"claude-3.7-sonnet","r":331,"s":63.76,"lo":280,"hi":383,"n":9,"rr":617,"mr":343},{"m":"kanana-2-30b-a3b-thinking","r":332,"s":63.74,"lo":298,"hi":436,"n":3,"rr":358,"mr":321},{"m":"instella-moe-16b-a3b-think","r":333,"s":63.73,"lo":286,"hi":382,"n":5,"rr":170,"mr":334},{"m":"qwen3-vl-32b-instruct","r":334,"s":63.7,"lo":255,"hi":361,"n":10,"rr":245,"mr":325},{"m":"seed1.5-vl-thinking","r":335,"s":63.69,"lo":214,"hi":490,"n":4,"rr":214,"mr":377},{"m":"minicpm4.1-8b","r":336,"s":63.64,"lo":292,"hi":371,"n":6,"rr":373,"mr":320},{"m":"instella-moe-16b-a3b-sft","r":337,"s":63.29,"lo":289,"hi":389,"n":5,"rr":190,"mr":338},{"m":"olmo-3-think-32b-dpo","r":338,"s":63.26,"lo":275,"hi":376,"n":10,"rr":266,"mr":319},{"m":"o1-2024-12-17","r":339,"s":63.23,"lo":262,"hi":385,"n":6,"rr":378,"mr":341},{"m":"claude-opus-4","r":340,"s":63.19,"lo":229,"hi":464,"n":13,"rr":836,"mr":340},{"m":"qwen3-32b","r":341,"s":63.12,"lo":297,"hi":364,"n":19,"rr":442,"mr":317},{"m":"telechat3-36b-thinking","r":342,"s":63.11,"lo":307,"hi":360,"n":4,"rr":158,"mr":329},{"m":"diffusiongemma-26b-a4b","r":343,"s":62.96,"lo":235,"hi":401,"n":3,"rr":347,"mr":358},{"m":"ministral-3-3b-reasoning","r":344,"s":62.89,"lo":307,"hi":531,"n":3,"rr":461,"mr":336},{"m":"olmo-3-think-32b","r":345,"s":62.89,"lo":285,"hi":397,"n":10,"rr":242,"mr":316},{"m":"gemini-2.5-flash-lite-thinking","r":346,"s":62.87,"lo":324,"hi":528,"n":3,"rr":800,"mr":355},{"m":"o1","r":347,"s":62.86,"lo":285,"hi":378,"n":7,"rr":630,"mr":347},{"m":"qwen3-8b-thinking","r":348,"s":62.73,"lo":289,"hi":378,"n":9,"rr":499,"mr":327},{"m":"joyai-llm-flash","r":349,"s":62.63,"lo":258,"hi":407,"n":7,"rr":329,"mr":324},{"m":"deepseek-r1-0120","r":350,"s":62.56,"lo":279,"hi":381,"n":4,"rr":530,"mr":349},{"m":"ring-lite","r":351,"s":62.34,"lo":315,"hi":439,"n":3,"rr":422,"mr":352},{"m":"clef-omni","r":352,"s":62.28,"lo":199,"hi":513,"n":4,"rr":47,"mr":391},{"m":"seed-1.5-vl","r":353,"s":62.25,"lo":253,"hi":538,"n":6,"rr":465,"mr":366},{"m":"motif-2-12.7b-instruct","r":354,"s":62.07,"lo":264,"hi":390,"n":7,"rr":71,"mr":335},{"m":"qwen3-30b-a3b-instruct-2507","r":355,"s":62.02,"lo":276,"hi":379,"n":18,"rr":250,"mr":339},{"m":"phi-4-reasoning-plus","r":356,"s":61.92,"lo":328,"hi":379,"n":10,"rr":594,"mr":346},{"m":"longcat-flash-lite","r":357,"s":61.85,"lo":290,"hi":386,"n":5,"rr":184,"mr":344},{"m":"olmo-3-think-7b-dpo","r":358,"s":61.82,"lo":305,"hi":428,"n":6,"rr":463,"mr":345},{"m":"lg-exaone-32b","r":359,"s":61.75,"lo":270,"hi":413,"n":5,"rr":145,"mr":353},{"m":"ling-2.6-flash","r":360,"s":61.75,"lo":312,"hi":418,"n":3,"rr":726,"mr":356},{"m":"qwen3-vl-4b-thinking","r":361,"s":61.68,"lo":313,"hi":397,"n":6,"rr":269,"mr":357},{"m":"mimo-v2.5-pro-base","r":362,"s":61.67,"lo":215,"hi":465,"n":5,"rr":21,"mr":367},{"m":"magistral-medium-1.0","r":363,"s":61.41,"lo":325,"hi":375,"n":3,"rr":395,"mr":361},{"m":"magistral-medium","r":364,"s":61.4,"lo":326,"hi":376,"n":3,"rr":396,"mr":362},{"m":"magistral-medium-2506","r":365,"s":61.4,"lo":327,"hi":377,"n":3,"rr":397,"mr":363},{"m":"olmo-3-think-7b-sft","r":366,"s":61.24,"lo":312,"hi":424,"n":6,"rr":482,"mr":351},{"m":"longcat-next","r":367,"s":61.23,"lo":261,"hi":480,"n":3,"rr":176,"mr":396},{"m":"olmo-3-think-32b-sft","r":368,"s":61.05,"lo":306,"hi":393,"n":10,"rr":323,"mr":350},{"m":"qwen3-omni-flash-instruct","r":369,"s":60.97,"lo":299,"hi":402,"n":3,"rr":746,"mr":386},{"m":"openpangu-r-72b-2512-fast-thinking","r":370,"s":60.75,"lo":284,"hi":402,"n":5,"rr":614,"mr":359},{"m":"llama-4-maverick-17b-128e-instruct","r":371,"s":60.73,"lo":310,"hi":528,"n":3,"rr":142,"mr":402},{"m":"clef","r":372,"s":60.58,"lo":240,"hi":507,"n":4,"rr":53,"mr":398},{"m":"mimo-7b-rl","r":373,"s":60.56,"lo":323,"hi":398,"n":8,"rr":654,"mr":365},{"m":"deepseek-tng-r1t-chimera","r":374,"s":60.43,"lo":314,"hi":417,"n":3,"rr":439,"mr":379},{"m":"phi-4-reasoning","r":375,"s":60.42,"lo":331,"hi":401,"n":4,"rr":647,"mr":376},{"m":"kimi-k2-0905","r":376,"s":60.33,"lo":220,"hi":407,"n":7,"rr":971,"mr":389},{"m":"gemma-4-26b-a4b","r":377,"s":60.29,"lo":171,"hi":684,"n":9,"rr":385,"mr":360},{"m":"llada2.1-flash-q","r":378,"s":60.22,"lo":302,"hi":392,"n":6,"rr":230,"mr":372},{"m":"magistral-medium-1.1","r":379,"s":60.19,"lo":332,"hi":401,"n":3,"rr":445,"mr":380},{"m":"acereason-nemotron-1.1","r":380,"s":60.09,"lo":345,"hi":402,"n":3,"rr":699,"mr":383},{"m":"magistral-small-1.0","r":381,"s":59.88,"lo":354,"hi":398,"n":3,"rr":475,"mr":384},{"m":"kimi-k2-instruct","r":382,"s":59.73,"lo":284,"hi":416,"n":13,"rr":690,"mr":369},{"m":"apriel-nemotron-15b-thinker","r":383,"s":59.73,"lo":300,"hi":428,"n":5,"rr":211,"mr":375},{"m":"llada2.1-flash-s","r":384,"s":59.73,"lo":312,"hi":397,"n":6,"rr":254,"mr":381},{"m":"magistral-small-2506","r":385,"s":59.65,"lo":352,"hi":399,"n":4,"rr":671,"mr":388},{"m":"telechat3-105b-a4.7b-thinking","r":386,"s":59.65,"lo":335,"hi":432,"n":4,"rr":235,"mr":368},{"m":"vllm-sr-d3","r":387,"s":59.52,"lo":275,"hi":477,"n":4,"rr":37,"mr":399},{"m":"gpt-5.4-none","r":388,"s":59.51,"lo":285,"hi":460,"n":5,"rr":679,"mr":390},{"m":"magistral-small-1.1","r":389,"s":59.45,"lo":365,"hi":411,"n":3,"rr":521,"mr":392},{"m":"kimi-linear-instruct","r":390,"s":59.27,"lo":343,"hi":417,"n":6,"rr":381,"mr":373},{"m":"llada2.0-flash","r":391,"s":59.16,"lo":318,"hi":410,"n":10,"rr":90,"mr":371},{"m":"nemotron-research-goosereason-4b-instruct","r":392,"s":59.06,"lo":312,"hi":420,"n":7,"rr":286,"mr":382},{"m":"longcat-flash-lite-sparse","r":393,"s":58.93,"lo":348,"hi":426,"n":7,"rr":584,"mr":370},{"m":"deepseek-r1-distill-qwen-32b","r":394,"s":58.88,"lo":331,"hi":413,"n":6,"rr":450,"mr":385},{"m":"olmo-3-think-7b","r":395,"s":58.87,"lo":354,"hi":426,"n":15,"rr":490,"mr":374},{"m":"autotrust-jev-35b","r":396,"s":58.82,"lo":257,"hi":500,"n":4,"rr":52,"mr":413},{"m":"claude-sonnet-4","r":397,"s":58.8,"lo":305,"hi":481,"n":20,"rr":818,"mr":395},{"m":"ling-flash-2.0","r":398,"s":58.65,"lo":297,"hi":418,"n":10,"rr":84,"mr":393},{"m":"k2-medium-70b","r":399,"s":58.4,"lo":289,"hi":505,"n":5,"rr":379,"mr":394},{"m":"llama-nemotron-super-v1","r":400,"s":58.31,"lo":374,"hi":419,"n":3,"rr":565,"mr":397},{"m":"pplx-decider-v1.2","r":401,"s":58.24,"lo":300,"hi":479,"n":4,"rr":45,"mr":408},{"m":"questa-nemotron-1.5b","r":402,"s":58.13,"lo":367,"hi":414,"n":5,"rr":620,"mr":400},{"m":"qwen3-omni-30b-a3b-instruct","r":403,"s":58.1,"lo":348,"hi":457,"n":9,"rr":485,"mr":412},{"m":"openthinker3-7b","r":404,"s":57.88,"lo":347,"hi":460,"n":6,"rr":604,"mr":401},{"m":"nemotron-labs-dory1.0-4b-1loop","r":405,"s":57.79,"lo":360,"hi":527,"n":3,"rr":1130,"mr":407},{"m":"qwen3-14b","r":406,"s":57.47,"lo":345,"hi":483,"n":13,"rr":581,"mr":387},{"m":"llama-3.1-nemotron-nano-8b-v1","r":407,"s":57.2,"lo":294,"hi":449,"n":5,"rr":359,"mr":410},{"m":"hyperclovax-seed-think","r":408,"s":57.05,"lo":399,"hi":545,"n":3,"rr":933,"mr":403},{"m":"minicpm-v-4.5-8b","r":409,"s":56.99,"lo":315,"hi":509,"n":3,"rr":74,"mr":437},{"m":"kimi-k2","r":410,"s":56.9,"lo":342,"hi":455,"n":3,"rr":737,"mr":417},{"m":"gemini-2.5-flash-lite","r":411,"s":56.8,"lo":329,"hi":444,"n":11,"rr":424,"mr":406},{"m":"olmo-hybrid-think-7b-sft","r":412,"s":56.75,"lo":367,"hi":459,"n":6,"rr":628,"mr":404},{"m":"gpt-5-mini-medium","r":413,"s":56.48,"lo":183,"hi":459,"n":3,"rr":801,"mr":427},{"m":"gpt-5-nano","r":414,"s":56.39,"lo":306,"hi":478,"n":7,"rr":404,"mr":439},{"m":"o1-mini","r":415,"s":56.35,"lo":355,"hi":460,"n":5,"rr":301,"mr":415},{"m":"skywork-or1-7b","r":416,"s":56.23,"lo":368,"hi":452,"n":3,"rr":888,"mr":420},{"m":"glm-4.1v","r":417,"s":55.86,"lo":334,"hi":553,"n":6,"rr":509,"mr":443},{"m":"glide-no-thinking","r":418,"s":55.85,"lo":298,"hi":508,"n":4,"rr":59,"mr":430},{"m":"mimo-vl-7b-rl-2508","r":419,"s":55.75,"lo":342,"hi":565,"n":3,"rr":223,"mr":446},{"m":"spark-x2.5-1.7b","r":420,"s":55.37,"lo":371,"hi":595,"n":5,"rr":1010,"mr":409},{"m":"claude-3.7-sonnet-thinking","r":421,"s":55.36,"lo":330,"hi":504,"n":5,"rr":652,"mr":444},{"m":"deepseek-r1-distill-32b","r":422,"s":55.31,"lo":381,"hi":451,"n":5,"rr":756,"mr":425},{"m":"nemotron-3-nano-4b-thinking","r":423,"s":55.3,"lo":295,"hi":571,"n":7,"rr":969,"mr":422},{"m":"openpangu-r-7b-2512-fast-thinking","r":424,"s":55.29,"lo":396,"hi":477,"n":5,"rr":861,"mr":418},{"m":"ling-mini-2.0","r":425,"s":55.16,"lo":358,"hi":446,"n":7,"rr":597,"mr":426},{"m":"qwen3-4b","r":426,"s":55.15,"lo":383,"hi":569,"n":13,"rr":303,"mr":411},{"m":"llama-3.1-405b","r":427,"s":55.13,"lo":345,"hi":514,"n":6,"rr":137,"mr":405},{"m":"step-3","r":428,"s":55.03,"lo":316,"hi":568,"n":6,"rr":495,"mr":450},{"m":"youtu-llm-2b","r":429,"s":54.91,"lo":380,"hi":468,"n":4,"rr":590,"mr":419},{"m":"nemotron-3-nano-4b","r":430,"s":54.82,"lo":398,"hi":478,"n":6,"rr":745,"mr":414},{"m":"glm-4.1v-9b-thinking","r":431,"s":54.67,"lo":358,"hi":479,"n":3,"rr":239,"mr":453},{"m":"deepseek-v3-0324","r":432,"s":54.65,"lo":356,"hi":458,"n":10,"rr":719,"mr":421},{"m":"ministral-3-14b-instruct","r":433,"s":54.64,"lo":379,"hi":487,"n":3,"rr":144,"mr":429},{"m":"autotrust-jev-27b","r":434,"s":54.49,"lo":327,"hi":544,"n":4,"rr":89,"mr":436},{"m":"nemotron-h-47b-reasoning","r":435,"s":54.47,"lo":404,"hi":461,"n":6,"rr":849,"mr":424},{"m":"gemini-2.0-pro","r":436,"s":54.4,"lo":390,"hi":479,"n":7,"rr":256,"mr":433},{"m":"hunyuan-4b-instruct","r":437,"s":54.24,"lo":401,"hi":496,"n":6,"rr":854,"mr":428},{"m":"grok-3","r":438,"s":54.23,"lo":301,"hi":457,"n":4,"rr":318,"mr":432},{"m":"keye-vl-1.5-8b","r":439,"s":54.21,"lo":334,"hi":503,"n":3,"rr":97,"mr":459},{"m":"qwen3-8b","r":440,"s":54.13,"lo":385,"hi":478,"n":21,"rr":694,"mr":416},{"m":"olmo-3.1-instruct-32b","r":441,"s":53.76,"lo":388,"hi":575,"n":9,"rr":290,"mr":423},{"m":"glm-4.6v-flash","r":442,"s":53.66,"lo":337,"hi":660,"n":5,"rr":524,"mr":461},{"m":"manzano-30b","r":443,"s":53.49,"lo":314,"hi":520,"n":3,"rr":43,"mr":469},{"m":"vllm-sr-d3-flash","r":444,"s":53.32,"lo":342,"hi":517,"n":4,"rr":81,"mr":441},{"m":"ernie-4.5","r":445,"s":53.28,"lo":302,"hi":489,"n":6,"rr":165,"mr":431},{"m":"deepseek-r1-lite-preview","r":446,"s":53.1,"lo":351,"hi":496,"n":3,"rr":464,"mr":445},{"m":"qwen3-vl-8b-instruct","r":447,"s":53.05,"lo":408,"hi":478,"n":14,"rr":730,"mr":438},{"m":"o1-mini-2024-09-12","r":448,"s":52.88,"lo":420,"hi":477,"n":3,"rr":175,"mr":447},{"m":"nemotron-1.5b","r":449,"s":52.65,"lo":414,"hi":473,"n":5,"rr":869,"mr":442},{"m":"gemini-2.0-flash","r":450,"s":52.53,"lo":387,"hi":521,"n":4,"rr":595,"mr":456},{"m":"vllm-sr-decision-2.0-vega-27b","r":451,"s":52.41,"lo":350,"hi":582,"n":4,"rr":109,"mr":451},{"m":"trinity-mini","r":452,"s":51.98,"lo":428,"hi":496,"n":5,"rr":504,"mr":435},{"m":"exaone-4.0-1.2b","r":453,"s":51.85,"lo":426,"hi":550,"n":3,"rr":1025,"mr":454},{"m":"mimo-vl-7b-rl","r":454,"s":51.79,"lo":370,"hi":541,"n":4,"rr":662,"mr":479},{"m":"deepseek-v3","r":455,"s":51.67,"lo":393,"hi":534,"n":11,"rr":529,"mr":434},{"m":"llada2.1-mini-q","r":456,"s":51.49,"lo":405,"hi":479,"n":6,"rr":564,"mr":449},{"m":"lfm2.5-8b-a1b","r":457,"s":51.21,"lo":431,"hi":539,"n":6,"rr":865,"mr":440},{"m":"gpt-oss-120b-low","r":458,"s":51.14,"lo":428,"hi":530,"n":3,"rr":1012,"mr":463},{"m":"autotrust-gev-26b-decide","r":459,"s":51.13,"lo":360,"hi":563,"n":4,"rr":96,"mr":470},{"m":"qwen3-4b-instruct-2507","r":460,"s":51.11,"lo":416,"hi":562,"n":15,"rr":715,"mr":448},{"m":"pplx-decider-flash-v1.2","r":461,"s":50.97,"lo":359,"hi":565,"n":4,"rr":115,"mr":462},{"m":"exaone-deep-2.4b","r":462,"s":50.82,"lo":445,"hi":539,"n":3,"rr":1032,"mr":465},{"m":"qwq-32b-preview","r":463,"s":50.64,"lo":422,"hi":493,"n":3,"rr":432,"mr":464},{"m":"claude-opus-4.1-20250805","r":464,"s":50.52,"lo":181,"hi":525,"n":4,"rr":778,"mr":478},{"m":"aquif-3-moe-17b-a2.8b","r":465,"s":50.28,"lo":440,"hi":511,"n":3,"rr":179,"mr":475},{"m":"marco-mini-instruct","r":466,"s":50.23,"lo":399,"hi":537,"n":6,"rr":217,"mr":458},{"m":"gpt-4.1","r":467,"s":50.23,"lo":393,"hi":498,"n":13,"rr":720,"mr":452},{"m":"gpt-4.5","r":468,"s":50.14,"lo":304,"hi":531,"n":6,"rr":739,"mr":477},{"m":"qwen3-vl-4b-instruct","r":469,"s":49.74,"lo":444,"hi":557,"n":13,"rr":700,"mr":472},{"m":"llada2.1-mini-s","r":470,"s":49.69,"lo":417,"hi":517,"n":6,"rr":649,"mr":467},{"m":"vllm-sr-d3-mini","r":471,"s":49.68,"lo":379,"hi":565,"n":4,"rr":113,"mr":474},{"m":"mimo-vl-7b-sft","r":472,"s":49.39,"lo":400,"hi":565,"n":4,"rr":704,"mr":493},{"m":"tri-21b-think","r":473,"s":49.35,"lo":434,"hi":634,"n":3,"rr":982,"mr":468},{"m":"gemma-4-e4b-it","r":474,"s":48.88,"lo":442,"hi":544,"n":22,"rr":887,"mr":455},{"m":"lfm2.5-2.6b","r":475,"s":48.74,"lo":451,"hi":618,"n":6,"rr":925,"mr":457},{"m":"minicpm-v-4.6-thinking","r":476,"s":48.54,"lo":433,"hi":508,"n":5,"rr":491,"mr":503},{"m":"openpangu-vl-7b","r":477,"s":48.37,"lo":430,"hi":537,"n":5,"rr":380,"mr":473},{"m":"deepseek-r1-distill-qwen-7b","r":478,"s":48.27,"lo":446,"hi":732,"n":7,"rr":733,"mr":471},{"m":"qwen2.5-plus-1127","r":479,"s":48.26,"lo":429,"hi":535,"n":3,"rr":187,"mr":460},{"m":"llada2.0-mini","r":480,"s":48.17,"lo":413,"hi":555,"n":8,"rr":763,"mr":480},{"m":"openreasoning-nemotron-1.5b","r":481,"s":48.08,"lo":450,"hi":762,"n":7,"rr":989,"mr":476},{"m":"llama-4-maverick","r":482,"s":48.05,"lo":337,"hi":629,"n":7,"rr":847,"mr":494},{"m":"o1-preview","r":483,"s":47.75,"lo":450,"hi":542,"n":4,"rr":299,"mr":481},{"m":"gemma-3-27b","r":484,"s":47.54,"lo":448,"hi":577,"n":9,"rr":86,"mr":484},{"m":"nemotron-3-super-120b-a12b-base","r":485,"s":47.41,"lo":417,"hi":544,"n":12,"rr":298,"mr":483},{"m":"qwen3-vl-2b-thinking","r":486,"s":47.27,"lo":393,"hi":646,"n":3,"rr":270,"mr":518},{"m":"kolibri-1-base","r":487,"s":47.22,"lo":370,"hi":625,"n":4,"rr":28,"mr":497},{"m":"k2-v2","r":488,"s":47.21,"lo":443,"hi":682,"n":6,"rr":334,"mr":466},{"m":"qwen3.8-27b-iq2-xxs","r":489,"s":47.17,"lo":375,"hi":616,"n":4,"rr":229,"mr":486},{"m":"granite-4.1-30b","r":490,"s":46.82,"lo":358,"hi":664,"n":6,"rr":206,"mr":490},{"m":"nemotron-3.5-super-vl-120b-a12b-base","r":491,"s":46.77,"lo":385,"hi":574,"n":9,"rr":185,"mr":485},{"m":"kanana-2-30b-a3b-instruct-2601","r":492,"s":46.68,"lo":453,"hi":557,"n":4,"rr":135,"mr":482},{"m":"nemotron-3-ultra-base","r":493,"s":46.26,"lo":395,"hi":631,"n":7,"rr":168,"mr":501},{"m":"bespoke-nimble-9b-v3","r":494,"s":46.15,"lo":414,"hi":592,"n":4,"rr":114,"mr":498},{"m":"youtu-vl-4b-instruct","r":495,"s":46.07,"lo":276,"hi":678,"n":5,"rr":342,"mr":528},{"m":"claude-3.5-sonnet-20240620","r":496,"s":46.05,"lo":387,"hi":596,"n":5,"rr":149,"mr":487},{"m":"nova-pro","r":497,"s":45.89,"lo":463,"hi":573,"n":3,"rr":569,"mr":492},{"m":"bagel-7b-mot","r":498,"s":45.75,"lo":435,"hi":561,"n":3,"rr":411,"mr":539},{"m":"deepseek-r1-distill-llama-8b","r":499,"s":45.72,"lo":455,"hi":846,"n":6,"rr":782,"mr":489},{"m":"gemini-2.0-flash-001","r":500,"s":45.71,"lo":370,"hi":562,"n":3,"rr":431,"mr":510},{"m":"llada2.1-mini","r":501,"s":45.5,"lo":433,"hi":690,"n":3,"rr":911,"mr":500},{"m":"magistral-small-2509","r":502,"s":45.34,"lo":487,"hi":544,"n":3,"rr":212,"mr":507},{"m":"smollm3-3b","r":503,"s":45.29,"lo":470,"hi":629,"n":15,"rr":837,"mr":488},{"m":"gpt-4.1-2025-04-14","r":504,"s":45.28,"lo":293,"hi":899,"n":3,"rr":1033,"mr":522},{"m":"deepseek-v3.1","r":505,"s":45.1,"lo":316,"hi":594,"n":8,"rr":619,"mr":502},{"m":"gpt-5-minimal","r":506,"s":44.96,"lo":413,"hi":639,"n":7,"rr":841,"mr":523},{"m":"k2-horizon-0.9b","r":507,"s":44.77,"lo":475,"hi":782,"n":4,"rr":1121,"mr":491},{"m":"minicpm5-1b","r":508,"s":44.44,"lo":475,"hi":832,"n":6,"rr":1060,"mr":496},{"m":"nemotron-3.5-lightning-30b-a3b","r":509,"s":44.33,"lo":316,"hi":666,"n":9,"rr":582,"mr":495},{"m":"diffusiongemma-jev","r":510,"s":44.19,"lo":449,"hi":601,"n":4,"rr":128,"mr":516},{"m":"qwen2.5-vl-72b-instruct","r":511,"s":44.08,"lo":427,"hi":587,"n":4,"rr":561,"mr":560},{"m":"nemotron-3-nano-30b-a3b-base","r":512,"s":44.07,"lo":472,"hi":572,"n":8,"rr":94,"mr":499},{"m":"granite-4.1-8b","r":513,"s":43.85,"lo":371,"hi":622,"n":6,"rr":216,"mr":515},{"m":"qwen2.5-math-72b-instruct","r":514,"s":43.85,"lo":462,"hi":634,"n":7,"rr":480,"mr":506},{"m":"olmo-3.1-instruct-32b-dpo","r":515,"s":43.71,"lo":452,"hi":614,"n":6,"rr":904,"mr":505},{"m":"kimi-vl-a3b-thinking-2506","r":516,"s":43.59,"lo":413,"hi":820,"n":6,"rr":770,"mr":566},{"m":"mistral-3.2-24b","r":517,"s":43.59,"lo":460,"hi":592,"n":6,"rr":92,"mr":520},{"m":"claude-sonnet-4-20250514","r":518,"s":43.51,"lo":257,"hi":911,"n":3,"rr":1048,"mr":547},{"m":"ling-3.0-flash-base","r":519,"s":43.5,"lo":412,"hi":629,"n":4,"rr":458,"mr":534},{"m":"hunyuan-large-instruct","r":520,"s":43.43,"lo":410,"hi":641,"n":4,"rr":203,"mr":536},{"m":"kimi-vl-a3b-thinking","r":521,"s":43.28,"lo":383,"hi":661,"n":4,"rr":562,"mr":569},{"m":"k2-low-70b","r":522,"s":43.26,"lo":421,"hi":595,"n":5,"rr":840,"mr":504},{"m":"openpangu-r-7b-diffusion","r":523,"s":43.2,"lo":491,"hi":582,"n":3,"rr":33,"mr":509},{"m":"trinity-large-preview","r":524,"s":43.01,"lo":382,"hi":618,"n":3,"rr":752,"mr":512},{"m":"ling-2.6-1t-base","r":525,"s":42.92,"lo":475,"hi":579,"n":7,"rr":615,"mr":535},{"m":"llada2.2-mini","r":526,"s":42.88,"lo":455,"hi":745,"n":3,"rr":981,"mr":531},{"m":"llama-4-scout-17b-16e","r":527,"s":42.79,"lo":417,"hi":949,"n":4,"rr":828,"mr":568},{"m":"kanana-2-30b-a3b-instruct","r":528,"s":42.73,"lo":479,"hi":647,"n":4,"rr":210,"mr":513},{"m":"g9v3-3b","r":529,"s":42.7,"lo":482,"hi":685,"n":4,"rr":1191,"mr":524},{"m":"qwen2.5-vl-72b","r":530,"s":42.64,"lo":450,"hi":583,"n":3,"rr":469,"mr":585},{"m":"mobilellm-r1.5-950m","r":531,"s":42.58,"lo":493,"hi":698,"n":4,"rr":702,"mr":511},{"m":"bespoke-nimble-9b-v2","r":532,"s":42.55,"lo":459,"hi":632,"n":4,"rr":154,"mr":532},{"m":"autotrust-jev-9b","r":533,"s":42.52,"lo":446,"hi":664,"n":4,"rr":180,"mr":533},{"m":"vllm-sr-decision-2.0-lux-9b","r":534,"s":42.37,"lo":450,"hi":663,"n":4,"rr":174,"mr":538},{"m":"qwen3.5-35b-a3b-base","r":535,"s":42.31,"lo":425,"hi":621,"n":7,"rr":322,"mr":526},{"m":"qwen-turbo-0919","r":536,"s":42.3,"lo":503,"hi":586,"n":3,"rr":280,"mr":508},{"m":"qwen2.5-turbo","r":537,"s":42.28,"lo":498,"hi":618,"n":3,"rr":294,"mr":546},{"m":"motif-3-base","r":538,"s":42.19,"lo":454,"hi":607,"n":4,"rr":30,"mr":530},{"m":"alodlm-8b","r":539,"s":42.14,"lo":497,"hi":602,"n":6,"rr":70,"mr":519},{"m":"grok-4-fast-thinking","r":540,"s":42.11,"lo":474,"hi":669,"n":3,"rr":519,"mr":596},{"m":"nova-lite","r":541,"s":42.05,"lo":490,"hi":619,"n":3,"rr":613,"mr":537},{"m":"gpt-4o-0327","r":542,"s":42.04,"lo":370,"hi":647,"n":3,"rr":1081,"mr":553},{"m":"kimi-k2-base","r":543,"s":42,"lo":449,"hi":611,"n":10,"rr":314,"mr":540},{"m":"gemma-3-27b-it","r":544,"s":41.88,"lo":493,"hi":637,"n":15,"rr":811,"mr":521},{"m":"keye-vl-8b","r":545,"s":41.82,"lo":435,"hi":867,"n":3,"rr":970,"mr":602},{"m":"olmo-3-instruct-7b","r":546,"s":41.77,"lo":483,"hi":704,"n":11,"rr":693,"mr":514},{"m":"hy3-preview-base","r":547,"s":41.77,"lo":488,"hi":646,"n":9,"rr":374,"mr":544},{"m":"gemma-4-e2b-it","r":548,"s":41.76,"lo":507,"hi":665,"n":19,"rr":949,"mr":517},{"m":"qwen3-8b-non-thinking","r":549,"s":41.57,"lo":477,"hi":644,"n":10,"rr":956,"mr":552},{"m":"nemotron-3.5-lightning-30b-a3b-base","r":550,"s":41.46,"lo":398,"hi":618,"n":5,"rr":143,"mr":542},{"m":"mimo-v2-flash-base","r":551,"s":41.41,"lo":472,"hi":601,"n":7,"rr":410,"mr":529},{"m":"qwen3-235b-a22b-base","r":552,"s":41.4,"lo":472,"hi":616,"n":5,"rr":416,"mr":555},{"m":"llama-3.1-tulu-3-405b","r":553,"s":41.37,"lo":419,"hi":669,"n":3,"rr":61,"mr":543},{"m":"llama-3.1-405b-instruct-fp8","r":554,"s":41.29,"lo":434,"hi":657,"n":3,"rr":300,"mr":545},{"m":"qwen-3-235b-a22b-nonthinking","r":555,"s":41.28,"lo":410,"hi":646,"n":3,"rr":1098,"mr":570},{"m":"hunyuan-large","r":556,"s":41.25,"lo":470,"hi":610,"n":5,"rr":24,"mr":556},{"m":"claude-3.5-sonnet","r":557,"s":41.24,"lo":397,"hi":662,"n":10,"rr":454,"mr":573},{"m":"mistral-small-3.1-24b-instruct","r":558,"s":41.19,"lo":494,"hi":615,"n":6,"rr":91,"mr":565},{"m":"claude-3-sonnet","r":559,"s":41.16,"lo":448,"hi":832,"n":3,"rr":192,"mr":567},{"m":"mistral-medium-3","r":560,"s":41.13,"lo":473,"hi":636,"n":6,"rr":942,"mr":548},{"m":"mistral-large-instruct-2407","r":561,"s":41.04,"lo":455,"hi":606,"n":4,"rr":189,"mr":527},{"m":"phi-4-14b","r":562,"s":40.79,"lo":478,"hi":626,"n":3,"rr":259,"mr":572},{"m":"minicpm-v-4.6","r":563,"s":40.63,"lo":473,"hi":633,"n":6,"rr":722,"mr":609},{"m":"qwen2.5-max","r":564,"s":40.53,"lo":411,"hi":655,"n":3,"rr":55,"mr":583},{"m":"qwen2.5-14b-instruct","r":565,"s":40.43,"lo":491,"hi":891,"n":5,"rr":255,"mr":525},{"m":"gpt-4o-2024-08-06","r":566,"s":40.29,"lo":465,"hi":837,"n":9,"rr":721,"mr":563},{"m":"minicpm-o-4.5","r":567,"s":40.14,"lo":446,"hi":657,"n":5,"rr":62,"mr":558},{"m":"llama-3.1-405b-instruct","r":568,"s":40.1,"lo":410,"hi":656,"n":8,"rr":406,"mr":541},{"m":"gpt-4-turbo-2024-04-09","r":569,"s":40.1,"lo":433,"hi":714,"n":8,"rr":415,"mr":551},{"m":"seed1.6","r":570,"s":39.94,"lo":473,"hi":629,"n":5,"rr":430,"mr":575},{"m":"qwen2-math-72b-instruct","r":571,"s":39.6,"lo":481,"hi":691,"n":7,"rr":640,"mr":571},{"m":"llada2.0-flash-preview","r":572,"s":39.58,"lo":535,"hi":624,"n":7,"rr":543,"mr":549},{"m":"internvl3.5-8b","r":573,"s":39.56,"lo":423,"hi":779,"n":6,"rr":474,"mr":618},{"m":"qwen3-32b-nothinking","r":574,"s":39.41,"lo":510,"hi":677,"n":8,"rr":1069,"mr":564},{"m":"manzano-3b","r":575,"s":39.4,"lo":477,"hi":627,"n":3,"rr":82,"mr":634},{"m":"sdar-8b-chat","r":576,"s":39.3,"lo":539,"hi":616,"n":3,"rr":63,"mr":593},{"m":"llama-3.3-70b-instruct","r":577,"s":39.22,"lo":476,"hi":699,"n":6,"rr":156,"mr":589},{"m":"qwen2.5-72b-instruct","r":578,"s":39.21,"lo":497,"hi":686,"n":11,"rr":637,"mr":550},{"m":"aquif-3.5-nano-1b","r":579,"s":39.21,"lo":538,"hi":729,"n":3,"rr":966,"mr":561},{"m":"kev-9b","r":580,"s":39.16,"lo":478,"hi":692,"n":4,"rr":199,"mr":574},{"m":"gemini-1.5-flash","r":581,"s":39.15,"lo":512,"hi":645,"n":6,"rr":402,"mr":562},{"m":"ling-1t-base","r":582,"s":39.11,"lo":515,"hi":635,"n":7,"rr":677,"mr":595},{"m":"deepseek-r1-distill-qwen-1.5b","r":583,"s":39.06,"lo":518,"hi":723,"n":6,"rr":822,"mr":559},{"m":"ling-2.6-flash-base","r":584,"s":39.02,"lo":533,"hi":645,"n":7,"rr":718,"mr":586},{"m":"phi-4-reasoning-vision-15b","r":585,"s":38.97,"lo":447,"hi":677,"n":3,"rr":440,"mr":638},{"m":"kanana-1.5-32.5b-instruct","r":586,"s":38.93,"lo":539,"hi":638,"n":4,"rr":267,"mr":590},{"m":"deepseek-v4-pro-base","r":587,"s":38.9,"lo":470,"hi":657,"n":6,"rr":122,"mr":577},{"m":"minicpm-v-4.7-1b","r":588,"s":38.83,"lo":453,"hi":686,"n":3,"rr":821,"mr":630},{"m":"qwen2.5-math-7b-instruct","r":589,"s":38.55,"lo":510,"hi":710,"n":7,"rr":675,"mr":599},{"m":"deepseek-v3-base","r":590,"s":38.44,"lo":461,"hi":654,"n":9,"rr":182,"mr":604},{"m":"deepseek-v4-flash-base","r":591,"s":38.37,"lo":503,"hi":668,"n":7,"rr":166,"mr":580},{"m":"qwen3-8b-instruct","r":592,"s":38.33,"lo":546,"hi":637,"n":6,"rr":183,"mr":578},{"m":"ling-2.5-flash-base","r":593,"s":38.3,"lo":489,"hi":699,"n":4,"rr":672,"mr":613},{"m":"nova-micro","r":594,"s":38.29,"lo":555,"hi":647,"n":3,"rr":643,"mr":584},{"m":"gpt-4o","r":595,"s":37.68,"lo":487,"hi":678,"n":20,"rr":820,"mr":594},{"m":"gpt-4.1-nano","r":596,"s":37.67,"lo":540,"hi":722,"n":4,"rr":338,"mr":623},{"m":"llama-3.1-tulu-3-405b-dpo","r":597,"s":37.55,"lo":434,"hi":721,"n":3,"rr":102,"mr":640},{"m":"gpt-4o-2024-11-24","r":598,"s":37.52,"lo":410,"hi":650,"n":3,"rr":64,"mr":587},{"m":"lfm2.5-1.2b-thinking","r":599,"s":37.47,"lo":522,"hi":763,"n":7,"rr":999,"mr":557},{"m":"gpt-4o-mini","r":600,"s":37.43,"lo":522,"hi":675,"n":5,"rr":429,"mr":576},{"m":"tev1-4b-experimental","r":601,"s":37.41,"lo":507,"hi":703,"n":4,"rr":202,"mr":605},{"m":"claude-3.5-sonnet-20241022","r":602,"s":37.34,"lo":433,"hi":771,"n":9,"rr":754,"mr":579},{"m":"gemma-3-12b-it","r":603,"s":37.32,"lo":545,"hi":691,"n":16,"rr":769,"mr":582},{"m":"llama-4-scout-17b","r":604,"s":37.11,"lo":517,"hi":749,"n":12,"rr":794,"mr":581},{"m":"olmo-3-instruct-7b-dpo","r":605,"s":37.07,"lo":562,"hi":701,"n":6,"rr":1052,"mr":597},{"m":"nemotron-labs-twotower-30b-a3b-base","r":606,"s":37.05,"lo":564,"hi":646,"n":5,"rr":48,"mr":598},{"m":"llama-3.1-tulu-3-405b-sft","r":607,"s":37.05,"lo":485,"hi":701,"n":3,"rr":98,"mr":637},{"m":"deepseek-v3.2-exp-base","r":608,"s":37,"lo":501,"hi":699,"n":8,"rr":435,"mr":625},{"m":"joyai-llm-flash-base","r":609,"s":36.97,"lo":537,"hi":684,"n":4,"rr":73,"mr":601},{"m":"lfm2-350m-math","r":610,"s":36.94,"lo":562,"hi":693,"n":5,"rr":1016,"mr":607},{"m":"qwen2.5-32b-instruct","r":611,"s":36.93,"lo":519,"hi":714,"n":12,"rr":772,"mr":591},{"m":"deepseek-v3.2-base","r":612,"s":36.89,"lo":510,"hi":680,"n":6,"rr":198,"mr":614},{"m":"wedlm-8b-instruct","r":613,"s":36.86,"lo":563,"hi":662,"n":7,"rr":148,"mr":588},{"m":"ministral-3-8b-instruct","r":614,"s":36.86,"lo":486,"hi":702,"n":6,"rr":520,"mr":608},{"m":"vllm-sr-decision-2.0-nox-4b","r":615,"s":36.84,"lo":485,"hi":772,"n":4,"rr":271,"mr":617},{"m":"llama-3-70b","r":616,"s":36.75,"lo":520,"hi":826,"n":5,"rr":377,"mr":554},{"m":"llama-3.1-tulu-3-70b","r":617,"s":36.55,"lo":497,"hi":703,"n":3,"rr":112,"mr":603},{"m":"qwen3-1.7b","r":618,"s":36.46,"lo":529,"hi":749,"n":20,"rr":897,"mr":592},{"m":"llama-4-maverick-17b-128e-base","r":619,"s":36.45,"lo":342,"hi":711,"n":3,"rr":120,"mr":656},{"m":"qwen-2.5-72b","r":620,"s":36.43,"lo":515,"hi":675,"n":12,"rr":505,"mr":600},{"m":"llama-3.1-tulu-3-70b-dpo","r":621,"s":36.38,"lo":496,"hi":706,"n":3,"rr":118,"mr":646},{"m":"ling-flash-base-2.0","r":622,"s":36.29,"lo":569,"hi":702,"n":12,"rr":684,"mr":628},{"m":"gpt-5.4-mini-none","r":623,"s":36.24,"lo":575,"hi":769,"n":3,"rr":1188,"mr":611},{"m":"glm-4.5-base","r":624,"s":36.22,"lo":470,"hi":689,"n":9,"rr":332,"mr":633},{"m":"gemini-1.5-pro","r":625,"s":36.21,"lo":486,"hi":750,"n":14,"rr":680,"mr":606},{"m":"deepseek-coder-v2-instruct","r":626,"s":36.2,"lo":547,"hi":693,"n":9,"rr":542,"mr":620},{"m":"gemini-1.5-pro-002","r":627,"s":35.9,"lo":402,"hi":726,"n":4,"rr":958,"mr":639},{"m":"qwen2.5-coder-32b-instruct","r":628,"s":35.86,"lo":573,"hi":725,"n":8,"rr":717,"mr":621},{"m":"gpt-5-nano-minimal","r":629,"s":35.78,"lo":552,"hi":971,"n":7,"rr":1100,"mr":663},{"m":"deepseek-v4.1-flash-base","r":630,"s":35.75,"lo":517,"hi":707,"n":4,"rr":316,"mr":635},{"m":"qwen2-72b-instruct","r":631,"s":35.68,"lo":567,"hi":740,"n":9,"rr":497,"mr":610},{"m":"gpt-4o-2024-05-13","r":632,"s":35.45,"lo":509,"hi":709,"n":13,"rr":663,"mr":626},{"m":"deepseek-v2.5","r":633,"s":35.42,"lo":533,"hi":712,"n":7,"rr":673,"mr":616},{"m":"deepseek-v3.1-base","r":634,"s":35.38,"lo":513,"hi":694,"n":5,"rr":540,"mr":647},{"m":"llama-3.1-70b-instruct","r":635,"s":35.37,"lo":547,"hi":727,"n":10,"rr":525,"mr":627},{"m":"skywork-o1-open-llama-3.1-8b","r":636,"s":35.36,"lo":555,"hi":735,"n":5,"rr":806,"mr":643},{"m":"glm-4-0520","r":637,"s":35.23,"lo":529,"hi":708,"n":4,"rr":405,"mr":612},{"m":"phi-3-medium-4k-instruct","r":638,"s":35.12,"lo":566,"hi":719,"n":4,"rr":249,"mr":622},{"m":"falcon-h1-34b-instruct","r":639,"s":35.11,"lo":563,"hi":728,"n":9,"rr":779,"mr":619},{"m":"seed1.5","r":640,"s":35,"lo":566,"hi":674,"n":5,"rr":544,"mr":651},{"m":"internvl3.5-4b","r":641,"s":34.89,"lo":506,"hi":893,"n":7,"rr":780,"mr":681},{"m":"qwen2.5-math-72b","r":642,"s":34.86,"lo":585,"hi":668,"n":3,"rr":67,"mr":632},{"m":"hermes-3-llama-3.1-405b","r":643,"s":34.77,"lo":471,"hi":733,"n":3,"rr":139,"mr":631},{"m":"claude-3-opus","r":644,"s":34.69,"lo":421,"hi":777,"n":10,"rr":550,"mr":629},{"m":"llada2.0-mini-preview","r":645,"s":34.67,"lo":598,"hi":689,"n":3,"rr":153,"mr":659},{"m":"phi-3-small-8k-instruct","r":646,"s":34.66,"lo":594,"hi":667,"n":3,"rr":40,"mr":649},{"m":"yuan2.0-m32","r":647,"s":34.6,"lo":488,"hi":736,"n":4,"rr":131,"mr":615},{"m":"mimo-v2.5-base","r":648,"s":34.47,"lo":554,"hi":740,"n":8,"rr":535,"mr":645},{"m":"mistral-large-3-base","r":649,"s":34.43,"lo":528,"hi":701,"n":9,"rr":478,"mr":636},{"m":"jamba-1.5-large","r":650,"s":34.33,"lo":543,"hi":705,"n":3,"rr":35,"mr":666},{"m":"qwen2-math-7b-instruct","r":651,"s":34.29,"lo":586,"hi":745,"n":7,"rr":764,"mr":642},{"m":"step-3.5-flash-base-midtrain","r":652,"s":34.2,"lo":560,"hi":676,"n":5,"rr":571,"mr":641},{"m":"mistral-small-3.2-24b-instruct","r":653,"s":33.97,"lo":563,"hi":734,"n":6,"rr":326,"mr":662},{"m":"step-3.5-flash-base","r":654,"s":33.93,"lo":595,"hi":749,"n":9,"rr":696,"mr":650},{"m":"intern-decision-4b","r":655,"s":33.83,"lo":555,"hi":747,"n":4,"rr":215,"mr":648},{"m":"apertus-v1.5-70b-thinking","r":656,"s":33.75,"lo":616,"hi":726,"n":7,"rr":859,"mr":644},{"m":"lfm2-24b-a2b","r":657,"s":33.58,"lo":524,"hi":766,"n":6,"rr":602,"mr":652},{"m":"qwen3-30b-a3b-base","r":658,"s":33.55,"lo":610,"hi":695,"n":5,"rr":368,"mr":658},{"m":"qwen3-1.7b-thinking","r":659,"s":33.51,"lo":570,"hi":764,"n":8,"rr":1077,"mr":653},{"m":"kanana-1.5-o-9.8b-instruct-2602","r":660,"s":33.48,"lo":536,"hi":767,"n":3,"rr":915,"mr":709},{"m":"marco-nano-instruct","r":661,"s":33.31,"lo":567,"hi":769,"n":6,"rr":670,"mr":665},{"m":"internvl3.5-2b","r":662,"s":33.15,"lo":488,"hi":789,"n":3,"rr":361,"mr":716},{"m":"gpt-5-mini-minimal","r":663,"s":33.13,"lo":512,"hi":804,"n":4,"rr":813,"mr":714},{"m":"llama-4-maverick-base","r":664,"s":33.08,"lo":593,"hi":699,"n":5,"rr":588,"mr":671},{"m":"llama-3.2v-90b-instruct","r":665,"s":32.95,"lo":365,"hi":781,"n":3,"rr":575,"mr":724},{"m":"motif-2-12.7b-base","r":666,"s":32.89,"lo":560,"hi":926,"n":8,"rr":563,"mr":660},{"m":"phi-3.5-moe-instruct","r":667,"s":32.79,"lo":587,"hi":734,"n":4,"rr":276,"mr":654},{"m":"molmo-72b","r":668,"s":32.75,"lo":281,"hi":831,"n":3,"rr":336,"mr":729},{"m":"midm-2.0-base-instruct","r":669,"s":32.67,"lo":583,"hi":810,"n":3,"rr":511,"mr":694},{"m":"internlm2-math-plus-mixtral8x22b","r":670,"s":32.65,"lo":548,"hi":735,"n":3,"rr":639,"mr":664},{"m":"apertus-v1.5-8b-thinking","r":671,"s":32.63,"lo":630,"hi":742,"n":7,"rr":882,"mr":661},{"m":"olmo-3-32b","r":672,"s":32.54,"lo":503,"hi":796,"n":4,"rr":238,"mr":673},{"m":"deepseek-v2-chat-sft","r":673,"s":32.49,"lo":588,"hi":748,"n":6,"rr":69,"mr":655},{"m":"granite-4.0-h-small","r":674,"s":32.35,"lo":556,"hi":820,"n":10,"rr":799,"mr":670},{"m":"minicpm4-8b","r":675,"s":32.28,"lo":605,"hi":799,"n":4,"rr":23,"mr":693},{"m":"qwen3.5-2b","r":676,"s":32.26,"lo":558,"hi":802,"n":24,"rr":941,"mr":624},{"m":"qwen2.5-math-1.5b-instruct","r":677,"s":32.26,"lo":585,"hi":797,"n":7,"rr":824,"mr":669},{"m":"glm-4-air-0605","r":678,"s":32.08,"lo":599,"hi":737,"n":4,"rr":473,"mr":657},{"m":"qwen2.5-coder-14b-instruct","r":679,"s":32.01,"lo":588,"hi":796,"n":7,"rr":877,"mr":674},{"m":"pixtral-12b","r":680,"s":31.99,"lo":292,"hi":841,"n":3,"rr":388,"mr":740},{"m":"gpt-4","r":681,"s":31.78,"lo":616,"hi":740,"n":6,"rr":669,"mr":672},{"m":"gpt-4-0314","r":682,"s":31.76,"lo":518,"hi":780,"n":4,"rr":494,"mr":676},{"m":"lfm2-8b-a1b","r":683,"s":31.68,"lo":599,"hi":766,"n":10,"rr":812,"mr":667},{"m":"llama-3.1-405b-base","r":684,"s":31.46,"lo":470,"hi":765,"n":7,"rr":87,"mr":668},{"m":"gpt-4-1106-preview","r":685,"s":31.46,"lo":464,"hi":956,"n":5,"rr":755,"mr":682},{"m":"gemini-1.5-flash-002","r":686,"s":31.43,"lo":474,"hi":776,"n":3,"rr":724,"mr":702},{"m":"ling-3.0-tiny-base","r":687,"s":31.36,"lo":601,"hi":794,"n":4,"rr":866,"mr":692},{"m":"llama-3.1-tulu-3-70b-sft","r":688,"s":31.06,"lo":568,"hi":774,"n":3,"rr":231,"mr":715},{"m":"qwen2-math-72b","r":689,"s":31.02,"lo":637,"hi":720,"n":3,"rr":140,"mr":677},{"m":"ling-2.5-mini-base","r":690,"s":30.88,"lo":629,"hi":771,"n":4,"rr":868,"mr":707},{"m":"granite-4.1-3b","r":691,"s":30.85,"lo":491,"hi":821,"n":6,"rr":566,"mr":697},{"m":"abab6.5","r":692,"s":30.84,"lo":562,"hi":791,"n":3,"rr":258,"mr":679},{"m":"qwen2.5-math-7b","r":693,"s":30.79,"lo":597,"hi":758,"n":3,"rr":172,"mr":691},{"m":"internlm2_5-20b-chat","r":694,"s":30.65,"lo":654,"hi":732,"n":4,"rr":554,"mr":690},{"m":"llama-3.3-70b","r":695,"s":30.61,"lo":480,"hi":839,"n":10,"rr":762,"mr":675},{"m":"llm-jp-4-vl-9b","r":696,"s":30.49,"lo":623,"hi":943,"n":4,"rr":862,"mr":695},{"m":"qwen2.5-7b-instruct","r":697,"s":30.34,"lo":618,"hi":848,"n":10,"rr":994,"mr":687},{"m":"numinamath-72b-cot","r":698,"s":30.31,"lo":645,"hi":908,"n":7,"rr":906,"mr":689},{"m":"molmo2-4b","r":699,"s":30.29,"lo":280,"hi":866,"n":3,"rr":401,"mr":761},{"m":"qvq-72b","r":700,"s":30.29,"lo":503,"hi":781,"n":3,"rr":1043,"mr":744},{"m":"xverse-moe-a36b","r":701,"s":30.19,"lo":586,"hi":776,"n":3,"rr":233,"mr":684},{"m":"falcon-h1-7b","r":702,"s":30.13,"lo":640,"hi":783,"n":9,"rr":885,"mr":678},{"m":"qwen3-6b","r":703,"s":30.1,"lo":652,"hi":791,"n":5,"rr":1113,"mr":700},{"m":"gemini-1.0-ultra","r":704,"s":29.99,"lo":502,"hi":788,"n":4,"rr":386,"mr":718},{"m":"qwen-2.5-3b-instruct","r":705,"s":29.95,"lo":657,"hi":776,"n":3,"rr":681,"mr":680},{"m":"mixtral-8x22b-instruct-v0.1","r":706,"s":29.92,"lo":625,"hi":781,"n":7,"rr":209,"mr":686},{"m":"mobilellm-r1-950m","r":707,"s":29.83,"lo":628,"hi":867,"n":7,"rr":1009,"mr":688},{"m":"olmo-3.1-instruct-32b-sft","r":708,"s":29.72,"lo":602,"hi":829,"n":6,"rr":1095,"mr":703},{"m":"trinity-large-base","r":709,"s":29.7,"lo":598,"hi":932,"n":5,"rr":399,"mr":704},{"m":"claude-3-opus-20240229","r":710,"s":29.69,"lo":418,"hi":851,"n":4,"rr":616,"mr":721},{"m":"llama-4-scout-17b-16e-base","r":711,"s":29.68,"lo":417,"hi":794,"n":3,"rr":272,"mr":743},{"m":"aquif-3.5-2.7b","r":712,"s":29.65,"lo":678,"hi":813,"n":3,"rr":1079,"mr":725},{"m":"olmo-hybrid-instruct-7b-dpo","r":713,"s":29.51,"lo":624,"hi":814,"n":6,"rr":1108,"mr":705},{"m":"qwen2.5-coder-32b","r":714,"s":29.49,"lo":586,"hi":880,"n":4,"rr":234,"mr":736},{"m":"gpt-4o-mini-2024-07-18","r":715,"s":29.42,"lo":503,"hi":838,"n":5,"rr":632,"mr":734},{"m":"llada2.0-uni","r":716,"s":29.4,"lo":560,"hi":824,"n":3,"rr":711,"mr":768},{"m":"yi-1.5-34b-chat","r":717,"s":29.19,"lo":593,"hi":799,"n":3,"rr":296,"mr":728},{"m":"vllm-sr-d3-nano","r":718,"s":29.11,"lo":620,"hi":830,"n":4,"rr":340,"mr":711},{"m":"mm1.5-30b","r":719,"s":29,"lo":508,"hi":806,"n":3,"rr":222,"mr":785},{"m":"kimi-linear-base","r":720,"s":28.98,"lo":677,"hi":742,"n":4,"rr":459,"mr":713},{"m":"yi-large-preview","r":721,"s":28.96,"lo":624,"hi":770,"n":3,"rr":626,"mr":699},{"m":"internlm2.5-7b-chat","r":722,"s":28.95,"lo":671,"hi":738,"n":4,"rr":580,"mr":719},{"m":"claude-3-haiku","r":723,"s":28.94,"lo":544,"hi":1017,"n":4,"rr":492,"mr":751},{"m":"qwen3.5-4b-base","r":724,"s":28.93,"lo":599,"hi":837,"n":10,"rr":472,"mr":730},{"m":"qwen3-8b-base","r":725,"s":28.86,"lo":668,"hi":776,"n":6,"rr":587,"mr":732},{"m":"llama-3.1-70b","r":726,"s":28.78,"lo":473,"hi":1018,"n":8,"rr":710,"mr":685},{"m":"qwen2.5-32b-base","r":727,"s":28.66,"lo":588,"hi":1039,"n":7,"rr":443,"mr":696},{"m":"baichuan-3","r":728,"s":28.54,"lo":566,"hi":808,"n":3,"rr":279,"mr":717},{"m":"llama-3-70b-instruct","r":729,"s":28.52,"lo":572,"hi":854,"n":8,"rr":466,"mr":706},{"m":"falcon-h1-1.5b-deep","r":730,"s":28.5,"lo":669,"hi":835,"n":9,"rr":977,"mr":708},{"m":"solar-pro-preview","r":731,"s":28.46,"lo":612,"hi":928,"n":4,"rr":434,"mr":720},{"m":"gemma-3-4b-it","r":732,"s":28.4,"lo":665,"hi":845,"n":12,"rr":843,"mr":698},{"m":"falcon-h1-3b","r":733,"s":28.34,"lo":679,"hi":807,"n":9,"rr":968,"mr":710},{"m":"qwen2.5-omni-7b","r":734,"s":28.24,"lo":673,"hi":843,"n":6,"rr":656,"mr":773},{"m":"qwen1.5-72b-chat","r":735,"s":28.24,"lo":651,"hi":809,"n":8,"rr":263,"mr":727},{"m":"mixtral-8x22b","r":736,"s":28.12,"lo":636,"hi":847,"n":7,"rr":310,"mr":683},{"m":"hermes-3-llama-3.1-70b","r":737,"s":27.96,"lo":591,"hi":858,"n":3,"rr":357,"mr":739},{"m":"gemma-3-27b-vl","r":738,"s":27.91,"lo":587,"hi":1017,"n":6,"rr":974,"mr":801},{"m":"qwen2.5-14b","r":739,"s":27.84,"lo":642,"hi":907,"n":5,"rr":551,"mr":701},{"m":"qwen2-math-1.5b-instruct","r":740,"s":27.82,"lo":654,"hi":904,"n":7,"rr":936,"mr":738},{"m":"qwen2-72b","r":741,"s":27.82,"lo":662,"hi":857,"n":6,"rr":403,"mr":712},{"m":"internlm2-math-plus-20b","r":742,"s":27.8,"lo":695,"hi":873,"n":6,"rr":892,"mr":737},{"m":"fast-dllm-v2-7b","r":743,"s":27.64,"lo":683,"hi":792,"n":3,"rr":366,"mr":758},{"m":"deepseek-math-7b-rl","r":744,"s":27.59,"lo":681,"hi":879,"n":5,"rr":855,"mr":742},{"m":"glm-4.5-air-base","r":745,"s":27.54,"lo":605,"hi":850,"n":10,"rr":689,"mr":747},{"m":"llada-o","r":746,"s":27.54,"lo":605,"hi":841,"n":3,"rr":747,"mr":803},{"m":"glm-4-0116","r":747,"s":27.53,"lo":636,"hi":815,"n":4,"rr":622,"mr":722},{"m":"qwen3.5-9b-base","r":748,"s":27.53,"lo":572,"hi":891,"n":4,"rr":950,"mr":766},{"m":"gemma-2-9b-it","r":749,"s":27.4,"lo":658,"hi":824,"n":5,"rr":577,"mr":726},{"m":"tigerbot-70b-chat","r":750,"s":27.29,"lo":421,"hi":800,"n":3,"rr":125,"mr":772},{"m":"llava-onevision-72b","r":751,"s":26.94,"lo":537,"hi":839,"n":5,"rr":829,"mr":817},{"m":"ouro-2.6b","r":752,"s":26.88,"lo":474,"hi":950,"n":4,"rr":152,"mr":788},{"m":"gpt-4-turbo","r":753,"s":26.83,"lo":456,"hi":943,"n":5,"rr":1071,"mr":809},{"m":"lfm2.5-1.2b-instruct","r":754,"s":26.72,"lo":687,"hi":894,"n":5,"rr":1023,"mr":723},{"m":"kimi-vl-a3b-instruct","r":755,"s":26.68,"lo":556,"hi":849,"n":4,"rr":858,"mr":820},{"m":"internvl-8b","r":756,"s":26.67,"lo":563,"hi":843,"n":3,"rr":938,"mr":808},{"m":"qwen2.5-7b","r":757,"s":26.66,"lo":717,"hi":837,"n":12,"rr":895,"mr":731},{"m":"apertus-v1.5-70b","r":758,"s":26.62,"lo":709,"hi":797,"n":6,"rr":506,"mr":748},{"m":"deepseek-v2-chat","r":759,"s":26.54,"lo":622,"hi":868,"n":9,"rr":528,"mr":735},{"m":"internvl2.5-78b","r":760,"s":26.53,"lo":456,"hi":880,"n":5,"rr":902,"mr":810},{"m":"internvl2.5-38b","r":761,"s":26.48,"lo":481,"hi":866,"n":5,"rr":921,"mr":811},{"m":"kanana-2-30b-a3b-base","r":762,"s":26.48,"lo":680,"hi":787,"n":3,"rr":350,"mr":756},{"m":"kanana-2-30b-a3b-mid-2601","r":763,"s":26.48,"lo":681,"hi":788,"n":3,"rr":351,"mr":757},{"m":"aquif-3-3.2b","r":764,"s":26.46,"lo":722,"hi":852,"n":3,"rr":1102,"mr":779},{"m":"bitcpm-cann-8b","r":765,"s":26.43,"lo":697,"hi":882,"n":4,"rr":51,"mr":764},{"m":"qwen3-vl-2b-instruct","r":766,"s":26.42,"lo":615,"hi":890,"n":11,"rr":804,"mr":798},{"m":"olmo-hybrid-instruct-7b-sft","r":767,"s":26.41,"lo":672,"hi":874,"n":6,"rr":1134,"mr":753},{"m":"granite-4.0-h-micro","r":768,"s":26.39,"lo":547,"hi":947,"n":6,"rr":844,"mr":790},{"m":"qwen2.5-coder-14b","r":769,"s":26.37,"lo":643,"hi":925,"n":4,"rr":363,"mr":787},{"m":"internlm2-math-plus-7b","r":770,"s":26.28,"lo":721,"hi":908,"n":6,"rr":924,"mr":762},{"m":"d1-3b","r":771,"s":26.19,"lo":666,"hi":881,"n":5,"rr":320,"mr":754},{"m":"llama-3-70b-base","r":772,"s":26.17,"lo":587,"hi":850,"n":7,"rr":297,"mr":733},{"m":"qwen1.5-72b","r":773,"s":26.1,"lo":624,"hi":844,"n":7,"rr":307,"mr":741},{"m":"yi-1.5-9b-chat","r":774,"s":26.05,"lo":697,"hi":793,"n":4,"rr":676,"mr":767},{"m":"llama-3.1-nemotron-70b","r":775,"s":26.03,"lo":653,"hi":898,"n":4,"rr":277,"mr":745},{"m":"qwen2.5-coder-7b-instruct","r":776,"s":26,"lo":689,"hi":994,"n":10,"rr":1050,"mr":750},{"m":"kanana-1.5-32.5b-base","r":777,"s":25.99,"lo":662,"hi":819,"n":3,"rr":393,"mr":794},{"m":"qwen2-57b-a14b-instruct","r":778,"s":25.94,"lo":707,"hi":810,"n":5,"rr":611,"mr":746},{"m":"moonlight-base","r":779,"s":25.9,"lo":715,"hi":826,"n":10,"rr":319,"mr":774},{"m":"deepseek-llm-67b-chat","r":780,"s":25.84,"lo":678,"hi":883,"n":7,"rr":260,"mr":765},{"m":"deepseek-v2","r":781,"s":25.76,"lo":607,"hi":841,"n":7,"rr":194,"mr":755},{"m":"gpt-4v","r":782,"s":25.74,"lo":585,"hi":830,"n":5,"rr":1018,"mr":823},{"m":"hy-1.8b","r":783,"s":25.71,"lo":404,"hi":928,"n":3,"rr":243,"mr":799},{"m":"claude-3.5-haiku-20241022","r":784,"s":25.63,"lo":499,"hi":1104,"n":5,"rr":886,"mr":832},{"m":"qwen2-7b-instruct","r":785,"s":25.61,"lo":726,"hi":890,"n":8,"rr":860,"mr":760},{"m":"mathstral-7b","r":786,"s":25.57,"lo":729,"hi":911,"n":6,"rr":931,"mr":777},{"m":"phi-3-mini-4k-instruct","r":787,"s":25.5,"lo":719,"hi":809,"n":3,"rr":138,"mr":793},{"m":"lfm2-2.6b","r":788,"s":25.43,"lo":730,"hi":843,"n":7,"rr":817,"mr":778},{"m":"hrm-text-1b","r":789,"s":25.36,"lo":711,"hi":832,"n":4,"rr":353,"mr":782},{"m":"llama-3.1-70b-base","r":790,"s":25.36,"lo":587,"hi":862,"n":5,"rr":221,"mr":763},{"m":"deepseek-coder-v2-lite-instruct","r":791,"s":25.29,"lo":711,"hi":912,"n":11,"rr":845,"mr":775},{"m":"instella-moe-16b-a3b-base","r":792,"s":25.26,"lo":681,"hi":853,"n":7,"rr":163,"mr":789},{"m":"glm-4-9b-chat","r":793,"s":25.24,"lo":706,"hi":824,"n":5,"rr":646,"mr":759},{"m":"deepseek-math-7b-instruct","r":794,"s":25.2,"lo":721,"hi":824,"n":3,"rr":330,"mr":781},{"m":"ovis1.6-gemma2-9b","r":795,"s":25.16,"lo":535,"hi":895,"n":3,"rr":787,"mr":843},{"m":"llama-3.1-tulu-3-8b","r":796,"s":25.14,"lo":672,"hi":856,"n":3,"rr":498,"mr":776},{"m":"hyperclovax-seed-omni-8b","r":797,"s":25.06,"lo":691,"hi":964,"n":5,"rr":876,"mr":815},{"m":"internlm2.5-20b","r":798,"s":25.06,"lo":679,"hi":820,"n":3,"rr":864,"mr":784},{"m":"qwen2-vl-72b","r":799,"s":25.01,"lo":491,"hi":874,"n":5,"rr":926,"mr":831},{"m":"qwen1.5-110b-chat","r":800,"s":24.86,"lo":674,"hi":860,"n":4,"rr":698,"mr":800},{"m":"phi-3.5-mini-instruct","r":801,"s":24.85,"lo":727,"hi":839,"n":5,"rr":627,"mr":749},{"m":"granite-3.3-8b-instruct","r":802,"s":24.82,"lo":725,"hi":898,"n":8,"rr":1042,"mr":771},{"m":"nemotron-nano-12b-v2-base","r":803,"s":24.81,"lo":676,"hi":1015,"n":7,"rr":547,"mr":812},{"m":"qwen2-math-7b","r":804,"s":24.8,"lo":734,"hi":821,"n":3,"rr":331,"mr":786},{"m":"falcon-h1-1.5b","r":805,"s":24.77,"lo":722,"hi":901,"n":9,"rr":1054,"mr":770},{"m":"qwen1.5-110b","r":806,"s":24.74,"lo":701,"hi":877,"n":5,"rr":591,"mr":752},{"m":"molmo-7b-d","r":807,"s":24.74,"lo":313,"hi":956,"n":3,"rr":538,"mr":858},{"m":"falcon3-10b","r":808,"s":24.42,"lo":735,"hi":904,"n":9,"rr":1000,"mr":780},{"m":"olmo-3-7b-sft","r":809,"s":24.3,"lo":725,"hi":904,"n":7,"rr":1166,"mr":795},{"m":"glm4-9b","r":810,"s":24.26,"lo":751,"hi":856,"n":5,"rr":814,"mr":783},{"m":"gemma-3n-e2b-it","r":811,"s":24.21,"lo":753,"hi":950,"n":4,"rr":1061,"mr":821},{"m":"qwen2.5-vl-3b","r":812,"s":24.2,"lo":631,"hi":873,"n":4,"rr":785,"mr":855},{"m":"qwen2-vl-72b-instruct","r":813,"s":24.15,"lo":479,"hi":894,"n":4,"rr":944,"mr":844},{"m":"deepseek-coder-v2-base","r":814,"s":24.09,"lo":712,"hi":953,"n":3,"rr":489,"mr":792},{"m":"glm-4-9b-chat-1m","r":815,"s":24.07,"lo":744,"hi":840,"n":3,"rr":846,"mr":791},{"m":"numinamath-7b-cot","r":816,"s":23.94,"lo":740,"hi":917,"n":5,"rr":934,"mr":806},{"m":"qwen2.5-math-1.5b","r":817,"s":23.75,"lo":758,"hi":859,"n":3,"rr":392,"mr":805},{"m":"internvl2.5-26b","r":818,"s":23.65,"lo":677,"hi":885,"n":8,"rr":830,"mr":826},{"m":"qwen2.5-coder-3b-instruct","r":819,"s":23.62,"lo":724,"hi":944,"n":7,"rr":1078,"mr":814},{"m":"falcon3-7b","r":820,"s":23.55,"lo":761,"hi":911,"n":9,"rr":1020,"mr":796},{"m":"exaone-3.5-7.8b-instruct","r":821,"s":23.54,"lo":745,"hi":844,"n":3,"rr":678,"mr":829},{"m":"bielik-11b-v3.0-instruct","r":822,"s":23.46,"lo":696,"hi":998,"n":3,"rr":262,"mr":834},{"m":"phi-3-vision-4b","r":823,"s":23.46,"lo":545,"hi":954,"n":3,"rr":364,"mr":870},{"m":"qwen2.5-vl-7b","r":824,"s":23.43,"lo":710,"hi":959,"n":8,"rr":1064,"mr":857},{"m":"qwen3-0.6b","r":825,"s":23.42,"lo":715,"hi":968,"n":14,"rr":1175,"mr":769},{"m":"llama-3.1-tulu-3-8b-dpo","r":826,"s":23.41,"lo":718,"hi":871,"n":3,"rr":555,"mr":838},{"m":"mistral-large-2411","r":827,"s":23.24,"lo":429,"hi":946,"n":3,"rr":734,"mr":848},{"m":"kanana-2-30b-a3b-base-2601","r":828,"s":23.18,"lo":701,"hi":867,"n":3,"rr":493,"mr":824},{"m":"ministral-3-3b-instruct","r":829,"s":23.06,"lo":561,"hi":958,"n":7,"rr":771,"mr":825},{"m":"eurollm-22b","r":830,"s":23.06,"lo":729,"hi":907,"n":8,"rr":729,"mr":807},{"m":"llama-3.1-8b","r":831,"s":23.05,"lo":758,"hi":904,"n":6,"rr":533,"mr":802},{"m":"minicpm-o-2.6","r":832,"s":22.99,"lo":630,"hi":910,"n":4,"rr":1090,"mr":874},{"m":"kanana-2-3b-instruct","r":833,"s":22.98,"lo":765,"hi":891,"n":3,"rr":943,"mr":827},{"m":"granite-4.0-h-tiny","r":834,"s":22.87,"lo":748,"hi":923,"n":13,"rr":997,"mr":813},{"m":"minicpm3-4b","r":835,"s":22.86,"lo":757,"hi":851,"n":4,"rr":795,"mr":804},{"m":"bielik-11b-v2.5-instruct","r":836,"s":22.66,"lo":710,"hi":1022,"n":3,"rr":321,"mr":862},{"m":"openpangu-7b-diffusion-base","r":837,"s":22.66,"lo":763,"hi":856,"n":3,"rr":556,"mr":830},{"m":"llada-v","r":838,"s":22.29,"lo":697,"hi":923,"n":3,"rr":850,"mr":887},{"m":"gemma-2-27b","r":839,"s":22.13,"lo":749,"hi":916,"n":7,"rr":884,"mr":797},{"m":"gemma-3-12b","r":840,"s":22.12,"lo":539,"hi":935,"n":7,"rr":423,"mr":859},{"m":"gpt-3.5-turbo-0125","r":841,"s":22.11,"lo":757,"hi":872,"n":3,"rr":605,"mr":842},{"m":"qwen2.5-coder-7b","r":842,"s":22.09,"lo":743,"hi":980,"n":4,"rr":558,"mr":818},{"m":"kanana-2-1.3b-instruct","r":843,"s":22.09,"lo":779,"hi":918,"n":3,"rr":976,"mr":839},{"m":"alodlm-1.7b","r":844,"s":22.06,"lo":766,"hi":954,"n":6,"rr":417,"mr":819},{"m":"qwen2-7b","r":845,"s":22.04,"lo":780,"hi":946,"n":7,"rr":735,"mr":816},{"m":"yi-1.5-34b","r":846,"s":21.99,"lo":741,"hi":917,"n":5,"rr":682,"mr":836},{"m":"cambrian-34b","r":847,"s":21.92,"lo":668,"hi":909,"n":3,"rr":285,"mr":894},{"m":"exaone-3.5-2.4b-instruct","r":848,"s":21.83,"lo":755,"hi":967,"n":3,"rr":788,"mr":867},{"m":"olmo-2-32b-base","r":849,"s":21.62,"lo":642,"hi":1026,"n":10,"rr":701,"mr":849},{"m":"olmo-3-7b","r":850,"s":21.59,"lo":716,"hi":921,"n":9,"rr":531,"mr":841},{"m":"ministral-8b-instruct","r":851,"s":21.54,"lo":770,"hi":883,"n":3,"rr":633,"mr":852},{"m":"hy-1.8b-int4gptq","r":852,"s":21.5,"lo":423,"hi":947,"n":3,"rr":345,"mr":861},{"m":"midm-2.0-mini-instruct","r":853,"s":21.49,"lo":739,"hi":1007,"n":3,"rr":823,"mr":878},{"m":"internvl3-2b","r":854,"s":21.48,"lo":717,"hi":892,"n":3,"rr":879,"mr":899},{"m":"bielik-11b-v2.6-instruct","r":855,"s":21.41,"lo":735,"hi":1016,"n":3,"rr":333,"mr":881},{"m":"qwen2.57b-a14b","r":856,"s":21.31,"lo":777,"hi":927,"n":5,"rr":714,"mr":822},{"m":"qwen1.5-32b-chat","r":857,"s":21.3,"lo":775,"hi":920,"n":6,"rr":688,"mr":846},{"m":"gemma-2-27b-it","r":858,"s":21.25,"lo":746,"hi":985,"n":9,"rr":1038,"mr":828},{"m":"mobilellm-r1.5-360m","r":859,"s":21.21,"lo":737,"hi":999,"n":4,"rr":1144,"mr":840},{"m":"jamba-1.5-mini","r":860,"s":21.12,"lo":711,"hi":1084,"n":3,"rr":609,"mr":879},{"m":"llama-3.1-8b-instruct","r":861,"s":21.07,"lo":808,"hi":957,"n":15,"rr":1045,"mr":837},{"m":"apertus-v1.5-8b","r":862,"s":21.05,"lo":800,"hi":907,"n":6,"rr":731,"mr":847},{"m":"internvl3-8b","r":863,"s":21,"lo":688,"hi":1084,"n":3,"rr":1176,"mr":909},{"m":"minicpm-v-2_6","r":864,"s":20.98,"lo":633,"hi":945,"n":4,"rr":964,"mr":907},{"m":"dream-7b-base","r":865,"s":20.94,"lo":773,"hi":889,"n":3,"rr":644,"mr":876},{"m":"qwen2-math-1.5b","r":866,"s":20.9,"lo":804,"hi":913,"n":3,"rr":552,"mr":850},{"m":"yi-1.5-6b-chat","r":867,"s":20.82,"lo":805,"hi":891,"n":3,"rr":686,"mr":864},{"m":"cogvlm-17b-chat","r":868,"s":20.78,"lo":531,"hi":1100,"n":3,"rr":624,"mr":919},{"m":"moonlight-instruct","r":869,"s":20.77,"lo":768,"hi":987,"n":7,"rr":1112,"mr":845},{"m":"qwen2.5-3b","r":870,"s":20.74,"lo":797,"hi":959,"n":11,"rr":1014,"mr":833},{"m":"qwen3.5-2b-base","r":871,"s":20.72,"lo":736,"hi":938,"n":7,"rr":275,"mr":854},{"m":"hy-1.8b-2bit","r":872,"s":20.69,"lo":427,"hi":987,"n":3,"rr":421,"mr":880},{"m":"internvl2.5-8b","r":873,"s":20.65,"lo":707,"hi":962,"n":8,"rr":893,"mr":888},{"m":"gpt-3.5-turbo","r":874,"s":20.61,"lo":746,"hi":914,"n":3,"rr":661,"mr":863},{"m":"phi-4-mini-3.8b","r":875,"s":20.57,"lo":811,"hi":957,"n":3,"rr":1145,"mr":883},{"m":"trinity-large-truebase","r":876,"s":20.51,"lo":718,"hi":977,"n":5,"rr":651,"mr":860},{"m":"qwen2-vl-7b-instruct","r":877,"s":20.44,"lo":602,"hi":948,"n":3,"rr":883,"mr":924},{"m":"trinity-mini-base","r":878,"s":20.44,"lo":572,"hi":991,"n":5,"rr":292,"mr":865},{"m":"internlm2-chat-20b","r":879,"s":20.44,"lo":769,"hi":914,"n":3,"rr":687,"mr":851},{"m":"llama-3-8b","r":880,"s":20.28,"lo":797,"hi":928,"n":7,"rr":786,"mr":835},{"m":"internvl2-llama-3-76b","r":881,"s":20.25,"lo":536,"hi":975,"n":6,"rr":987,"mr":912},{"m":"gpt-3.5","r":882,"s":20.09,"lo":785,"hi":919,"n":4,"rr":567,"mr":875},{"m":"dream-7b-instruct","r":883,"s":20.06,"lo":802,"hi":952,"n":7,"rr":653,"mr":868},{"m":"granite-4.0-micro","r":884,"s":20.03,"lo":655,"hi":1123,"n":7,"rr":1003,"mr":895},{"m":"olmo-2-0325-32b-instruct","r":885,"s":19.78,"lo":774,"hi":1054,"n":6,"rr":1168,"mr":871},{"m":"skywork-moe-base","r":886,"s":19.63,"lo":649,"hi":930,"n":3,"rr":659,"mr":872},{"m":"command-r-plus","r":887,"s":19.6,"lo":806,"hi":948,"n":3,"rr":327,"mr":896},{"m":"qwen2-vl-7b","r":888,"s":19.53,"lo":689,"hi":945,"n":5,"rr":995,"mr":939},{"m":"rnd1-base-0910","r":889,"s":19.48,"lo":750,"hi":1010,"n":3,"rr":348,"mr":914},{"m":"qwen1.5-32b","r":890,"s":19.44,"lo":804,"hi":950,"n":5,"rr":775,"mr":853},{"m":"apriel-5b-instruct","r":891,"s":19.39,"lo":835,"hi":976,"n":3,"rr":1150,"mr":901},{"m":"bielik-11b-v2.3-instruct","r":892,"s":19.35,"lo":782,"hi":1047,"n":3,"rr":438,"mr":920},{"m":"bitcpm-cann-3b","r":893,"s":19.34,"lo":817,"hi":1005,"n":4,"rr":161,"mr":889},{"m":"exaone-3.5-2.4b","r":894,"s":19.33,"lo":849,"hi":986,"n":3,"rr":1161,"mr":902},{"m":"internlm2.5-7b","r":895,"s":19.25,"lo":771,"hi":924,"n":4,"rr":873,"mr":866},{"m":"gemini-pro","r":896,"s":19.25,"lo":735,"hi":947,"n":5,"rr":905,"mr":916},{"m":"bielik-11b-v2.2-instruct","r":897,"s":19.22,"lo":787,"hi":1044,"n":3,"rr":437,"mr":923},{"m":"smollm3-3b-base","r":898,"s":19.14,"lo":759,"hi":967,"n":7,"rr":284,"mr":908},{"m":"llama-3-8b-instruct","r":899,"s":19.11,"lo":784,"hi":940,"n":7,"rr":650,"mr":856},{"m":"apertus-70b","r":900,"s":18.98,"lo":710,"hi":1002,"n":7,"rr":807,"mr":897},{"m":"bielik-11b-v2.1-instruct","r":901,"s":18.9,"lo":797,"hi":1045,"n":3,"rr":448,"mr":931},{"m":"internlm2-chat-20b-sft","r":902,"s":18.84,"lo":805,"hi":940,"n":3,"rr":742,"mr":884},{"m":"map-neo-7b-instruct","r":903,"s":18.79,"lo":775,"hi":932,"n":5,"rr":500,"mr":869},{"m":"internlm2-20b","r":904,"s":18.78,"lo":800,"hi":932,"n":5,"rr":986,"mr":877},{"m":"molmo-7b-o","r":905,"s":18.73,"lo":398,"hi":1068,"n":3,"rr":706,"mr":968},{"m":"llada-8b-instruct","r":906,"s":18.63,"lo":783,"hi":973,"n":6,"rr":603,"mr":906},{"m":"yi-1.5-9b","r":907,"s":18.59,"lo":801,"hi":939,"n":4,"rr":898,"mr":898},{"m":"intern-decision-2b","r":908,"s":18.57,"lo":825,"hi":979,"n":4,"rr":553,"mr":882},{"m":"map-neo-7b-sft","r":909,"s":18.56,"lo":776,"hi":938,"n":5,"rr":513,"mr":873},{"m":"gemma-3-4b","r":910,"s":18.55,"lo":596,"hi":1089,"n":6,"rr":918,"mr":934},{"m":"llama-3.1-tulu-3-8b-sft","r":911,"s":18.49,"lo":814,"hi":943,"n":3,"rr":760,"mr":929},{"m":"internlm-xcomposer2-vl-7b","r":912,"s":18.49,"lo":641,"hi":979,"n":3,"rr":909,"mr":964},{"m":"deepseek-math-7b","r":913,"s":18.49,"lo":844,"hi":1050,"n":7,"rr":912,"mr":893},{"m":"metamath-70b","r":914,"s":18.46,"lo":785,"hi":976,"n":3,"rr":705,"mr":918},{"m":"qwen3-1.7b-base","r":915,"s":18.34,"lo":835,"hi":1020,"n":4,"rr":728,"mr":930},{"m":"qwen3-4b-base","r":916,"s":18.28,"lo":799,"hi":983,"n":3,"rr":732,"mr":933},{"m":"granite-3.2-8b-instruct","r":917,"s":18.21,"lo":794,"hi":1021,"n":4,"rr":913,"mr":917},{"m":"command-r-plus-08-2024","r":918,"s":18.2,"lo":633,"hi":948,"n":3,"rr":291,"mr":905},{"m":"granite-3.3-2b-instruct","r":919,"s":18.13,"lo":855,"hi":999,"n":4,"rr":975,"mr":913},{"m":"vllm-sr-d3-lite","r":920,"s":18.07,"lo":834,"hi":992,"n":4,"rr":583,"mr":890},{"m":"internvl2-8b","r":921,"s":18.05,"lo":780,"hi":1049,"n":9,"rr":973,"mr":921},{"m":"falcon-h1-0.5b-instruct","r":922,"s":18.01,"lo":862,"hi":1002,"n":9,"rr":1128,"mr":891},{"m":"qwen2.5-coder-3b","r":923,"s":17.92,"lo":841,"hi":1047,"n":4,"rr":766,"mr":932},{"m":"mixtral-8x7b","r":924,"s":17.9,"lo":798,"hi":1018,"n":7,"rr":783,"mr":886},{"m":"mixtral-8x7b-instruct-v0.1","r":925,"s":17.83,"lo":759,"hi":947,"n":3,"rr":759,"mr":900},{"m":"ouro-1.4b","r":926,"s":17.48,"lo":648,"hi":1007,"n":5,"rr":638,"mr":944},{"m":"internvl2-26b","r":927,"s":17.42,"lo":810,"hi":1014,"n":9,"rr":984,"mr":941},{"m":"gemma-2-9b","r":928,"s":17.42,"lo":828,"hi":980,"n":10,"rr":961,"mr":885},{"m":"llama3.0-70b","r":929,"s":17.42,"lo":777,"hi":1082,"n":6,"rr":939,"mr":892},{"m":"tigerbot-70b-base","r":930,"s":17.4,"lo":400,"hi":969,"n":3,"rr":240,"mr":952},{"m":"trinity-nano-base","r":931,"s":17.39,"lo":748,"hi":1015,"n":7,"rr":264,"mr":928},{"m":"llada-moe-7b-a1b-base","r":932,"s":17.38,"lo":852,"hi":963,"n":3,"rr":816,"mr":945},{"m":"qwen-vl-max","r":933,"s":17.34,"lo":686,"hi":982,"n":3,"rr":953,"mr":986},{"m":"aquila-vl-2b","r":934,"s":17.29,"lo":700,"hi":996,"n":4,"rr":1015,"mr":985},{"m":"internvl-u","r":935,"s":17.29,"lo":740,"hi":1021,"n":3,"rr":927,"mr":979},{"m":"deepseek-coder-v2-lite-base","r":936,"s":17.26,"lo":862,"hi":1007,"n":5,"rr":692,"mr":926},{"m":"gemma-3-pt-27b","r":937,"s":17.25,"lo":827,"hi":994,"n":7,"rr":712,"mr":943},{"m":"llm-jp-4-vl-9b-beta","r":938,"s":17.23,"lo":838,"hi":981,"n":4,"rr":1051,"mr":940},{"m":"vllm-sr-decision-2.0-sol-2b","r":939,"s":17.21,"lo":837,"hi":1018,"n":4,"rr":658,"mr":903},{"m":"granite-4.0-1b","r":940,"s":17.02,"lo":889,"hi":1028,"n":5,"rr":1136,"mr":904},{"m":"falcon3-3b","r":941,"s":16.99,"lo":881,"hi":1052,"n":9,"rr":1116,"mr":911},{"m":"qwen2.5-1.5b-instruct","r":942,"s":16.89,"lo":813,"hi":1053,"n":6,"rr":1118,"mr":922},{"m":"stablebeluga2-70b","r":943,"s":16.87,"lo":763,"hi":1034,"n":5,"rr":522,"mr":910},{"m":"phi-4-multimodal-instruct","r":944,"s":16.81,"lo":783,"hi":990,"n":3,"rr":922,"mr":991},{"m":"granite-3.1-8b-instruct","r":945,"s":16.79,"lo":830,"hi":1038,"n":4,"rr":940,"mr":949},{"m":"bielik-11b-v2.0-instruct","r":946,"s":16.76,"lo":831,"hi":1054,"n":3,"rr":515,"mr":961},{"m":"internlm2-math-plus-1.8b","r":947,"s":16.73,"lo":731,"hi":1002,"n":3,"rr":1011,"mr":938},{"m":"dbrx-instruct-preview","r":948,"s":16.72,"lo":717,"hi":975,"n":3,"rr":790,"mr":951},{"m":"llama-3.2-3b","r":949,"s":16.59,"lo":860,"hi":1044,"n":9,"rr":668,"mr":915},{"m":"marin-8b-instruct","r":950,"s":16.49,"lo":869,"hi":1001,"n":6,"rr":901,"mr":947},{"m":"llada-8b-base","r":951,"s":16.47,"lo":843,"hi":970,"n":3,"rr":838,"mr":969},{"m":"chatglm3-6b","r":952,"s":16.45,"lo":830,"hi":977,"n":3,"rr":833,"mr":946},{"m":"bielik-11b-v3.0","r":953,"s":16.42,"lo":786,"hi":1029,"n":3,"rr":457,"mr":955},{"m":"qwen-14b","r":954,"s":16.33,"lo":774,"hi":998,"n":6,"rr":362,"mr":927},{"m":"openchat-3.5-0106-gemma","r":955,"s":16.32,"lo":826,"hi":1000,"n":3,"rr":470,"mr":962},{"m":"wizardmath-70b-v1.0","r":956,"s":16.31,"lo":796,"hi":1013,"n":3,"rr":793,"mr":963},{"m":"strands-decider-2b","r":957,"s":16.27,"lo":851,"hi":1026,"n":4,"rr":666,"mr":925},{"m":"skywork-13b-math","r":958,"s":16.23,"lo":855,"hi":1048,"n":3,"rr":819,"mr":967},{"m":"kanana-2-3b-base","r":959,"s":16.17,"lo":872,"hi":991,"n":3,"rr":871,"mr":942},{"m":"chatglm3-6b-base","r":960,"s":16.1,"lo":857,"hi":983,"n":4,"rr":979,"mr":948},{"m":"internlm2-math-base-20b","r":961,"s":16.06,"lo":874,"hi":976,"n":4,"rr":955,"mr":954},{"m":"internvl2-40b","r":962,"s":16.05,"lo":639,"hi":1033,"n":6,"rr":1056,"mr":993},{"m":"deepseek-llm-67b-base","r":963,"s":16.01,"lo":743,"hi":1022,"n":7,"rr":537,"mr":936},{"m":"xverse-65b-2","r":964,"s":15.98,"lo":706,"hi":1019,"n":3,"rr":810,"mr":950},{"m":"mm1.5-3b","r":965,"s":15.83,"lo":674,"hi":1031,"n":3,"rr":545,"mr":1008},{"m":"llama-3.2-3b-base","r":966,"s":15.74,"lo":833,"hi":1092,"n":9,"rr":1124,"mr":937},{"m":"solar-10.7b-instruct-v1.0","r":967,"s":15.74,"lo":797,"hi":982,"n":3,"rr":471,"mr":957},{"m":"bielik-4.5b-v3-instruct","r":968,"s":15.73,"lo":846,"hi":1066,"n":3,"rr":579,"mr":983},{"m":"llama-3.1-8b-base","r":969,"s":15.52,"lo":890,"hi":1034,"n":13,"rr":1036,"mr":935},{"m":"internlm2-chat-7b","r":970,"s":15.5,"lo":862,"hi":998,"n":3,"rr":878,"mr":958},{"m":"deepseek-coder-7b-instruct-v1.5","r":971,"s":15.47,"lo":882,"hi":1084,"n":4,"rr":910,"mr":970},{"m":"qwen1.5-14b","r":972,"s":15.34,"lo":879,"hi":1021,"n":4,"rr":802,"mr":972},{"m":"gemma-2-2b-it","r":973,"s":15.19,"lo":866,"hi":989,"n":3,"rr":1082,"mr":959},{"m":"yi-1.5-6b","r":974,"s":15.13,"lo":877,"hi":993,"n":3,"rr":903,"mr":978},{"m":"internlm2-chat-7b-sft","r":975,"s":15.1,"lo":867,"hi":1002,"n":3,"rr":891,"mr":965},{"m":"qwen-14b-chat","r":976,"s":15.04,"lo":829,"hi":1000,"n":3,"rr":896,"mr":974},{"m":"internlm2.5-1.8b-chat","r":977,"s":15.04,"lo":856,"hi":1052,"n":4,"rr":1035,"mr":953},{"m":"grok-1","r":978,"s":14.99,"lo":734,"hi":1000,"n":3,"rr":867,"mr":975},{"m":"eurollm-9b-instruct-2512","r":979,"s":14.99,"lo":903,"hi":1019,"n":6,"rr":946,"mr":960},{"m":"meta-llama-3-8b-instruct","r":980,"s":14.93,"lo":801,"hi":1035,"n":3,"rr":534,"mr":977},{"m":"llama-2-70b-chat","r":981,"s":14.85,"lo":420,"hi":1014,"n":3,"rr":398,"mr":1003},{"m":"internlm2-7b","r":982,"s":14.83,"lo":851,"hi":1020,"n":5,"rr":1058,"mr":966},{"m":"internvl2.5-4b","r":983,"s":14.79,"lo":668,"hi":1060,"n":5,"rr":1068,"mr":1012},{"m":"llava-next-34b","r":984,"s":14.7,"lo":798,"hi":1036,"n":4,"rr":740,"mr":1022},{"m":"qwen2.5-1.5b","r":985,"s":14.65,"lo":924,"hi":1065,"n":11,"rr":1151,"mr":956},{"m":"internlm2.5-1.8b","r":986,"s":14.57,"lo":899,"hi":1024,"n":3,"rr":1129,"mr":984},{"m":"gemma-7b","r":987,"s":14.57,"lo":884,"hi":1024,"n":6,"rr":798,"mr":973},{"m":"trida-7b","r":988,"s":14.39,"lo":813,"hi":1037,"n":3,"rr":825,"mr":988},{"m":"bielik-11b-v2","r":989,"s":14.35,"lo":859,"hi":1040,"n":3,"rr":601,"mr":1001},{"m":"llama-3-8b-base","r":990,"s":14.14,"lo":841,"hi":1037,"n":5,"rr":932,"mr":971},{"m":"mobilemoe-l","r":991,"s":14.09,"lo":923,"hi":1057,"n":7,"rr":743,"mr":987},{"m":"marin-32b-mantis","r":992,"s":14.01,"lo":893,"hi":1048,"n":7,"rr":808,"mr":1005},{"m":"qwen2.5-coder-1.5b","r":993,"s":13.98,"lo":917,"hi":1095,"n":4,"rr":945,"mr":981},{"m":"llama-3.2-3b-instruct","r":994,"s":13.93,"lo":905,"hi":1099,"n":7,"rr":1019,"mr":992},{"m":"mobilellm-r1-950m-base","r":995,"s":13.81,"lo":933,"hi":1035,"n":3,"rr":1008,"mr":1006},{"m":"internlm-20b","r":996,"s":13.79,"lo":811,"hi":1072,"n":6,"rr":501,"mr":980},{"m":"granite-4.0-h-1b","r":997,"s":13.79,"lo":899,"hi":1101,"n":4,"rr":1123,"mr":997},{"m":"jamba-v0.1","r":998,"s":13.78,"lo":790,"hi":1021,"n":3,"rr":600,"mr":999},{"m":"kanana-2-1.3b-base","r":999,"s":13.71,"lo":915,"hi":1055,"n":3,"rr":993,"mr":990},{"m":"mm1-30b","r":1000,"s":13.69,"lo":779,"hi":1072,"n":3,"rr":573,"mr":1054},{"m":"qwen1.5-moe-a2.7b","r":1001,"s":13.64,"lo":890,"hi":1022,"n":3,"rr":951,"mr":998},{"m":"qwen3-0.8b","r":1002,"s":13.62,"lo":935,"hi":1115,"n":9,"rr":1186,"mr":982},{"m":"command-r-08-2024","r":1003,"s":13.58,"lo":775,"hi":1039,"n":3,"rr":606,"mr":1004},{"m":"lfm2-1.2b","r":1004,"s":13.54,"lo":797,"hi":1036,"n":4,"rr":930,"mr":1023},{"m":"gemma-1.1-7b-it","r":1005,"s":13.48,"lo":913,"hi":1027,"n":3,"rr":972,"mr":1000},{"m":"qwen2-1.5b-instruct","r":1006,"s":13.45,"lo":965,"hi":1092,"n":7,"rr":1125,"mr":1002},{"m":"yi-34b","r":1007,"s":13.38,"lo":675,"hi":1074,"n":3,"rr":880,"mr":1009},{"m":"llama-2-70b","r":1008,"s":13.32,"lo":824,"hi":1068,"n":7,"rr":635,"mr":994},{"m":"qwen1.5-7b","r":1009,"s":13.14,"lo":918,"hi":1057,"n":5,"rr":990,"mr":989},{"m":"apertus-70b-instruct","r":1010,"s":13.11,"lo":913,"hi":1121,"n":12,"rr":1165,"mr":976},{"m":"qwen3-0.6b-base","r":1011,"s":13.03,"lo":940,"hi":1077,"n":4,"rr":967,"mr":1037},{"m":"llama-3.1-3b","r":1012,"s":13,"lo":759,"hi":1097,"n":3,"rr":1169,"mr":1027},{"m":"deepseek-v2-lite-chat","r":1013,"s":12.92,"lo":934,"hi":1086,"n":9,"rr":988,"mr":996},{"m":"qwen2-vl-2b-instruct","r":1014,"s":12.91,"lo":771,"hi":1063,"n":3,"rr":1027,"mr":1068},{"m":"orion-14b-base","r":1015,"s":12.87,"lo":812,"hi":1107,"n":6,"rr":559,"mr":995},{"m":"deepseek-coder-6.7b-instruct","r":1016,"s":12.83,"lo":939,"hi":1157,"n":4,"rr":1057,"mr":1017},{"m":"codellama-34b","r":1017,"s":12.82,"lo":905,"hi":1040,"n":3,"rr":1138,"mr":1029},{"m":"aquif-3.5-a0.6b","r":1018,"s":12.78,"lo":801,"hi":1059,"n":3,"rr":978,"mr":1045},{"m":"granite-3.3-8b-base","r":1019,"s":12.77,"lo":870,"hi":1091,"n":4,"rr":748,"mr":1040},{"m":"deepseek-coder-33b-base","r":1020,"s":12.61,"lo":946,"hi":1136,"n":4,"rr":1040,"mr":1013},{"m":"llemma-34b","r":1021,"s":12.56,"lo":937,"hi":1056,"n":4,"rr":1072,"mr":1021},{"m":"map-neo-7b","r":1022,"s":12.45,"lo":864,"hi":1053,"n":5,"rr":796,"mr":1007},{"m":"aquif-3-0.4b","r":1023,"s":12.4,"lo":827,"hi":1057,"n":3,"rr":1002,"mr":1055},{"m":"llama-3-8b-instruct-gradient-1048k","r":1024,"s":12.38,"lo":852,"hi":1053,"n":3,"rr":1135,"mr":1016},{"m":"olmo-2-1124-7b-instruct","r":1025,"s":12.36,"lo":937,"hi":1127,"n":6,"rr":1199,"mr":1028},{"m":"telechat-12b","r":1026,"s":12.33,"lo":726,"hi":1060,"n":3,"rr":947,"mr":1024},{"m":"aquila2-34b","r":1027,"s":12.32,"lo":705,"hi":1094,"n":4,"rr":598,"mr":1046},{"m":"bielik-4.5b-v3","r":1028,"s":12.31,"lo":885,"hi":1100,"n":3,"rr":738,"mr":1047},{"m":"qwen1.5-7b-chat","r":1029,"s":12.28,"lo":951,"hi":1063,"n":6,"rr":1013,"mr":1015},{"m":"granite-3.1-2b-instruct","r":1030,"s":12.28,"lo":941,"hi":1116,"n":4,"rr":1076,"mr":1036},{"m":"granite-3.2-2b-instruct","r":1031,"s":12.27,"lo":940,"hi":1115,"n":4,"rr":1075,"mr":1035},{"m":"deepseek-coder-7b-base-v1.5","r":1032,"s":12.22,"lo":956,"hi":1088,"n":5,"rr":1046,"mr":1014},{"m":"starcoder2-15b","r":1033,"s":12.2,"lo":949,"hi":1087,"n":4,"rr":959,"mr":1031},{"m":"qwen2-1.5b","r":1034,"s":12.16,"lo":967,"hi":1088,"n":6,"rr":1006,"mr":1010},{"m":"internvl2.5-2b","r":1035,"s":12.1,"lo":903,"hi":1090,"n":8,"rr":1086,"mr":1060},{"m":"qwen-vl-plus","r":1036,"s":12.08,"lo":754,"hi":1083,"n":3,"rr":1030,"mr":1088},{"m":"phi-3.5-vision-instruct","r":1037,"s":12.05,"lo":748,"hi":1123,"n":5,"rr":1083,"mr":1074},{"m":"gemma-3-1b-it","r":1038,"s":12.04,"lo":972,"hi":1128,"n":11,"rr":1155,"mr":1011},{"m":"marin-32b-bison","r":1039,"s":12.02,"lo":934,"hi":1086,"n":7,"rr":874,"mr":1044},{"m":"bitcpm-cann-1b","r":1040,"s":12.02,"lo":944,"hi":1091,"n":4,"rr":507,"mr":1025},{"m":"internlm2-math-base-7b","r":1041,"s":12,"lo":849,"hi":1066,"n":3,"rr":1140,"mr":1038},{"m":"qwen2-vl-2b","r":1042,"s":11.9,"lo":800,"hi":1080,"n":4,"rr":1091,"mr":1081},{"m":"hy-0.5b","r":1043,"s":11.8,"lo":605,"hi":1099,"n":3,"rr":917,"mr":1049},{"m":"tigerbot-13b-chat","r":1044,"s":11.77,"lo":591,"hi":1067,"n":3,"rr":750,"mr":1067},{"m":"olmoe-1b-7b-base","r":1045,"s":11.59,"lo":930,"hi":1069,"n":7,"rr":592,"mr":1043},{"m":"minicpm-v-2.0-3b","r":1046,"s":11.53,"lo":785,"hi":1105,"n":3,"rr":685,"mr":1104},{"m":"mistral-7b","r":1047,"s":11.48,"lo":887,"hi":1081,"n":5,"rr":757,"mr":1033},{"m":"qwen-7b","r":1048,"s":11.44,"lo":924,"hi":1080,"n":6,"rr":827,"mr":1034},{"m":"qwen2.5-0.5b-instruct","r":1049,"s":11.44,"lo":953,"hi":1133,"n":6,"rr":1194,"mr":1041},{"m":"deepseek-llm-7b-chat","r":1050,"s":11.44,"lo":977,"hi":1087,"n":7,"rr":805,"mr":1030},{"m":"mobilellm-r1-360m","r":1051,"s":11.43,"lo":945,"hi":1160,"n":3,"rr":1185,"mr":1053},{"m":"mistral-7b-instruct-v0.2","r":1052,"s":11.42,"lo":914,"hi":1086,"n":6,"rr":667,"mr":1026},{"m":"minicpm-2b-sft","r":1053,"s":11.38,"lo":986,"hi":1070,"n":6,"rr":928,"mr":1020},{"m":"lfm2.5-vl-1.6b","r":1054,"s":11.34,"lo":906,"hi":1115,"n":7,"rr":1106,"mr":1077},{"m":"deepseek-v2-lite","r":1055,"s":11.33,"lo":934,"hi":1089,"n":9,"rr":776,"mr":1032},{"m":"intern-decision-0.8b","r":1056,"s":11.24,"lo":949,"hi":1092,"n":4,"rr":835,"mr":1018},{"m":"apertus-8b-instruct","r":1057,"s":11.19,"lo":990,"hi":1128,"n":9,"rr":1167,"mr":1039},{"m":"tev1-0.8b-experimental","r":1058,"s":11.17,"lo":947,"hi":1087,"n":4,"rr":842,"mr":1019},{"m":"wizardmath-13b-v1.0","r":1059,"s":11.16,"lo":976,"hi":1091,"n":3,"rr":1037,"mr":1062},{"m":"mobilemoe-m","r":1060,"s":11.15,"lo":991,"hi":1101,"n":7,"rr":890,"mr":1042},{"m":"qwen3.5-0.8b-thinking","r":1061,"s":11.06,"lo":930,"hi":1157,"n":11,"rr":1152,"mr":1058},{"m":"internvl2-4b","r":1062,"s":11.06,"lo":713,"hi":1140,"n":5,"rr":1107,"mr":1095},{"m":"phi-2","r":1063,"s":11.05,"lo":956,"hi":1168,"n":5,"rr":848,"mr":1051},{"m":"mistral-7b-v0.1","r":1064,"s":10.99,"lo":938,"hi":1082,"n":9,"rr":907,"mr":1050},{"m":"gemma-2-7b","r":1065,"s":10.92,"lo":978,"hi":1091,"n":6,"rr":856,"mr":1048},{"m":"yi-9b","r":1066,"s":10.87,"lo":950,"hi":1081,"n":4,"rr":960,"mr":1052},{"m":"magpie-8b","r":1067,"s":10.78,"lo":897,"hi":1172,"n":3,"rr":1041,"mr":1071},{"m":"minicpm-moe-8x2b","r":1068,"s":10.59,"lo":932,"hi":1112,"n":3,"rr":1026,"mr":1069},{"m":"llama-3.2-1.24b","r":1069,"s":10.51,"lo":986,"hi":1134,"n":6,"rr":1178,"mr":1059},{"m":"llama-1-65b","r":1070,"s":10.42,"lo":955,"hi":1096,"n":6,"rr":797,"mr":1057},{"m":"skywork-13b-base","r":1071,"s":10.32,"lo":945,"hi":1103,"n":6,"rr":697,"mr":1056},{"m":"deepseek-moe-16b-chat","r":1072,"s":10.27,"lo":995,"hi":1132,"n":6,"rr":889,"mr":1061},{"m":"deepseek-vl-7b","r":1073,"s":10.25,"lo":945,"hi":1130,"n":4,"rr":1059,"mr":1094},{"m":"internvl2.5-1b","r":1074,"s":10.18,"lo":880,"hi":1137,"n":5,"rr":1157,"mr":1105},{"m":"minicpm-2b-dpo-fp32","r":1075,"s":10.17,"lo":982,"hi":1101,"n":5,"rr":853,"mr":1063},{"m":"lfm2-700m","r":1076,"s":10.17,"lo":832,"hi":1096,"n":4,"rr":1044,"mr":1084},{"m":"smolvlm2-2.2b","r":1077,"s":10.04,"lo":831,"hi":1185,"n":3,"rr":1031,"mr":1102},{"m":"bluelm-7b-chat","r":1078,"s":10.01,"lo":1010,"hi":1094,"n":3,"rr":1094,"mr":1090},{"m":"yi-6b-chat","r":1079,"s":9.95,"lo":947,"hi":1154,"n":5,"rr":863,"mr":1064},{"m":"qwen2.5-0.5b","r":1080,"s":9.94,"lo":1011,"hi":1143,"n":11,"rr":1197,"mr":1066},{"m":"palm-540b","r":1081,"s":9.86,"lo":975,"hi":1119,"n":4,"rr":707,"mr":1086},{"m":"qwen1.5-4b","r":1082,"s":9.83,"lo":968,"hi":1121,"n":3,"rr":1063,"mr":1092},{"m":"llama-3.2-1b-instruct","r":1083,"s":9.77,"lo":1026,"hi":1147,"n":6,"rr":1210,"mr":1080},{"m":"qwen3.5-0.8b","r":1084,"s":9.71,"lo":969,"hi":1149,"n":17,"rr":1080,"mr":1076},{"m":"gemma-3-1b","r":1085,"s":9.7,"lo":870,"hi":1156,"n":6,"rr":1099,"mr":1091},{"m":"solar-10.7b-v1.0","r":1086,"s":9.69,"lo":963,"hi":1138,"n":4,"rr":991,"mr":1070},{"m":"olmoe-1b-7b","r":1087,"s":9.66,"lo":1032,"hi":1143,"n":11,"rr":1143,"mr":1075},{"m":"gemma-4-e4b","r":1088,"s":9.58,"lo":873,"hi":1189,"n":7,"rr":894,"mr":1083},{"m":"vllm-sr-decision-2.0-eos-0.8b","r":1089,"s":9.46,"lo":974,"hi":1126,"n":4,"rr":929,"mr":1065},{"m":"internvl-chat-v1.5","r":1090,"s":9.4,"lo":741,"hi":1150,"n":5,"rr":1122,"mr":1128},{"m":"olmo-2-0425-1b-instruct","r":1091,"s":9.39,"lo":1032,"hi":1154,"n":10,"rr":1142,"mr":1087},{"m":"smollm2-1.7b-instruct","r":1092,"s":9.36,"lo":1034,"hi":1164,"n":10,"rr":1147,"mr":1089},{"m":"baichuan2-13b-chat","r":1093,"s":9.34,"lo":965,"hi":1137,"n":3,"rr":1067,"mr":1108},{"m":"baichuan2-13b-base","r":1094,"s":9.29,"lo":1009,"hi":1111,"n":6,"rr":857,"mr":1085},{"m":"mistral-7b-v0.2","r":1095,"s":9.24,"lo":851,"hi":1126,"n":3,"rr":870,"mr":1093},{"m":"vllm-sr-d3-edge","r":1096,"s":9.21,"lo":950,"hi":1134,"n":4,"rr":923,"mr":1073},{"m":"llemma-7b","r":1097,"s":9.14,"lo":982,"hi":1122,"n":4,"rr":1158,"mr":1115},{"m":"vllm-sr-decision-2.0-kai-0.6b","r":1098,"s":9.12,"lo":977,"hi":1130,"n":4,"rr":935,"mr":1072},{"m":"falcon3-1b","r":1099,"s":9.08,"lo":1036,"hi":1153,"n":9,"rr":1193,"mr":1100},{"m":"t5gemma-2-4b-4b","r":1100,"s":9.02,"lo":1027,"hi":1117,"n":7,"rr":1007,"mr":1096},{"m":"llama-2-13b-chat","r":1101,"s":8.99,"lo":715,"hi":1169,"n":4,"rr":954,"mr":1122},{"m":"janus-pro-7b","r":1102,"s":8.97,"lo":893,"hi":1113,"n":4,"rr":920,"mr":1117},{"m":"llama-1-33b","r":1103,"s":8.97,"lo":974,"hi":1120,"n":6,"rr":875,"mr":1099},{"m":"qwen2-0.5b-instruct","r":1104,"s":8.91,"lo":1010,"hi":1126,"n":4,"rr":1174,"mr":1103},{"m":"llava-1.6-13b","r":1105,"s":8.87,"lo":821,"hi":1153,"n":3,"rr":1047,"mr":1137},{"m":"minicpm4-0.5b","r":1106,"s":8.85,"lo":1001,"hi":1142,"n":4,"rr":761,"mr":1106},{"m":"deepseek-coder-6.7b-base","r":1107,"s":8.83,"lo":1002,"hi":1161,"n":4,"rr":1137,"mr":1097},{"m":"stablelm-zephyr-3b","r":1108,"s":8.82,"lo":1019,"hi":1125,"n":5,"rr":962,"mr":1098},{"m":"aquila2-7b","r":1109,"s":8.77,"lo":735,"hi":1139,"n":3,"rr":753,"mr":1134},{"m":"qwen1.5-14b-chat","r":1110,"s":8.68,"lo":768,"hi":1144,"n":3,"rr":881,"mr":1101},{"m":"tigerbot-13b-base","r":1111,"s":8.62,"lo":523,"hi":1129,"n":3,"rr":839,"mr":1138},{"m":"granite-4-h-300m","r":1112,"s":8.54,"lo":950,"hi":1156,"n":3,"rr":1148,"mr":1079},{"m":"mobilellm-p1-base","r":1113,"s":8.53,"lo":713,"hi":1128,"n":3,"rr":765,"mr":1107},{"m":"internlm2-1.8b","r":1114,"s":8.49,"lo":898,"hi":1132,"n":3,"rr":1183,"mr":1125},{"m":"internlm2-chat-1.8b","r":1115,"s":8.44,"lo":1045,"hi":1121,"n":3,"rr":1139,"mr":1121},{"m":"palm-62b","r":1116,"s":8.43,"lo":689,"hi":1131,"n":3,"rr":723,"mr":1119},{"m":"gemma-2-2b","r":1117,"s":8.43,"lo":1010,"hi":1151,"n":9,"rr":1105,"mr":1078},{"m":"mobilellm-r1-360m-base","r":1118,"s":8.42,"lo":1029,"hi":1139,"n":3,"rr":1184,"mr":1109},{"m":"minicpm-1b-sft","r":1119,"s":8.39,"lo":1010,"hi":1135,"n":5,"rr":965,"mr":1110},{"m":"telechat-7b","r":1120,"s":8.24,"lo":922,"hi":1130,"n":3,"rr":1120,"mr":1124},{"m":"lfm2-350m","r":1121,"s":8.07,"lo":901,"hi":1158,"n":5,"rr":1146,"mr":1116},{"m":"qwen-7b-chat","r":1122,"s":7.98,"lo":1045,"hi":1160,"n":5,"rr":1004,"mr":1120},{"m":"mobilemoe-s","r":1123,"s":7.96,"lo":1054,"hi":1154,"n":7,"rr":1053,"mr":1111},{"m":"internlm2-base-7b","r":1124,"s":7.94,"lo":870,"hi":1136,"n":3,"rr":1117,"mr":1129},{"m":"sharegpt4v-7b","r":1125,"s":7.92,"lo":831,"hi":1178,"n":3,"rr":1156,"mr":1163},{"m":"llava-1.5-13b","r":1126,"s":7.89,"lo":861,"hi":1176,"n":4,"rr":1039,"mr":1149},{"m":"qwen-vl","r":1127,"s":7.85,"lo":927,"hi":1164,"n":3,"rr":703,"mr":1161},{"m":"llama-2-13b","r":1128,"s":7.73,"lo":1018,"hi":1146,"n":6,"rr":914,"mr":1118},{"m":"d1-omni-600m","r":1129,"s":7.57,"lo":1024,"hi":1156,"n":4,"rr":996,"mr":1114},{"m":"llama-2-34b","r":1130,"s":7.54,"lo":888,"hi":1158,"n":3,"rr":1111,"mr":1142},{"m":"internvl2-1b","r":1131,"s":7.54,"lo":981,"hi":1174,"n":5,"rr":1187,"mr":1160},{"m":"internvl2-2b","r":1132,"s":7.54,"lo":1051,"hi":1158,"n":8,"rr":1154,"mr":1147},{"m":"qwen-vl-chat","r":1133,"s":7.52,"lo":825,"hi":1175,"n":3,"rr":826,"mr":1171},{"m":"qwen2-0.5b","r":1134,"s":7.5,"lo":1020,"hi":1165,"n":5,"rr":1163,"mr":1135},{"m":"internlm-7b","r":1135,"s":7.46,"lo":989,"hi":1151,"n":6,"rr":983,"mr":1133},{"m":"granite-4-300m","r":1136,"s":7.42,"lo":893,"hi":1162,"n":3,"rr":1164,"mr":1082},{"m":"qwen2.5-coder-0.5b","r":1137,"s":7.41,"lo":1021,"hi":1167,"n":4,"rr":1153,"mr":1113},{"m":"smollm2-1.7b-base","r":1138,"s":7.35,"lo":1053,"hi":1158,"n":6,"rr":1179,"mr":1123},{"m":"baichuan2-7b-chat","r":1139,"s":7.31,"lo":1038,"hi":1151,"n":5,"rr":992,"mr":1136},{"m":"llava-onevision-0.5b","r":1140,"s":7.31,"lo":860,"hi":1171,"n":3,"rr":1114,"mr":1175},{"m":"starcoder2-7b","r":1141,"s":7.21,"lo":1014,"hi":1159,"n":4,"rr":1159,"mr":1127},{"m":"mistral-7b-instruct-v0.1","r":1142,"s":7.1,"lo":1009,"hi":1172,"n":5,"rr":985,"mr":1112},{"m":"bitcpm-cann-0.5b","r":1143,"s":7.06,"lo":1039,"hi":1166,"n":4,"rr":900,"mr":1126},{"m":"huginn-3.5b","r":1144,"s":7.01,"lo":1033,"hi":1165,"n":4,"rr":1171,"mr":1131},{"m":"chatglm2-6b","r":1145,"s":6.98,"lo":1043,"hi":1154,"n":5,"rr":1017,"mr":1141},{"m":"codeqwen1.5-7b","r":1146,"s":6.86,"lo":1046,"hi":1165,"n":4,"rr":1160,"mr":1139},{"m":"qwen1.5-1.8b","r":1147,"s":6.86,"lo":1059,"hi":1163,"n":5,"rr":1062,"mr":1144},{"m":"llama-3.2-1.24b-base","r":1148,"s":6.83,"lo":1056,"hi":1183,"n":10,"rr":1213,"mr":1130},{"m":"bielik-7b-instruct-v0.1","r":1149,"s":6.81,"lo":970,"hi":1154,"n":3,"rr":1049,"mr":1145},{"m":"gpt-3","r":1150,"s":6.76,"lo":1041,"hi":1160,"n":5,"rr":908,"mr":1143},{"m":"gemma-2b","r":1151,"s":6.72,"lo":1063,"hi":1175,"n":5,"rr":1092,"mr":1140},{"m":"llama-2-7b-chat","r":1152,"s":6.68,"lo":1062,"hi":1159,"n":6,"rr":963,"mr":1146},{"m":"internlm-chat-7b","r":1153,"s":6.67,"lo":1038,"hi":1159,"n":3,"rr":1162,"mr":1158},{"m":"falcon-40b","r":1154,"s":6.67,"lo":1039,"hi":1167,"n":6,"rr":980,"mr":1132},{"m":"telechat-1b","r":1155,"s":6.6,"lo":1075,"hi":1165,"n":3,"rr":1181,"mr":1155},{"m":"chatglm2-6b-base","r":1156,"s":6.53,"lo":1073,"hi":1159,"n":3,"rr":1173,"mr":1164},{"m":"baichuan-13b-base","r":1157,"s":6.45,"lo":1076,"hi":1166,"n":6,"rr":1028,"mr":1150},{"m":"yi-6b","r":1158,"s":6.36,"lo":1002,"hi":1167,"n":4,"rr":1104,"mr":1156},{"m":"bielik-7b-v0.1","r":1159,"s":6.34,"lo":969,"hi":1162,"n":3,"rr":1087,"mr":1154},{"m":"olmo-2-0425-1b-base","r":1160,"s":6.34,"lo":1076,"hi":1174,"n":3,"rr":1172,"mr":1148},{"m":"open-llama-13b","r":1161,"s":6.27,"lo":1032,"hi":1189,"n":4,"rr":1001,"mr":1153},{"m":"bluelm-7b-base","r":1162,"s":6.13,"lo":996,"hi":1167,"n":3,"rr":1170,"mr":1170},{"m":"olmo-1.7-7b","r":1163,"s":6.02,"lo":989,"hi":1167,"n":5,"rr":1074,"mr":1165},{"m":"llama-1-13b","r":1164,"s":5.79,"lo":1062,"hi":1178,"n":6,"rr":1021,"mr":1151},{"m":"codellama-7b","r":1165,"s":5.73,"lo":1084,"hi":1184,"n":6,"rr":1149,"mr":1169},{"m":"qwen-1.8b","r":1166,"s":5.68,"lo":1084,"hi":1173,"n":5,"rr":1088,"mr":1166},{"m":"deepseek-llm-7b-base","r":1167,"s":5.59,"lo":1092,"hi":1178,"n":7,"rr":1066,"mr":1162},{"m":"starcoder2-3b","r":1168,"s":5.55,"lo":1048,"hi":1182,"n":4,"rr":1190,"mr":1152},{"m":"vicuna-13b","r":1169,"s":5.48,"lo":1039,"hi":1180,"n":3,"rr":1177,"mr":1172},{"m":"baichuan2-7b-base","r":1170,"s":5.41,"lo":1070,"hi":1177,"n":6,"rr":1084,"mr":1174},{"m":"llava-1.5-7b","r":1171,"s":5.36,"lo":941,"hi":1196,"n":5,"rr":1133,"mr":1189},{"m":"llama-2-7b","r":1172,"s":5.34,"lo":1078,"hi":1180,"n":7,"rr":1073,"mr":1168},{"m":"deepseek-moe-16b-base","r":1173,"s":5.24,"lo":1100,"hi":1180,"n":6,"rr":1103,"mr":1173},{"m":"xverse-13b","r":1174,"s":5.19,"lo":1072,"hi":1191,"n":5,"rr":1065,"mr":1157},{"m":"mobilellm-p1","r":1175,"s":5.18,"lo":1090,"hi":1198,"n":7,"rr":1126,"mr":1167},{"m":"pythia-2.8b","r":1176,"s":5.15,"lo":1019,"hi":1187,"n":3,"rr":691,"mr":1186},{"m":"gemma-4-e2b","r":1177,"s":5,"lo":1040,"hi":1187,"n":7,"rr":1034,"mr":1177},{"m":"gemini-nano-2","r":1178,"s":4.86,"lo":810,"hi":1189,"n":3,"rr":1131,"mr":1196},{"m":"gliner2.5-decide","r":1179,"s":4.81,"lo":1053,"hi":1192,"n":4,"rr":1115,"mr":1159},{"m":"mpt-30b","r":1180,"s":4.69,"lo":1092,"hi":1187,"n":6,"rr":1070,"mr":1178},{"m":"pythia-1.4b","r":1181,"s":4.65,"lo":1037,"hi":1192,"n":3,"rr":744,"mr":1193},{"m":"llama-3.2-1b","r":1182,"s":4.4,"lo":1057,"hi":1197,"n":6,"rr":1109,"mr":1190},{"m":"llama-1-7b","r":1183,"s":4.35,"lo":1109,"hi":1194,"n":6,"rr":1101,"mr":1183},{"m":"pythia-12b","r":1184,"s":4.35,"lo":1105,"hi":1203,"n":7,"rr":1110,"mr":1182},{"m":"pythia-1b","r":1185,"s":4.27,"lo":1031,"hi":1199,"n":3,"rr":791,"mr":1199},{"m":"qwen1.5-0.5b","r":1186,"s":4.27,"lo":1122,"hi":1195,"n":3,"rr":1201,"mr":1195},{"m":"mobilellm-r1-140m","r":1187,"s":4.15,"lo":1093,"hi":1207,"n":3,"rr":1217,"mr":1185},{"m":"deepseek-vl-1.3b","r":1188,"s":4.13,"lo":895,"hi":1196,"n":3,"rr":1180,"mr":1202},{"m":"mpt-7b","r":1189,"s":4.07,"lo":1120,"hi":1196,"n":6,"rr":1127,"mr":1187},{"m":"pythia-6.9b","r":1190,"s":4.03,"lo":1110,"hi":1205,"n":7,"rr":1119,"mr":1188},{"m":"deepseek-coder-1.3b-base","r":1191,"s":4.03,"lo":1012,"hi":1199,"n":4,"rr":1203,"mr":1176},{"m":"amberchat","r":1192,"s":3.97,"lo":1111,"hi":1200,"n":5,"rr":1192,"mr":1191},{"m":"t5gemma-2-1b-1b","r":1193,"s":3.96,"lo":1122,"hi":1199,"n":7,"rr":1182,"mr":1184},{"m":"trlm-135m","r":1194,"s":3.91,"lo":985,"hi":1213,"n":3,"rr":1189,"mr":1179},{"m":"emu3-8b","r":1195,"s":3.87,"lo":864,"hi":1214,"n":4,"rr":1097,"mr":1198},{"m":"vicuna-7b","r":1196,"s":3.83,"lo":1083,"hi":1198,"n":3,"rr":1198,"mr":1197},{"m":"laya","r":1197,"s":3.76,"lo":998,"hi":1203,"n":4,"rr":1141,"mr":1180},{"m":"falcon-7b","r":1198,"s":3.76,"lo":1127,"hi":1203,"n":6,"rr":1132,"mr":1194},{"m":"olmo-7b-instruct","r":1199,"s":3.62,"lo":945,"hi":1202,"n":5,"rr":1093,"mr":1181},{"m":"lumina-dimoo","r":1200,"s":3.43,"lo":904,"hi":1213,"n":3,"rr":1204,"mr":1200},{"m":"chinese-alpaca-plus-13b","r":1201,"s":3.37,"lo":1115,"hi":1203,"n":3,"rr":1205,"mr":1208},{"m":"chatglm-6b","r":1202,"s":3.37,"lo":1122,"hi":1208,"n":3,"rr":1211,"mr":1204},{"m":"pythia-410m","r":1203,"s":3.35,"lo":1061,"hi":1207,"n":3,"rr":899,"mr":1209},{"m":"baichuan-7b","r":1204,"s":3.33,"lo":1119,"hi":1202,"n":3,"rr":1206,"mr":1206},{"m":"gemma-3-270m-it","r":1205,"s":3.18,"lo":1109,"hi":1208,"n":9,"rr":1202,"mr":1192},{"m":"amber-7b","r":1206,"s":3.09,"lo":1117,"hi":1210,"n":5,"rr":1208,"mr":1201},{"m":"smollm2-360m-instruct","r":1207,"s":2.84,"lo":1132,"hi":1210,"n":8,"rr":1200,"mr":1203},{"m":"alpaca-7b","r":1208,"s":2.77,"lo":1133,"hi":1210,"n":3,"rr":1212,"mr":1207},{"m":"pythia-160m","r":1209,"s":2.67,"lo":1094,"hi":1211,"n":3,"rr":1005,"mr":1215},{"m":"smollm2-135m-instruct","r":1210,"s":2.56,"lo":1129,"hi":1213,"n":3,"rr":1218,"mr":1205},{"m":"t5gemma-2-270m-270m","r":1211,"s":2.42,"lo":1141,"hi":1214,"n":7,"rr":1207,"mr":1210},{"m":"gemma-3-pt-270m","r":1212,"s":2.3,"lo":1137,"hi":1213,"n":5,"rr":1196,"mr":1211},{"m":"olmo-7b","r":1213,"s":2.25,"lo":1131,"hi":1212,"n":5,"rr":1209,"mr":1214},{"m":"tinyllama-1.1b","r":1214,"s":2.24,"lo":1134,"hi":1214,"n":5,"rr":1195,"mr":1213},{"m":"pythia-70m","r":1215,"s":2.08,"lo":1091,"hi":1215,"n":3,"rr":1096,"mr":1218},{"m":"smollm2-360m-base","r":1216,"s":2.07,"lo":1145,"hi":1215,"n":5,"rr":1216,"mr":1212},{"m":"smollm2-135m-base","r":1217,"s":1.69,"lo":1144,"hi":1217,"n":3,"rr":1214,"mr":1217},{"m":"gemma-3-pt-1b","r":1218,"s":1.66,"lo":1149,"hi":1217,"n":3,"rr":1215,"mr":1216}]},"faix-text":{"name":"Text","n":1626,"nb":179,"acc":0.8511,"raw_acc":0.7071,"rows":[{"m":"gpt-6-astra","r":1,"s":94.54,"lo":1,"hi":4,"n":8,"rr":12,"mr":1},{"m":"claude-fable-5.1","r":2,"s":93.41,"lo":1,"hi":9,"n":9,"rr":18,"mr":4},{"m":"claude-fable-5","r":3,"s":93.3,"lo":2,"hi":8,"n":16,"rr":169,"mr":2},{"m":"claude-opus-5","r":4,"s":93.22,"lo":2,"hi":7,"n":12,"rr":27,"mr":3},{"m":"claude-mythos-5","r":5,"s":92.47,"lo":3,"hi":16,"n":6,"rr":23,"mr":5},{"m":"gpt-5.6-sol","r":6,"s":92.23,"lo":4,"hi":19,"n":23,"rr":308,"mr":6},{"m":"claude-opus-5.5","r":7,"s":91.89,"lo":1,"hi":137,"n":5,"rr":29,"mr":14},{"m":"gpt-5.4-pro","r":8,"s":91.83,"lo":6,"hi":18,"n":6,"rr":15,"mr":8},{"m":"gpt-5.5","r":9,"s":91.74,"lo":6,"hi":18,"n":33,"rr":188,"mr":7},{"m":"claude-mythos-preview","r":10,"s":91.62,"lo":7,"hi":18,"n":8,"rr":220,"mr":9},{"m":"muse-spark-1.2","r":11,"s":91.56,"lo":4,"hi":594,"n":3,"rr":176,"mr":18},{"m":"ling-3.1-flash","r":12,"s":91.53,"lo":7,"hi":82,"n":4,"rr":51,"mr":11},{"m":"kimi-k3","r":13,"s":91.04,"lo":6,"hi":28,"n":15,"rr":239,"mr":10},{"m":"glm-5.3","r":14,"s":90.99,"lo":9,"hi":62,"n":9,"rr":152,"mr":13},{"m":"gpt-5.4-xhigh","r":15,"s":90.75,"lo":12,"hi":110,"n":3,"rr":38,"mr":16},{"m":"mirothinker-h1","r":16,"s":90.67,"lo":11,"hi":44,"n":3,"rr":28,"mr":17},{"m":"qwen3.8-max","r":17,"s":90.63,"lo":14,"hi":28,"n":12,"rr":333,"mr":15},{"m":"claude-opus-4.8","r":18,"s":90.63,"lo":14,"hi":27,"n":27,"rr":179,"mr":12},{"m":"deepseek-v4.1-flash","r":19,"s":90.54,"lo":12,"hi":71,"n":7,"rr":134,"mr":19},{"m":"fugu-ultra","r":20,"s":90.34,"lo":10,"hi":91,"n":5,"rr":108,"mr":20},{"m":"claude-opus-4.6-high","r":21,"s":90.27,"lo":17,"hi":203,"n":3,"rr":48,"mr":21},{"m":"claude-opus-4.6-max","r":22,"s":90.1,"lo":18,"hi":186,"n":3,"rr":62,"mr":24},{"m":"gpt-5.4-thinking","r":23,"s":89.92,"lo":12,"hi":82,"n":3,"rr":32,"mr":30},{"m":"claude-opus-4.7","r":24,"s":89.87,"lo":17,"hi":51,"n":31,"rr":394,"mr":23},{"m":"gemini-3.1-pro","r":25,"s":89.78,"lo":15,"hi":44,"n":41,"rr":456,"mr":22},{"m":"seed2.1-pro","r":26,"s":89.73,"lo":17,"hi":49,"n":17,"rr":337,"mr":25},{"m":"hy4-preview","r":27,"s":89.69,"lo":19,"hi":102,"n":3,"rr":31,"mr":39},{"m":"gemini-3.5-flash","r":28,"s":89.69,"lo":20,"hi":166,"n":11,"rr":396,"mr":26},{"m":"muse-spark-open","r":29,"s":89.69,"lo":7,"hi":221,"n":3,"rr":107,"mr":50},{"m":"seed2.1-turbo","r":30,"s":89.68,"lo":21,"hi":50,"n":13,"rr":534,"mr":28},{"m":"ornith-1.5-397b","r":31,"s":89.55,"lo":23,"hi":57,"n":5,"rr":40,"mr":32},{"m":"gpt-5.4","r":32,"s":89.51,"lo":22,"hi":51,"n":32,"rr":316,"mr":27},{"m":"deepseek-v4-pro-0813","r":33,"s":89.29,"lo":25,"hi":81,"n":6,"rr":81,"mr":41},{"m":"claude-sonnet-5","r":34,"s":89.24,"lo":25,"hi":52,"n":11,"rr":436,"mr":31},{"m":"claude-opus-4.6","r":35,"s":89.24,"lo":25,"hi":50,"n":43,"rr":341,"mr":29},{"m":"gpt-5.6-terra","r":36,"s":89.2,"lo":22,"hi":99,"n":10,"rr":222,"mr":34},{"m":"fugu","r":37,"s":89.14,"lo":17,"hi":108,"n":5,"rr":170,"mr":40},{"m":"dots3-note-preview","r":38,"s":89.03,"lo":11,"hi":92,"n":7,"rr":61,"mr":38},{"m":"muse-spark-1.1","r":39,"s":89,"lo":9,"hi":255,"n":3,"rr":279,"mr":60},{"m":"gpt-5.2-pro","r":40,"s":88.95,"lo":31,"hi":64,"n":5,"rr":129,"mr":45},{"m":"gemini-4-argon","r":41,"s":88.94,"lo":1,"hi":667,"n":3,"rr":11,"mr":68},{"m":"qwen3.8-flash-next","r":42,"s":88.88,"lo":23,"hi":72,"n":16,"rr":103,"mr":33},{"m":"deepseek-v4-flash-0731","r":43,"s":88.87,"lo":31,"hi":66,"n":21,"rr":148,"mr":35},{"m":"qwen3.8-omni-flash","r":44,"s":88.79,"lo":31,"hi":72,"n":5,"rr":65,"mr":48},{"m":"deepseek-v4-pro-thinking-max","r":45,"s":88.79,"lo":29,"hi":58,"n":30,"rr":131,"mr":37},{"m":"gpt-5.2-high","r":46,"s":88.74,"lo":31,"hi":59,"n":22,"rr":166,"mr":43},{"m":"grok-4.2","r":47,"s":88.67,"lo":29,"hi":100,"n":8,"rr":415,"mr":46},{"m":"glm-5.2","r":48,"s":88.64,"lo":24,"hi":80,"n":22,"rr":187,"mr":36},{"m":"deepseek-v4-pro","r":49,"s":88.59,"lo":34,"hi":67,"n":25,"rr":153,"mr":44},{"m":"gpt-5.6-luna","r":50,"s":88.5,"lo":31,"hi":66,"n":15,"rr":219,"mr":47},{"m":"qwen3.7-max","r":51,"s":88.43,"lo":34,"hi":65,"n":24,"rr":136,"mr":42},{"m":"gpt-5.3-codex","r":52,"s":88.38,"lo":30,"hi":74,"n":6,"rr":210,"mr":53},{"m":"claude-sonnet-4.6-high","r":53,"s":88.38,"lo":32,"hi":246,"n":3,"rr":125,"mr":54},{"m":"nex-n2-pro","r":54,"s":88.26,"lo":39,"hi":84,"n":6,"rr":73,"mr":52},{"m":"glm-5.3-flash","r":55,"s":88.21,"lo":25,"hi":159,"n":17,"rr":193,"mr":51},{"m":"beam","r":56,"s":88.19,"lo":38,"hi":67,"n":11,"rr":174,"mr":49},{"m":"gemini-3.8-flash","r":57,"s":88.04,"lo":11,"hi":252,"n":4,"rr":41,"mr":79},{"m":"ornith-1.0-397b","r":58,"s":87.82,"lo":51,"hi":80,"n":6,"rr":130,"mr":57},{"m":"ornith-1.5-122b","r":59,"s":87.6,"lo":54,"hi":96,"n":5,"rr":267,"mr":66},{"m":"kimi-k2.6-thinking","r":60,"s":87.59,"lo":49,"hi":79,"n":32,"rr":185,"mr":55},{"m":"gpt-5.2-extra-high","r":61,"s":87.52,"lo":43,"hi":135,"n":5,"rr":214,"mr":62},{"m":"claude-sonnet-4.6","r":62,"s":87.51,"lo":43,"hi":107,"n":26,"rr":374,"mr":59},{"m":"sage-a1.5","r":63,"s":87.51,"lo":41,"hi":270,"n":4,"rr":413,"mr":77},{"m":"minimax-m3","r":64,"s":87.49,"lo":47,"hi":98,"n":10,"rr":264,"mr":61},{"m":"hy3","r":65,"s":87.45,"lo":50,"hi":84,"n":12,"rr":203,"mr":58},{"m":"qwen3.7-plus","r":66,"s":87.39,"lo":49,"hi":84,"n":21,"rr":199,"mr":56},{"m":"gpt-6.1-sol","r":67,"s":87.32,"lo":24,"hi":671,"n":3,"rr":24,"mr":97},{"m":"gpt-5.2-thinking-xhigh","r":68,"s":87.27,"lo":44,"hi":99,"n":18,"rr":576,"mr":65},{"m":"k2-horizon-375b-a23b","r":69,"s":87.24,"lo":37,"hi":185,"n":5,"rr":471,"mr":83},{"m":"kimi-k2.6","r":70,"s":87.23,"lo":30,"hi":109,"n":10,"rr":163,"mr":64},{"m":"muse-spark","r":71,"s":87.15,"lo":53,"hi":113,"n":9,"rr":684,"mr":70},{"m":"apodex-1.0","r":72,"s":87.09,"lo":35,"hi":118,"n":3,"rr":320,"mr":92},{"m":"gpt-5.2","r":73,"s":87.07,"lo":56,"hi":91,"n":48,"rr":373,"mr":63},{"m":"bigbang-v1","r":74,"s":87.05,"lo":39,"hi":176,"n":5,"rr":594,"mr":81},{"m":"gpt-5.2-thinking","r":75,"s":86.96,"lo":55,"hi":121,"n":18,"rr":195,"mr":67},{"m":"mirothinker-1.7","r":76,"s":86.92,"lo":52,"hi":105,"n":3,"rr":147,"mr":93},{"m":"deepseek-v4-pro-thinking","r":77,"s":86.86,"lo":65,"hi":95,"n":10,"rr":154,"mr":69},{"m":"intern-s2-397b","r":78,"s":86.81,"lo":40,"hi":245,"n":3,"rr":260,"mr":101},{"m":"longcat-2.0","r":79,"s":86.71,"lo":62,"hi":231,"n":5,"rr":49,"mr":87},{"m":"inkling-small","r":80,"s":86.68,"lo":65,"hi":100,"n":18,"rr":204,"mr":74},{"m":"deepseek-v3.2-speciale","r":81,"s":86.64,"lo":7,"hi":305,"n":4,"rr":78,"mr":89},{"m":"inkling","r":82,"s":86.64,"lo":66,"hi":93,"n":13,"rr":457,"mr":80},{"m":"claude-opus-4.5-thinking","r":83,"s":86.59,"lo":40,"hi":132,"n":19,"rr":522,"mr":72},{"m":"agents-a1","r":84,"s":86.55,"lo":19,"hi":164,"n":10,"rr":464,"mr":85},{"m":"gemini-3-pro","r":85,"s":86.5,"lo":60,"hi":104,"n":67,"rr":303,"mr":73},{"m":"claude-opus-4.5","r":86,"s":86.41,"lo":63,"hi":105,"n":64,"rr":335,"mr":78},{"m":"glm-5.1","r":87,"s":86.37,"lo":62,"hi":103,"n":35,"rr":248,"mr":76},{"m":"seed2.0-pro","r":88,"s":86.36,"lo":66,"hi":161,"n":24,"rr":269,"mr":86},{"m":"deepseek-v4-flash-thinking-max","r":89,"s":86.3,"lo":68,"hi":113,"n":20,"rr":254,"mr":82},{"m":"mimo-v2-pro","r":90,"s":86.27,"lo":49,"hi":134,"n":5,"rr":224,"mr":96},{"m":"jais-3-375b-a23b","r":91,"s":86.24,"lo":32,"hi":222,"n":3,"rr":409,"mr":109},{"m":"intern-s2-preview-397b","r":92,"s":86.24,"lo":53,"hi":236,"n":3,"rr":273,"mr":102},{"m":"kat-coder-pro-v2","r":93,"s":86.23,"lo":74,"hi":126,"n":6,"rr":352,"mr":91},{"m":"qwen3.6-plus","r":94,"s":86.22,"lo":74,"hi":102,"n":25,"rr":234,"mr":75},{"m":"grm-3.2-sky","r":95,"s":86.2,"lo":68,"hi":125,"n":5,"rr":14,"mr":71},{"m":"qwen3.5-397b-a17b","r":96,"s":86.13,"lo":72,"hi":109,"n":40,"rr":301,"mr":84},{"m":"deepseek-v4-flash","r":97,"s":86.11,"lo":70,"hi":113,"n":25,"rr":358,"mr":90},{"m":"kimi-k2.7-code","r":98,"s":86.04,"lo":63,"hi":285,"n":4,"rr":371,"mr":100},{"m":"qwen3.6-max-preview","r":99,"s":86.02,"lo":75,"hi":211,"n":5,"rr":940,"mr":108},{"m":"grok-4.5","r":100,"s":86.01,"lo":54,"hi":673,"n":3,"rr":133,"mr":114},{"m":"mirothinker-v1.5-235b","r":101,"s":85.99,"lo":65,"hi":129,"n":4,"rr":140,"mr":105},{"m":"gemini-3-pro-preview","r":102,"s":85.98,"lo":52,"hi":122,"n":27,"rr":160,"mr":88},{"m":"mercury-3","r":103,"s":85.83,"lo":69,"hi":201,"n":4,"rr":186,"mr":106},{"m":"motif-3","r":104,"s":85.76,"lo":80,"hi":178,"n":6,"rr":243,"mr":95},{"m":"mirothinker-1.7-mini","r":105,"s":85.56,"lo":73,"hi":135,"n":3,"rr":274,"mr":115},{"m":"longcat-flash-thinking-2601","r":106,"s":85.44,"lo":43,"hi":163,"n":11,"rr":282,"mr":99},{"m":"ring-2.6-1t-xhigh","r":107,"s":85.44,"lo":42,"hi":179,"n":13,"rr":247,"mr":103},{"m":"muse-glimmer-30b","r":108,"s":85.27,"lo":78,"hi":149,"n":14,"rr":311,"mr":94},{"m":"openpangu-2.0-pro-thinking","r":109,"s":85.21,"lo":66,"hi":142,"n":12,"rr":172,"mr":98},{"m":"ax-k2","r":110,"s":85.14,"lo":30,"hi":194,"n":7,"rr":191,"mr":107},{"m":"ling-3.0-flash","r":111,"s":85.13,"lo":87,"hi":151,"n":8,"rr":158,"mr":110},{"m":"gpt-6-sol","r":112,"s":85.12,"lo":26,"hi":586,"n":3,"rr":26,"mr":164},{"m":"snowdon-1.1-small","r":113,"s":84.9,"lo":15,"hi":432,"n":7,"rr":36,"mr":130},{"m":"gpt-5.2-medium","r":114,"s":84.85,"lo":78,"hi":184,"n":4,"rr":566,"mr":125},{"m":"gemini-3.5-flash-lite","r":115,"s":84.83,"lo":73,"hi":180,"n":9,"rr":276,"mr":104},{"m":"gemini-3-flash","r":116,"s":84.63,"lo":85,"hi":156,"n":34,"rr":608,"mr":112},{"m":"nemotron-3.5-super-vl-120b-a12b","r":117,"s":84.54,"lo":94,"hi":172,"n":15,"rr":290,"mr":111},{"m":"mimo-v2.5-pro","r":118,"s":84.48,"lo":73,"hi":222,"n":4,"rr":88,"mr":118},{"m":"iquest-coder-v1-40b-loop-thinking","r":119,"s":84.43,"lo":1,"hi":190,"n":4,"rr":10,"mr":151},{"m":"ornith-1.5-35b-a3b","r":120,"s":84.39,"lo":102,"hi":192,"n":9,"rr":681,"mr":127},{"m":"areal-sea-235b-a22b","r":121,"s":84.3,"lo":96,"hi":271,"n":3,"rr":74,"mr":161},{"m":"gpt-5.4-mini","r":122,"s":84.3,"lo":106,"hi":156,"n":25,"rr":461,"mr":123},{"m":"kimi-k2.5","r":123,"s":84.27,"lo":100,"hi":148,"n":40,"rr":598,"mr":116},{"m":"hy3-preview","r":124,"s":84.26,"lo":112,"hi":145,"n":8,"rr":493,"mr":129},{"m":"nemotron-3-ultra","r":125,"s":84.24,"lo":102,"hi":158,"n":23,"rr":343,"mr":117},{"m":"deepseek-v4-flash-thinking","r":126,"s":84.17,"lo":103,"hi":155,"n":10,"rr":364,"mr":121},{"m":"qwen3.8-27b","r":127,"s":84.16,"lo":92,"hi":179,"n":29,"rr":192,"mr":113},{"m":"kimi-k2.5-thinking","r":128,"s":84.12,"lo":101,"hi":155,"n":28,"rr":596,"mr":124},{"m":"seed2.0-lite-0428","r":129,"s":84.1,"lo":103,"hi":170,"n":9,"rr":590,"mr":135},{"m":"longcat-flash-thinking-zigzag","r":130,"s":84.08,"lo":69,"hi":172,"n":9,"rr":181,"mr":131},{"m":"glm-5","r":131,"s":84.01,"lo":99,"hi":162,"n":35,"rr":479,"mr":119},{"m":"minimax-m2.7","r":132,"s":83.89,"lo":105,"hi":169,"n":26,"rr":447,"mr":128},{"m":"mimo-v2.5","r":133,"s":83.89,"lo":104,"hi":185,"n":14,"rr":612,"mr":120},{"m":"step-3.5-flash-20260204","r":134,"s":83.79,"lo":100,"hi":177,"n":15,"rr":569,"mr":126},{"m":"nemotron-3.5-bolt-74b-a9b","r":135,"s":83.75,"lo":106,"hi":230,"n":5,"rr":652,"mr":148},{"m":"step-3.7-flash","r":136,"s":83.75,"lo":102,"hi":191,"n":9,"rr":265,"mr":132},{"m":"qwen3.6-27b","r":137,"s":83.71,"lo":117,"hi":171,"n":18,"rr":391,"mr":122},{"m":"gpt-5","r":138,"s":83.66,"lo":91,"hi":176,"n":60,"rr":519,"mr":134},{"m":"gemini-3.6-flash","r":139,"s":83.66,"lo":96,"hi":662,"n":4,"rr":469,"mr":172},{"m":"seed1.8","r":140,"s":83.64,"lo":99,"hi":168,"n":17,"rr":427,"mr":133},{"m":"gpt-5-pro","r":141,"s":83.62,"lo":106,"hi":173,"n":4,"rr":611,"mr":155},{"m":"gpt-5.1-thinking","r":142,"s":83.52,"lo":106,"hi":183,"n":3,"rr":913,"mr":160},{"m":"ornith-1.0-35b","r":143,"s":83.5,"lo":125,"hi":176,"n":7,"rr":758,"mr":144},{"m":"claude-sonnet-4.5","r":144,"s":83.49,"lo":98,"hi":170,"n":62,"rr":537,"mr":136},{"m":"gpt-5.1-high","r":145,"s":83.47,"lo":112,"hi":171,"n":11,"rr":881,"mr":138},{"m":"gpt-5-codex","r":146,"s":83.44,"lo":116,"hi":174,"n":7,"rr":791,"mr":141},{"m":"comet-60b-a12b-fp8","r":147,"s":83.3,"lo":118,"hi":189,"n":9,"rr":387,"mr":145},{"m":"iquest-coder-v1-40b-thinking","r":148,"s":83.26,"lo":2,"hi":232,"n":5,"rr":50,"mr":175},{"m":"glm-4.7-thinking","r":149,"s":83.21,"lo":68,"hi":201,"n":8,"rr":646,"mr":150},{"m":"ring-1t-2.5","r":150,"s":83.18,"lo":117,"hi":215,"n":3,"rr":874,"mr":158},{"m":"seed2.0-lite","r":151,"s":83.17,"lo":121,"hi":212,"n":23,"rr":510,"mr":154},{"m":"kimi-k2-thinking","r":152,"s":83.14,"lo":116,"hi":193,"n":31,"rr":536,"mr":137},{"m":"flint","r":153,"s":83.12,"lo":81,"hi":205,"n":4,"rr":43,"mr":169},{"m":"mai-thinking-1","r":154,"s":83.1,"lo":123,"hi":189,"n":5,"rr":486,"mr":147},{"m":"openpangu-2.0-flash-thinking","r":155,"s":83.05,"lo":116,"hi":185,"n":12,"rr":347,"mr":149},{"m":"flint-nvfp4","r":156,"s":83.05,"lo":93,"hi":201,"n":4,"rr":45,"mr":166},{"m":"deepseek-v3.2-thinking","r":157,"s":83.03,"lo":121,"hi":190,"n":40,"rr":704,"mr":140},{"m":"gpt-5.1","r":158,"s":83.03,"lo":105,"hi":198,"n":21,"rr":507,"mr":146},{"m":"qwen3-max-thinking","r":159,"s":82.99,"lo":110,"hi":187,"n":28,"rr":367,"mr":142},{"m":"qwen3.6-35b-a3b","r":160,"s":82.95,"lo":117,"hi":183,"n":34,"rr":446,"mr":139},{"m":"gpt-5-thinking","r":161,"s":82.94,"lo":118,"hi":188,"n":10,"rr":923,"mr":163},{"m":"mirothinker-v1.5-30b","r":162,"s":82.89,"lo":115,"hi":197,"n":4,"rr":401,"mr":177},{"m":"comet-60b-a12b","r":163,"s":82.85,"lo":119,"hi":206,"n":9,"rr":416,"mr":159},{"m":"solar-pro-4","r":164,"s":82.83,"lo":104,"hi":200,"n":7,"rr":227,"mr":162},{"m":"qwen3.5-122b-a10b","r":165,"s":82.77,"lo":127,"hi":179,"n":37,"rr":549,"mr":153},{"m":"gpt-5-high","r":166,"s":82.74,"lo":114,"hi":187,"n":45,"rr":637,"mr":156},{"m":"raon-1-mini-preview","r":167,"s":82.67,"lo":109,"hi":237,"n":9,"rr":441,"mr":143},{"m":"nemotron-3.5-super-vl-120b-a12b-nvfp4","r":168,"s":82.63,"lo":122,"hi":221,"n":9,"rr":458,"mr":165},{"m":"gpt-5-thinking-high","r":169,"s":82.6,"lo":114,"hi":417,"n":4,"rr":249,"mr":174},{"m":"nex-n2-mini","r":170,"s":82.59,"lo":89,"hi":271,"n":13,"rr":852,"mr":152},{"m":"ernie-5.0","r":171,"s":82.59,"lo":105,"hi":241,"n":15,"rr":67,"mr":157},{"m":"laguna-m.1","r":172,"s":82.47,"lo":148,"hi":208,"n":4,"rr":903,"mr":176},{"m":"ring-2.6-1t-high","r":173,"s":82.47,"lo":72,"hi":241,"n":6,"rr":94,"mr":167},{"m":"gpt-5-codex-high","r":174,"s":82.45,"lo":146,"hi":204,"n":4,"rr":690,"mr":179},{"m":"comet-60b-a12b-nvfp4","r":175,"s":82.43,"lo":127,"hi":222,"n":9,"rr":472,"mr":170},{"m":"gpt-6-luna-medium","r":176,"s":82.43,"lo":128,"hi":214,"n":6,"rr":892,"mr":178},{"m":"pacore-8b","r":177,"s":82.38,"lo":106,"hi":486,"n":3,"rr":283,"mr":192},{"m":"minimax-m2.5","r":178,"s":82.36,"lo":113,"hi":245,"n":12,"rr":949,"mr":173},{"m":"mimo-v2-flash","r":179,"s":82.17,"lo":138,"hi":205,"n":13,"rr":650,"mr":168},{"m":"oxcoder-9b","r":180,"s":82.1,"lo":159,"hi":222,"n":4,"rr":495,"mr":184},{"m":"gpt-5-medium","r":181,"s":82.07,"lo":99,"hi":226,"n":7,"rr":752,"mr":185},{"m":"solar-open-2-250b","r":182,"s":81.93,"lo":102,"hi":224,"n":11,"rr":552,"mr":171},{"m":"mercury-2.5","r":183,"s":81.85,"lo":145,"hi":264,"n":5,"rr":878,"mr":190},{"m":"xing4.0-29b-a4b","r":184,"s":81.83,"lo":151,"hi":281,"n":4,"rr":528,"mr":188},{"m":"mai-code-1-flash","r":185,"s":81.59,"lo":137,"hi":267,"n":6,"rr":585,"mr":186},{"m":"o3","r":186,"s":81.47,"lo":145,"hi":214,"n":42,"rr":687,"mr":183},{"m":"agnes-3.0-flash-preview","r":187,"s":81.3,"lo":158,"hi":279,"n":4,"rr":588,"mr":202},{"m":"qwen3.5-35b-a3b","r":188,"s":81.26,"lo":161,"hi":212,"n":40,"rr":672,"mr":182},{"m":"minimax-m2.1","r":189,"s":81.21,"lo":157,"hi":245,"n":17,"rr":761,"mr":181},{"m":"gemini-3-flash-preview","r":190,"s":81.09,"lo":70,"hi":367,"n":14,"rr":164,"mr":198},{"m":"qwen3.5-27b","r":191,"s":81.05,"lo":159,"hi":226,"n":52,"rr":359,"mr":180},{"m":"nanbeige4.2-3b","r":192,"s":81.01,"lo":139,"hi":246,"n":12,"rr":738,"mr":187},{"m":"nova-2-pro","r":193,"s":80.84,"lo":127,"hi":260,"n":8,"rr":257,"mr":200},{"m":"longcat-flash-prover","r":194,"s":80.8,"lo":174,"hi":276,"n":4,"rr":278,"mr":203},{"m":"mirothinker-v1.0-72b","r":195,"s":80.8,"lo":85,"hi":267,"n":3,"rr":810,"mr":213},{"m":"claude-opus-4.1","r":196,"s":80.8,"lo":161,"hi":242,"n":28,"rr":883,"mr":191},{"m":"mistral-medium-3.5","r":197,"s":80.78,"lo":123,"hi":245,"n":13,"rr":744,"mr":189},{"m":"spark-x2.6-4b","r":198,"s":80.7,"lo":164,"hi":243,"n":11,"rr":661,"mr":195},{"m":"grok-4","r":199,"s":80.68,"lo":161,"hi":248,"n":33,"rr":680,"mr":194},{"m":"ring-1t","r":200,"s":80.68,"lo":165,"hi":513,"n":4,"rr":505,"mr":206},{"m":"deepseek-v3.2","r":201,"s":80.6,"lo":176,"hi":227,"n":49,"rr":667,"mr":196},{"m":"trinity-large-thinking","r":202,"s":80.57,"lo":75,"hi":335,"n":7,"rr":263,"mr":197},{"m":"gpt-5-mini-high","r":203,"s":80.52,"lo":159,"hi":230,"n":39,"rr":614,"mr":199},{"m":"qwen3-moe-2507","r":204,"s":80.45,"lo":81,"hi":370,"n":3,"rr":91,"mr":219},{"m":"claude-4.5-sonnet-thinking","r":205,"s":80.44,"lo":163,"hi":227,"n":33,"rr":851,"mr":204},{"m":"kat-coder-v2.5-dev","r":206,"s":80.38,"lo":189,"hi":283,"n":3,"rr":917,"mr":209},{"m":"ling-2.6-1t","r":207,"s":80.29,"lo":62,"hi":317,"n":9,"rr":951,"mr":205},{"m":"glm-4.7","r":208,"s":80.28,"lo":155,"hi":308,"n":21,"rr":410,"mr":193},{"m":"o3-pro-high","r":209,"s":80.25,"lo":147,"hi":286,"n":5,"rr":823,"mr":210},{"m":"intern-s2-preview","r":210,"s":80.19,"lo":138,"hi":271,"n":4,"rr":517,"mr":208},{"m":"claude-haiku-5.5-medium","r":211,"s":80.17,"lo":173,"hi":277,"n":6,"rr":1050,"mr":212},{"m":"qwen3.8-27b-ud-q4-k-xl","r":212,"s":80.09,"lo":150,"hi":352,"n":10,"rr":35,"mr":207},{"m":"laguna-xs.2","r":213,"s":80.02,"lo":184,"hi":266,"n":4,"rr":1114,"mr":218},{"m":"o3-pro","r":214,"s":79.93,"lo":150,"hi":321,"n":3,"rr":1226,"mr":222},{"m":"kolibri-1","r":215,"s":79.93,"lo":127,"hi":296,"n":10,"rr":229,"mr":201},{"m":"gpt-5.4-nano","r":216,"s":79.36,"lo":165,"hi":334,"n":12,"rr":771,"mr":216},{"m":"claude-sonnet-4-thinking","r":217,"s":79.22,"lo":159,"hi":342,"n":9,"rr":593,"mr":232},{"m":"tongyi-deepresearch","r":218,"s":79.15,"lo":162,"hi":302,"n":4,"rr":756,"mr":248},{"m":"k2-horizon-7b","r":219,"s":79.12,"lo":185,"hi":293,"n":7,"rr":924,"mr":215},{"m":"devstral-2","r":220,"s":79.1,"lo":184,"hi":287,"n":3,"rr":1054,"mr":236},{"m":"gpt-5-mini","r":221,"s":79.05,"lo":187,"hi":263,"n":48,"rr":739,"mr":220},{"m":"grok-4-fast","r":222,"s":79,"lo":175,"hi":296,"n":17,"rr":689,"mr":217},{"m":"ornith-1.0-9b","r":223,"s":78.97,"lo":198,"hi":259,"n":6,"rr":991,"mr":226},{"m":"ring-1t-preview","r":224,"s":78.96,"lo":209,"hi":273,"n":5,"rr":511,"mr":231},{"m":"gpt-5.1-medium","r":225,"s":78.95,"lo":187,"hi":278,"n":3,"rr":1389,"mr":239},{"m":"openpangu-2.0-pro","r":226,"s":78.91,"lo":198,"hi":271,"n":11,"rr":568,"mr":214},{"m":"ternary-bonsai-2-27b","r":227,"s":78.87,"lo":140,"hi":376,"n":10,"rr":30,"mr":233},{"m":"longcat-flash-thinking","r":228,"s":78.86,"lo":199,"hi":372,"n":6,"rr":582,"mr":235},{"m":"o3-2025-04-16","r":229,"s":78.82,"lo":117,"hi":813,"n":7,"rr":853,"mr":250},{"m":"gemini-3.7-flash","r":230,"s":78.81,"lo":138,"hi":679,"n":3,"rr":202,"mr":299},{"m":"openai-deepresearch","r":231,"s":78.81,"lo":197,"hi":371,"n":3,"rr":1103,"mr":262},{"m":"o3-high","r":232,"s":78.81,"lo":194,"hi":273,"n":19,"rr":974,"mr":225},{"m":"vibethinker-3b","r":233,"s":78.77,"lo":180,"hi":390,"n":5,"rr":366,"mr":224},{"m":"k2-horizon-32b","r":234,"s":78.75,"lo":199,"hi":397,"n":3,"rr":755,"mr":257},{"m":"gpt-5-low","r":235,"s":78.72,"lo":148,"hi":364,"n":6,"rr":971,"mr":246},{"m":"north-mini-code-1.0","r":236,"s":78.72,"lo":200,"hi":290,"n":6,"rr":1304,"mr":229},{"m":"nova-2-omni","r":237,"s":78.69,"lo":137,"hi":337,"n":4,"rr":177,"mr":241},{"m":"ling-2.5-1t","r":238,"s":78.51,"lo":78,"hi":327,"n":11,"rr":936,"mr":240},{"m":"claude-opus-4-thinking","r":239,"s":78.49,"lo":152,"hi":281,"n":7,"rr":322,"mr":244},{"m":"neohorse-1-9b","r":240,"s":78.49,"lo":162,"hi":381,"n":5,"rr":336,"mr":256},{"m":"k-exaone-2.0","r":241,"s":78.45,"lo":192,"hi":346,"n":12,"rr":478,"mr":211},{"m":"gemini-3.1-flash-lite","r":242,"s":78.45,"lo":190,"hi":314,"n":13,"rr":644,"mr":221},{"m":"claude-4.5-haiku","r":243,"s":78.39,"lo":209,"hi":270,"n":32,"rr":822,"mr":230},{"m":"nemotron-labs-dory1.0-4b-4loop","r":244,"s":78.37,"lo":154,"hi":340,"n":5,"rr":706,"mr":242},{"m":"nemotron-3-super-120b-a12b","r":245,"s":78.37,"lo":200,"hi":273,"n":25,"rr":645,"mr":223},{"m":"qwen3-coder-next","r":246,"s":78.26,"lo":197,"hi":281,"n":4,"rr":911,"mr":251},{"m":"intern-s1-pro","r":247,"s":78.24,"lo":137,"hi":401,"n":6,"rr":665,"mr":227},{"m":"gpt-5.4-none","r":248,"s":78.16,"lo":132,"hi":391,"n":10,"rr":1099,"mr":228},{"m":"nanbeige4.1-3b","r":249,"s":78.15,"lo":213,"hi":373,"n":4,"rr":356,"mr":254},{"m":"deepseek-v3-0528","r":250,"s":78.08,"lo":115,"hi":634,"n":4,"rr":75,"mr":264},{"m":"grok-4-0709","r":251,"s":78.02,"lo":186,"hi":815,"n":4,"rr":630,"mr":283},{"m":"gemini-2.5-pro","r":252,"s":77.93,"lo":219,"hi":276,"n":81,"rr":893,"mr":243},{"m":"minimax-m2","r":253,"s":77.88,"lo":207,"hi":315,"n":25,"rr":802,"mr":234},{"m":"o4-mini","r":254,"s":77.84,"lo":211,"hi":294,"n":16,"rr":1171,"mr":260},{"m":"k2-horizon-mova-36b-a4b","r":255,"s":77.7,"lo":216,"hi":372,"n":3,"rr":789,"mr":276},{"m":"nemotron-labs-dory1.0-4b","r":256,"s":77.64,"lo":177,"hi":339,"n":5,"rr":742,"mr":259},{"m":"gpt-5-2025-08-07","r":257,"s":77.57,"lo":177,"hi":1082,"n":6,"rr":1006,"mr":280},{"m":"keye-vl-2.0-30b-a3b","r":258,"s":77.55,"lo":66,"hi":363,"n":4,"rr":963,"mr":266},{"m":"laguna-xs-2.1","r":259,"s":77.55,"lo":195,"hi":612,"n":7,"rr":1107,"mr":253},{"m":"qwen3-235b-a22b-thinking-2507","r":260,"s":77.53,"lo":213,"hi":306,"n":55,"rr":695,"mr":245},{"m":"qwen3-coder-plus","r":261,"s":77.53,"lo":214,"hi":334,"n":4,"rr":1385,"mr":271},{"m":"ornith-1.5-9b","r":262,"s":77.46,"lo":203,"hi":496,"n":10,"rr":868,"mr":255},{"m":"gemini-2.5-pro-preview-03-25","r":263,"s":77.45,"lo":229,"hi":384,"n":3,"rr":541,"mr":284},{"m":"qwen3.5-omni-plus","r":264,"s":77.38,"lo":204,"hi":310,"n":12,"rr":638,"mr":238},{"m":"o3-medium","r":265,"s":77.37,"lo":188,"hi":376,"n":4,"rr":1135,"mr":295},{"m":"deepseek-v3.1-terminus-thinking","r":266,"s":77.32,"lo":238,"hi":310,"n":7,"rr":1051,"mr":274},{"m":"glm-4.6","r":267,"s":77.29,"lo":226,"hi":316,"n":27,"rr":817,"mr":252},{"m":"exaone-4.5-33b-thinking","r":268,"s":77.25,"lo":215,"hi":317,"n":11,"rr":297,"mr":247},{"m":"telechat3-coder-36b-thinking","r":269,"s":77.19,"lo":235,"hi":334,"n":6,"rr":463,"mr":261},{"m":"grok-3-mini-fast-high-reasoning","r":270,"s":77.18,"lo":221,"hi":526,"n":4,"rr":76,"mr":285},{"m":"gemma-4-31b-it","r":271,"s":77.01,"lo":202,"hi":350,"n":39,"rr":353,"mr":237},{"m":"grok-4-fast-thinking","r":272,"s":76.97,"lo":220,"hi":348,"n":6,"rr":1349,"mr":281},{"m":"qwen3-coder-480b-a35b","r":273,"s":76.96,"lo":223,"hi":323,"n":6,"rr":1472,"mr":279},{"m":"sarvam-105b","r":274,"s":76.94,"lo":224,"hi":342,"n":11,"rr":233,"mr":249},{"m":"deepseek-v3.1-terminus","r":275,"s":76.89,"lo":223,"hi":317,"n":22,"rr":1052,"mr":263},{"m":"agents-a1-4b","r":276,"s":76.88,"lo":149,"hi":474,"n":8,"rr":743,"mr":289},{"m":"o4-mini-high","r":277,"s":76.86,"lo":221,"hi":344,"n":11,"rr":959,"mr":277},{"m":"openpangu-r-72b-2512-slow-thinking","r":278,"s":76.84,"lo":214,"hi":418,"n":16,"rr":294,"mr":265},{"m":"gemma-4-26b-a4b-it","r":279,"s":76.8,"lo":206,"hi":322,"n":31,"rr":795,"mr":258},{"m":"deepseek-v3.1-thinking","r":280,"s":76.68,"lo":241,"hi":302,"n":21,"rr":1067,"mr":270},{"m":"iquest-coder-v1-40b-instruct","r":281,"s":76.63,"lo":171,"hi":380,"n":15,"rr":395,"mr":278},{"m":"gpt-5.3-instant","r":282,"s":76.61,"lo":243,"hi":497,"n":4,"rr":1063,"mr":311},{"m":"ling-1t","r":283,"s":76.57,"lo":156,"hi":416,"n":17,"rr":997,"mr":282},{"m":"qwen3-next-80b-a3b-thinking","r":284,"s":76.49,"lo":251,"hi":308,"n":40,"rr":484,"mr":267},{"m":"command-a-plus-05-2026","r":285,"s":76.38,"lo":201,"hi":490,"n":12,"rr":1011,"mr":275},{"m":"kimi-k2-0905-preview","r":286,"s":76.34,"lo":218,"hi":393,"n":9,"rr":1440,"mr":292},{"m":"longcat-flash-lite-sparse","r":287,"s":76.33,"lo":204,"hi":371,"n":17,"rr":729,"mr":272},{"m":"k-exaone","r":288,"s":76.32,"lo":252,"hi":319,"n":18,"rr":581,"mr":268},{"m":"nemotron-labs-3-puzzle-75b-a9b","r":289,"s":76.3,"lo":219,"hi":332,"n":13,"rr":658,"mr":286},{"m":"gpt-5-mini-medium","r":290,"s":76.2,"lo":244,"hi":322,"n":8,"rr":1214,"mr":287},{"m":"intern-s2-mobius","r":291,"s":76.19,"lo":199,"hi":472,"n":3,"rr":597,"mr":322},{"m":"gpt-oss-120b-high","r":292,"s":76.07,"lo":235,"hi":352,"n":19,"rr":591,"mr":269},{"m":"claude-opus-4.1-20250805","r":293,"s":75.98,"lo":151,"hi":366,"n":7,"rr":544,"mr":297},{"m":"claude-haiku-5.5","r":294,"s":75.94,"lo":60,"hi":522,"n":5,"rr":287,"mr":351},{"m":"claude-3.7-sonnet-20250219","r":295,"s":75.92,"lo":268,"hi":352,"n":5,"rr":392,"mr":312},{"m":"iquest-coder-v1-40b-loop-instruct","r":296,"s":75.78,"lo":211,"hi":358,"n":13,"rr":327,"mr":290},{"m":"openpangu-2.0-flash","r":297,"s":75.76,"lo":235,"hi":407,"n":10,"rr":717,"mr":273},{"m":"grok-code-fast-1","r":298,"s":75.75,"lo":246,"hi":347,"n":5,"rr":1002,"mr":306},{"m":"claude-opus-4-1-20250805-thinking","r":299,"s":75.74,"lo":14,"hi":396,"n":3,"rr":39,"mr":320},{"m":"qwen3-max","r":300,"s":75.72,"lo":224,"hi":371,"n":7,"rr":1247,"mr":305},{"m":"deepseek-tng-r1t2-chimera","r":301,"s":75.72,"lo":167,"hi":502,"n":4,"rr":117,"mr":314},{"m":"g9v3-39a5b","r":302,"s":75.66,"lo":253,"hi":471,"n":3,"rr":918,"mr":315},{"m":"qwen3-vl-32b-thinking","r":303,"s":75.55,"lo":203,"hi":414,"n":15,"rr":157,"mr":288},{"m":"underdog-saluki-27b-1.0","r":304,"s":75.48,"lo":158,"hi":574,"n":4,"rr":132,"mr":374},{"m":"zdtaichu5.0-9b","r":305,"s":75.45,"lo":217,"hi":413,"n":6,"rr":99,"mr":310},{"m":"claude-sonnet-4","r":306,"s":75.43,"lo":237,"hi":351,"n":60,"rr":908,"mr":291},{"m":"o3-mini-2025-01-31-high","r":307,"s":75.39,"lo":253,"hi":485,"n":5,"rr":482,"mr":329},{"m":"glm-4.5v","r":308,"s":75.25,"lo":8,"hi":508,"n":4,"rr":1026,"mr":364},{"m":"claude-3.7-sonnet-thinking","r":309,"s":75.21,"lo":219,"hi":382,"n":8,"rr":168,"mr":326},{"m":"grok-4.1-fast","r":310,"s":75.21,"lo":258,"hi":414,"n":13,"rr":1139,"mr":294},{"m":"qwen3-max-instruct-preview","r":311,"s":75.14,"lo":232,"hi":390,"n":10,"rr":691,"mr":316},{"m":"qwen3-coder-480b-a35b-instruct","r":312,"s":75.12,"lo":227,"hi":365,"n":21,"rr":543,"mr":301},{"m":"ring-flash-2.0","r":313,"s":75.1,"lo":285,"hi":369,"n":5,"rr":948,"mr":321},{"m":"kimi-k2-instruct-0711","r":314,"s":75.1,"lo":241,"hi":480,"n":6,"rr":1154,"mr":327},{"m":"gemini-2.5-pro-preview-06-05","r":315,"s":75.07,"lo":208,"hi":463,"n":10,"rr":1285,"mr":319},{"m":"kimi-k2-instruct-0905","r":316,"s":75.02,"lo":223,"hi":390,"n":18,"rr":465,"mr":307},{"m":"claude-opus-4","r":317,"s":75.01,"lo":237,"hi":376,"n":38,"rr":764,"mr":298},{"m":"kimi-k2-0711-preview","r":318,"s":74.92,"lo":282,"hi":492,"n":3,"rr":1425,"mr":346},{"m":"cogito-671b-v2.1","r":319,"s":74.85,"lo":220,"hi":419,"n":6,"rr":425,"mr":313},{"m":"nova-2-lite","r":320,"s":74.79,"lo":257,"hi":391,"n":10,"rr":857,"mr":304},{"m":"seed-oss-36b-instruct","r":321,"s":74.78,"lo":294,"hi":361,"n":6,"rr":794,"mr":324},{"m":"gpt-5.4-nano-high","r":322,"s":74.77,"lo":266,"hi":868,"n":3,"rr":1539,"mr":340},{"m":"iterresearch-30b-a3b","r":323,"s":74.71,"lo":277,"hi":715,"n":3,"rr":1183,"mr":343},{"m":"spark-x2.5-4b","r":324,"s":74.68,"lo":246,"hi":443,"n":15,"rr":1013,"mr":300},{"m":"intellect-3","r":325,"s":74.68,"lo":267,"hi":457,"n":6,"rr":92,"mr":293},{"m":"kimi-k2-instruct","r":326,"s":74.66,"lo":281,"hi":346,"n":40,"rr":772,"mr":302},{"m":"qwen3-vl-235b-a22b-thinking","r":327,"s":74.65,"lo":243,"hi":400,"n":15,"rr":783,"mr":296},{"m":"qwen-3-235b-a22b-thinking","r":328,"s":74.57,"lo":264,"hi":421,"n":19,"rr":215,"mr":303},{"m":"o4-mini-medium","r":329,"s":74.4,"lo":253,"hi":407,"n":5,"rr":1167,"mr":337},{"m":"neohorse-1-4b","r":330,"s":74.31,"lo":258,"hi":450,"n":5,"rr":506,"mr":335},{"m":"deepseek-r1-0528","r":331,"s":74.19,"lo":275,"hi":389,"n":37,"rr":972,"mr":309},{"m":"nemotron-cascade-2-30b-a3b","r":332,"s":74.12,"lo":177,"hi":442,"n":12,"rr":621,"mr":330},{"m":"glm-4.5","r":333,"s":74.11,"lo":282,"hi":364,"n":32,"rr":1073,"mr":317},{"m":"devstral-small-2","r":334,"s":74.08,"lo":258,"hi":555,"n":7,"rr":1462,"mr":341},{"m":"jev-1.13","r":335,"s":74.02,"lo":252,"hi":437,"n":8,"rr":22,"mr":331},{"m":"lfm2.5-24b-a2b","r":336,"s":73.97,"lo":208,"hi":390,"n":7,"rr":299,"mr":336},{"m":"openreasoning-nemotron-32b","r":337,"s":73.91,"lo":303,"hi":366,"n":6,"rr":580,"mr":333},{"m":"deepseek-v3.2-exp","r":338,"s":73.88,"lo":269,"hi":457,"n":41,"rr":627,"mr":308},{"m":"o1","r":339,"s":73.81,"lo":273,"hi":398,"n":15,"rr":310,"mr":348},{"m":"qwen3-235b-2507","r":340,"s":73.78,"lo":249,"hi":427,"n":8,"rr":928,"mr":318},{"m":"iquest-coder-v1-14b-thinking","r":341,"s":73.71,"lo":276,"hi":446,"n":4,"rr":876,"mr":349},{"m":"gpt-oss-120b","r":342,"s":73.69,"lo":291,"hi":386,"n":59,"rr":897,"mr":323},{"m":"ring-flash-linear-2.0","r":343,"s":73.68,"lo":312,"hi":412,"n":5,"rr":1058,"mr":359},{"m":"dots-vlm1","r":344,"s":73.68,"lo":286,"hi":439,"n":4,"rr":1377,"mr":363},{"m":"o1-2024-12-17-high","r":345,"s":73.67,"lo":298,"hi":493,"n":3,"rr":699,"mr":389},{"m":"jev-1.14","r":346,"s":73.55,"lo":268,"hi":444,"n":8,"rr":20,"mr":342},{"m":"longcat-flash-lite","r":347,"s":73.52,"lo":298,"hi":422,"n":12,"rr":483,"mr":338},{"m":"seed2.0-mini","r":348,"s":73.48,"lo":264,"hi":438,"n":18,"rr":809,"mr":350},{"m":"kimi-k2","r":349,"s":73.4,"lo":281,"hi":425,"n":17,"rr":1245,"mr":358},{"m":"minimax-m1-80k","r":350,"s":73.36,"lo":312,"hi":382,"n":12,"rr":694,"mr":334},{"m":"hy-2.0-thinking","r":351,"s":73.32,"lo":306,"hi":387,"n":6,"rr":1225,"mr":347},{"m":"mirothinker-v1.0-8b","r":352,"s":73.31,"lo":311,"hi":505,"n":3,"rr":1196,"mr":378},{"m":"gemma-4-12b-it","r":353,"s":73.31,"lo":267,"hi":407,"n":25,"rr":1014,"mr":332},{"m":"seed1.6-thinking","r":354,"s":73.3,"lo":256,"hi":535,"n":3,"rr":842,"mr":410},{"m":"granite-4.2-30b","r":355,"s":73.27,"lo":293,"hi":436,"n":14,"rr":814,"mr":328},{"m":"claude-3.7-sonnet","r":356,"s":73.13,"lo":280,"hi":419,"n":27,"rr":844,"mr":352},{"m":"nemotron-labs-dory1.0-4b-1loop","r":357,"s":73.1,"lo":258,"hi":470,"n":5,"rr":993,"mr":344},{"m":"gemini-2.5-flash-thinking","r":358,"s":73.04,"lo":304,"hi":407,"n":32,"rr":651,"mr":339},{"m":"joyai-llm-flash","r":359,"s":72.93,"lo":299,"hi":452,"n":19,"rr":321,"mr":325},{"m":"o3-mini-2025-01-31-med","r":360,"s":72.92,"lo":298,"hi":575,"n":4,"rr":578,"mr":403},{"m":"gpt-oss-swallow-120b-rl-v0.1","r":361,"s":72.89,"lo":196,"hi":615,"n":5,"rr":109,"mr":360},{"m":"clef-flash","r":362,"s":72.88,"lo":150,"hi":643,"n":8,"rr":33,"mr":405},{"m":"gpt-oss-120b-medium","r":363,"s":72.88,"lo":292,"hi":434,"n":17,"rr":562,"mr":356},{"m":"ling-3.0-tiny","r":364,"s":72.87,"lo":289,"hi":559,"n":5,"rr":854,"mr":365},{"m":"o3-mini","r":365,"s":72.87,"lo":301,"hi":413,"n":14,"rr":806,"mr":371},{"m":"diffusiongemma-26b-a4b","r":366,"s":72.84,"lo":314,"hi":436,"n":5,"rr":444,"mr":357},{"m":"grok-3-beta-think","r":367,"s":72.79,"lo":326,"hi":381,"n":3,"rr":682,"mr":391},{"m":"rlvr-8b-0926","r":368,"s":72.55,"lo":324,"hi":769,"n":3,"rr":880,"mr":386},{"m":"gpt-4.1-2025-04-14","r":369,"s":72.53,"lo":288,"hi":852,"n":8,"rr":1098,"mr":395},{"m":"clef-omni","r":370,"s":72.41,"lo":179,"hi":628,"n":8,"rr":34,"mr":399},{"m":"qwen3.5-9b","r":371,"s":72.22,"lo":315,"hi":455,"n":55,"rr":724,"mr":345},{"m":"openreasoning-nemotron-14b","r":372,"s":72.21,"lo":351,"hi":418,"n":6,"rr":723,"mr":375},{"m":"deepseek-v3.1","r":373,"s":72.08,"lo":307,"hi":448,"n":45,"rr":560,"mr":353},{"m":"minicpm5-2b","r":374,"s":72,"lo":277,"hi":460,"n":15,"rr":662,"mr":355},{"m":"qwen3.5-4b","r":375,"s":71.99,"lo":307,"hi":459,"n":50,"rr":765,"mr":354},{"m":"golongrl-30b-a3b","r":376,"s":71.98,"lo":327,"hi":457,"n":5,"rr":355,"mr":409},{"m":"qwen3-vl-235b-a22b","r":377,"s":71.98,"lo":304,"hi":427,"n":6,"rr":1251,"mr":401},{"m":"seed-thinking-v1.5","r":378,"s":71.92,"lo":332,"hi":432,"n":13,"rr":801,"mr":376},{"m":"qwen3-30b-a3b-2507","r":379,"s":71.91,"lo":331,"hi":461,"n":9,"rr":820,"mr":370},{"m":"o1-2024-12-17","r":380,"s":71.88,"lo":322,"hi":435,"n":12,"rr":450,"mr":404},{"m":"k2-think","r":381,"s":71.88,"lo":340,"hi":429,"n":7,"rr":975,"mr":382},{"m":"ax-k1","r":382,"s":71.87,"lo":235,"hi":644,"n":11,"rr":586,"mr":368},{"m":"claude-opus-4-20250514","r":383,"s":71.84,"lo":242,"hi":496,"n":5,"rr":1373,"mr":420},{"m":"ling-2.6-flash","r":384,"s":71.83,"lo":297,"hi":488,"n":7,"rr":1133,"mr":380},{"m":"qwen3-235b-a22b","r":385,"s":71.83,"lo":332,"hi":442,"n":70,"rr":683,"mr":362},{"m":"qwen3-swallow-32b-rl-v0.2","r":386,"s":71.68,"lo":308,"hi":530,"n":5,"rr":104,"mr":379},{"m":"gemini-2.5-pro-exp-03.25","r":387,"s":71.68,"lo":311,"hi":515,"n":4,"rr":197,"mr":419},{"m":"minimax-m1-40k","r":388,"s":71.67,"lo":343,"hi":419,"n":12,"rr":722,"mr":372},{"m":"glm-4.5-air","r":389,"s":71.65,"lo":337,"hi":442,"n":32,"rr":790,"mr":366},{"m":"qwen3-30b-a3b-thinking-2507","r":390,"s":71.63,"lo":337,"hi":477,"n":49,"rr":726,"mr":367},{"m":"nemotron-3-nano-30b-a3b","r":391,"s":71.62,"lo":317,"hi":474,"n":23,"rr":688,"mr":361},{"m":"qwen3-14b-thinking","r":392,"s":71.61,"lo":323,"hi":495,"n":15,"rr":419,"mr":377},{"m":"qwenlong-l1.5-30b-a3b","r":393,"s":71.57,"lo":347,"hi":463,"n":5,"rr":377,"mr":418},{"m":"nemotron-32b","r":394,"s":71.55,"lo":349,"hi":441,"n":6,"rr":1180,"mr":388},{"m":"qwen3-next-80b-a3b","r":395,"s":71.33,"lo":280,"hi":528,"n":8,"rr":1036,"mr":369},{"m":"qwen3-vl-32b-instruct","r":396,"s":71.29,"lo":309,"hi":547,"n":15,"rr":462,"mr":394},{"m":"k2-horizon-3.7b","r":397,"s":71.28,"lo":272,"hi":525,"n":5,"rr":1241,"mr":407},{"m":"o3-mini-high","r":398,"s":71.26,"lo":331,"hi":584,"n":21,"rr":1147,"mr":413},{"m":"kimi-k2-0905","r":399,"s":71.22,"lo":290,"hi":498,"n":27,"rr":1250,"mr":387},{"m":"gemini-2.5-flash","r":400,"s":71.17,"lo":344,"hi":436,"n":58,"rr":1087,"mr":396},{"m":"apriel-1.6-15b-thinker","r":401,"s":71.15,"lo":327,"hi":472,"n":15,"rr":1032,"mr":414},{"m":"grok-3-mini-fast-low-reasoning","r":402,"s":70.98,"lo":375,"hi":520,"n":4,"rr":194,"mr":428},{"m":"mercury-2","r":403,"s":70.96,"lo":277,"hi":523,"n":8,"rr":1100,"mr":400},{"m":"deepseek-r1","r":404,"s":70.86,"lo":354,"hi":443,"n":41,"rr":869,"mr":412},{"m":"openpangu-r-72b-2512-fast-thinking","r":405,"s":70.83,"lo":314,"hi":515,"n":16,"rr":557,"mr":397},{"m":"qwen3-vl-30b-a3b-thinking","r":406,"s":70.81,"lo":360,"hi":451,"n":17,"rr":452,"mr":402},{"m":"granite-4.2-8b","r":407,"s":70.7,"lo":331,"hi":513,"n":16,"rr":925,"mr":390},{"m":"mellum2.1-12b-a2.5b-thinking","r":408,"s":70.67,"lo":283,"hi":490,"n":8,"rr":106,"mr":408},{"m":"pulsar-16b","r":409,"s":70.67,"lo":276,"hi":559,"n":3,"rr":328,"mr":435},{"m":"gpt-oss-swallow-120b-sft-v0.1","r":410,"s":70.63,"lo":373,"hi":502,"n":5,"rr":95,"mr":406},{"m":"clef","r":411,"s":70.6,"lo":221,"hi":660,"n":8,"rr":44,"mr":427},{"m":"mistral-small-4-thinking","r":412,"s":70.52,"lo":314,"hi":514,"n":13,"rr":633,"mr":381},{"m":"qwen3-vl-8b-thinking","r":413,"s":70.5,"lo":306,"hi":522,"n":16,"rr":384,"mr":393},{"m":"o3-mini-medium","r":414,"s":70.49,"lo":357,"hi":487,"n":6,"rr":1346,"mr":434},{"m":"sarvam-30b","r":415,"s":70.45,"lo":348,"hi":486,"n":12,"rr":435,"mr":392},{"m":"o1-preview-2024-09-12","r":416,"s":70.42,"lo":317,"hi":526,"n":10,"rr":56,"mr":438},{"m":"llada2.2-flash","r":417,"s":70.41,"lo":271,"hi":715,"n":3,"rr":1434,"mr":447},{"m":"olmo-3.1-think-32b","r":418,"s":70.41,"lo":356,"hi":478,"n":25,"rr":291,"mr":398},{"m":"nemotron-cascade-14b-thinking","r":419,"s":70.36,"lo":334,"hi":503,"n":10,"rr":390,"mr":373},{"m":"telechat3-36b-thinking","r":420,"s":70.32,"lo":367,"hi":466,"n":7,"rr":255,"mr":385},{"m":"glm-4.7-flash","r":421,"s":70.29,"lo":320,"hi":512,"n":28,"rr":677,"mr":384},{"m":"claude-sonnet-4-20250514","r":422,"s":70.17,"lo":332,"hi":527,"n":8,"rr":1479,"mr":439},{"m":"ring-mini-2.0","r":423,"s":70.17,"lo":384,"hi":548,"n":3,"rr":1208,"mr":432},{"m":"minicpm-v-4.7-35b-a3b","r":424,"s":70.15,"lo":298,"hi":517,"n":5,"rr":535,"mr":425},{"m":"qwen3-next-80b-a3b-instruct","r":425,"s":70.14,"lo":343,"hi":477,"n":35,"rr":748,"mr":417},{"m":"o4-mini-low","r":426,"s":70.08,"lo":371,"hi":482,"n":3,"rr":1553,"mr":440},{"m":"gemini-2.5-flash-preview-09-2025","r":427,"s":69.99,"lo":365,"hi":516,"n":16,"rr":1143,"mr":415},{"m":"qwen3-omni-flash-thinking","r":428,"s":69.88,"lo":379,"hi":497,"n":10,"rr":296,"mr":446},{"m":"llada2.1-flash-q","r":429,"s":69.85,"lo":346,"hi":516,"n":26,"rr":206,"mr":421},{"m":"agentcpm-explore","r":430,"s":69.83,"lo":382,"hi":509,"n":3,"rr":1350,"mr":468},{"m":"longcat-next","r":431,"s":69.74,"lo":362,"hi":528,"n":10,"rr":910,"mr":433},{"m":"ernie-4.5","r":432,"s":69.73,"lo":341,"hi":514,"n":21,"rr":112,"mr":411},{"m":"grok-3-mini-beta","r":433,"s":69.66,"lo":399,"hi":509,"n":3,"rr":342,"mr":491},{"m":"o4-mini-2025-04-16","r":434,"s":69.6,"lo":249,"hi":526,"n":7,"rr":891,"mr":466},{"m":"gemini-2.5-flash-preview-05-20","r":435,"s":69.6,"lo":342,"hi":613,"n":9,"rr":1428,"mr":449},{"m":"minimax-m1","r":436,"s":69.53,"lo":399,"hi":494,"n":3,"rr":386,"mr":452},{"m":"qwen3-235b-a22b-instruct-2507","r":437,"s":69.5,"lo":342,"hi":473,"n":26,"rr":964,"mr":436},{"m":"qwen3-235b-a22b-2507","r":438,"s":69.46,"lo":283,"hi":497,"n":3,"rr":1369,"mr":481},{"m":"qwen3-32b-thinking","r":439,"s":69.35,"lo":377,"hi":506,"n":46,"rr":796,"mr":424},{"m":"nemotron-labs-3-elastic-30b-a3b","r":440,"s":69.31,"lo":311,"hi":602,"n":7,"rr":815,"mr":464},{"m":"gpt-oss-swallow-20b-rl-v0.1","r":441,"s":69.24,"lo":384,"hi":628,"n":5,"rr":141,"mr":430},{"m":"gpt-5-chat","r":442,"s":69.19,"lo":273,"hi":615,"n":3,"rr":1078,"mr":517},{"m":"deepseek-v3-0324","r":443,"s":69.15,"lo":377,"hi":546,"n":35,"rr":849,"mr":426},{"m":"qwen3-omni-30b-a3b-thinking","r":444,"s":69.13,"lo":391,"hi":521,"n":10,"rr":331,"mr":470},{"m":"st-moe-32b","r":445,"s":69.09,"lo":399,"hi":668,"n":3,"rr":1,"mr":543},{"m":"yuan3.0-ultra","r":446,"s":69.08,"lo":319,"hi":838,"n":3,"rr":904,"mr":528},{"m":"olmo-3-think-32b-dpo","r":447,"s":69.02,"lo":365,"hi":506,"n":21,"rr":338,"mr":423},{"m":"nemotron-cascade-8b","r":448,"s":68.99,"lo":355,"hi":536,"n":10,"rr":476,"mr":416},{"m":"vllm-sr-d3","r":449,"s":68.99,"lo":271,"hi":576,"n":8,"rr":42,"mr":460},{"m":"openthinkeragent-32b","r":450,"s":68.9,"lo":321,"hi":553,"n":3,"rr":1471,"mr":474},{"m":"gpt-4.1","r":451,"s":68.88,"lo":348,"hi":497,"n":60,"rr":767,"mr":431},{"m":"llada2.1-flash-s","r":452,"s":68.86,"lo":382,"hi":541,"n":26,"rr":246,"mr":442},{"m":"gpt-5-nano-high","r":453,"s":68.8,"lo":373,"hi":582,"n":6,"rr":1505,"mr":476},{"m":"mirothinker-v0.2-32b","r":454,"s":68.77,"lo":254,"hi":566,"n":3,"rr":1477,"mr":493},{"m":"gemini-2.5-flash-preview-05-20-thinking","r":455,"s":68.76,"lo":364,"hi":625,"n":3,"rr":712,"mr":477},{"m":"mistral-large-3","r":456,"s":68.73,"lo":358,"hi":564,"n":7,"rr":832,"mr":450},{"m":"hypernova-60b-2605","r":457,"s":68.58,"lo":376,"hi":498,"n":9,"rr":1149,"mr":462},{"m":"llada2.0-flash","r":458,"s":68.58,"lo":394,"hi":532,"n":34,"rr":127,"mr":437},{"m":"gka-primed-hqwen3-32b-reasoner","r":459,"s":68.55,"lo":367,"hi":944,"n":5,"rr":1134,"mr":501},{"m":"motif-2-12.7b-reasoning","r":460,"s":68.54,"lo":378,"hi":531,"n":14,"rr":80,"mr":445},{"m":"gpt-oss-20b-medium","r":461,"s":68.5,"lo":413,"hi":565,"n":6,"rr":573,"mr":461},{"m":"exaone-4.0-32b-thinking","r":462,"s":68.41,"lo":367,"hi":715,"n":13,"rr":786,"mr":463},{"m":"claude-4.5-haiku-thinking","r":463,"s":68.4,"lo":390,"hi":532,"n":6,"rr":1021,"mr":456},{"m":"magistral-medium-1.2","r":464,"s":68.35,"lo":346,"hi":557,"n":11,"rr":1137,"mr":453},{"m":"solar-open-100b","r":465,"s":68.35,"lo":366,"hi":615,"n":16,"rr":1043,"mr":429},{"m":"o1-preview","r":466,"s":68.34,"lo":395,"hi":538,"n":13,"rr":55,"mr":472},{"m":"vega-v2","r":467,"s":68.29,"lo":424,"hi":705,"n":3,"rr":3,"mr":572},{"m":"gpt-5-mini-low","r":468,"s":68.28,"lo":339,"hi":537,"n":4,"rr":1585,"mr":503},{"m":"pplx-decider-v1.2","r":469,"s":68.25,"lo":285,"hi":594,"n":8,"rr":47,"mr":479},{"m":"gpt-oss-20b","r":470,"s":68.2,"lo":421,"hi":514,"n":50,"rr":932,"mr":444},{"m":"o1-mini","r":471,"s":68.19,"lo":323,"hi":517,"n":19,"rr":351,"mr":486},{"m":"hunyuan-7b-instruct","r":472,"s":68.18,"lo":420,"hi":676,"n":3,"rr":501,"mr":515},{"m":"gpt-oss-20b-a4b","r":473,"s":68.16,"lo":398,"hi":547,"n":4,"rr":1153,"mr":489},{"m":"abeja-qwq32b-reasoning-japanese-v1.0","r":474,"s":68.13,"lo":396,"hi":562,"n":5,"rr":171,"mr":454},{"m":"codex-mini-latest","r":475,"s":68.11,"lo":334,"hi":590,"n":3,"rr":1612,"mr":508},{"m":"nemotron-cascade-8b-thinking","r":476,"s":68.09,"lo":380,"hi":554,"n":10,"rr":485,"mr":422},{"m":"grok-code-fast","r":477,"s":68.07,"lo":422,"hi":554,"n":3,"rr":1319,"mr":509},{"m":"magistral-medium","r":478,"s":68.05,"lo":411,"hi":515,"n":4,"rr":1317,"mr":492},{"m":"openpangu-r-7b-2512-slow-thinking","r":479,"s":68.05,"lo":392,"hi":561,"n":16,"rr":716,"mr":465},{"m":"gemma-4-26b-a4b","r":480,"s":68.02,"lo":279,"hi":956,"n":21,"rr":406,"mr":383},{"m":"hyperclovax-seed-think","r":481,"s":67.99,"lo":253,"hi":666,"n":8,"rr":1297,"mr":459},{"m":"llama-4-behemoth","r":482,"s":67.95,"lo":377,"hi":531,"n":5,"rr":146,"mr":487},{"m":"mimo-v2.5-pro-base","r":483,"s":67.86,"lo":371,"hi":574,"n":19,"rr":89,"mr":443},{"m":"gpt-4.5","r":484,"s":67.84,"lo":320,"hi":518,"n":12,"rr":679,"mr":488},{"m":"olmo-3-think-32b","r":485,"s":67.78,"lo":399,"hi":540,"n":26,"rr":332,"mr":441},{"m":"nvidia-nemotron-nano-9b-v2","r":486,"s":67.68,"lo":395,"hi":565,"n":22,"rr":399,"mr":455},{"m":"motif-2-12.7b-instruct","r":487,"s":67.64,"lo":402,"hi":537,"n":14,"rr":116,"mr":457},{"m":"qwen3-30b-a3b-instruct-2507","r":488,"s":67.61,"lo":418,"hi":551,"n":56,"rr":496,"mr":448},{"m":"apriel-1.5-15b-thinker","r":489,"s":67.58,"lo":411,"hi":558,"n":19,"rr":1260,"mr":475},{"m":"o3-mini-2025-01-31-low","r":490,"s":67.57,"lo":440,"hi":603,"n":4,"rr":846,"mr":514},{"m":"gpt-5-minimal","r":491,"s":67.49,"lo":355,"hi":543,"n":13,"rr":1266,"mr":485},{"m":"k2-high-70b","r":492,"s":67.34,"lo":410,"hi":599,"n":7,"rr":235,"mr":469},{"m":"apriel-1.5-15b-thinker-self-reported","r":493,"s":67.29,"lo":388,"hi":667,"n":8,"rr":1195,"mr":500},{"m":"qwen3-omni-flash-instruct","r":494,"s":67.28,"lo":434,"hi":609,"n":9,"rr":345,"mr":507},{"m":"qwen3-swallow-32b-sft-v0.2","r":495,"s":67.25,"lo":423,"hi":580,"n":5,"rr":190,"mr":484},{"m":"gpt-5-nano-medium","r":496,"s":67.19,"lo":387,"hi":571,"n":3,"rr":1619,"mr":523},{"m":"qwen3-32b","r":497,"s":67.18,"lo":434,"hi":585,"n":59,"rr":800,"mr":471},{"m":"hairuo","r":498,"s":67.16,"lo":455,"hi":672,"n":3,"rr":2,"mr":575},{"m":"grok-3-mini","r":499,"s":67.13,"lo":403,"hi":567,"n":6,"rr":1406,"mr":521},{"m":"zaya1-8b","r":500,"s":67.1,"lo":436,"hi":726,"n":6,"rr":411,"mr":451},{"m":"autotrust-jev-35b","r":501,"s":67.1,"lo":293,"hi":664,"n":8,"rr":68,"mr":516},{"m":"ling-flash-2.0","r":502,"s":67.05,"lo":395,"hi":565,"n":34,"rr":144,"mr":467},{"m":"qwen3.5-omni-flash","r":503,"s":67,"lo":420,"hi":619,"n":12,"rr":978,"mr":458},{"m":"deepseek-v3","r":504,"s":66.93,"lo":444,"hi":547,"n":48,"rr":459,"mr":478},{"m":"nemotron-nano-v2-9b","r":505,"s":66.9,"lo":402,"hi":734,"n":10,"rr":162,"mr":495},{"m":"olmo-3-think-32b-sft","r":506,"s":66.85,"lo":406,"hi":564,"n":21,"rr":420,"mr":473},{"m":"falcon-h1r-7b","r":507,"s":66.8,"lo":403,"hi":716,"n":17,"rr":841,"mr":482},{"m":"gpt-oss-120b-low","r":508,"s":66.76,"lo":431,"hi":704,"n":4,"rr":1007,"mr":513},{"m":"gpt-5-nano","r":509,"s":66.7,"lo":395,"hi":587,"n":16,"rr":1347,"mr":524},{"m":"nemotron-research-goosereason-4b-instruct","r":510,"s":66.61,"lo":413,"hi":629,"n":7,"rr":211,"mr":496},{"m":"deepseek-r1-distill-qwen-32b","r":511,"s":66.6,"lo":427,"hi":645,"n":15,"rr":698,"mr":497},{"m":"grok-3-mini-beta-low","r":512,"s":66.56,"lo":445,"hi":566,"n":3,"rr":1603,"mr":531},{"m":"qwen3-swallow-32b-cpt-v0.2","r":513,"s":66.39,"lo":471,"hi":556,"n":5,"rr":184,"mr":499},{"m":"qwen3-32b-thinking-2504","r":514,"s":66.27,"lo":415,"hi":569,"n":5,"rr":1262,"mr":534},{"m":"phi-4-reasoning-plus","r":515,"s":66.27,"lo":425,"hi":559,"n":11,"rr":1086,"mr":502},{"m":"gpt-4.5-preview","r":516,"s":66.23,"lo":439,"hi":663,"n":5,"rr":980,"mr":549},{"m":"nvidia-nemotron-3-nano-30b-a3b-bf16","r":517,"s":66.18,"lo":418,"hi":593,"n":20,"rr":1235,"mr":494},{"m":"claude-3.5-sonnet-20241022","r":518,"s":66.16,"lo":416,"hi":594,"n":33,"rr":438,"mr":490},{"m":"gpt-5.2-none","r":519,"s":66.11,"lo":456,"hi":566,"n":3,"rr":1591,"mr":535},{"m":"telechat3-105b-a4.7b-thinking","r":520,"s":66.09,"lo":429,"hi":586,"n":7,"rr":403,"mr":480},{"m":"ministral-3-r-8b","r":521,"s":66.03,"lo":386,"hi":961,"n":11,"rr":400,"mr":511},{"m":"step3-vl-10b","r":522,"s":65.94,"lo":463,"hi":651,"n":6,"rr":453,"mr":506},{"m":"gpt-oss-20b-high","r":523,"s":65.94,"lo":436,"hi":587,"n":13,"rr":907,"mr":498},{"m":"minicpm-sala","r":524,"s":65.91,"lo":454,"hi":625,"n":10,"rr":114,"mr":505},{"m":"superapriel-15b-instruct","r":525,"s":65.88,"lo":371,"hi":662,"n":6,"rr":142,"mr":522},{"m":"grok-3","r":526,"s":65.86,"lo":355,"hi":571,"n":8,"rr":1046,"mr":539},{"m":"plamo-3.0-prime-thinking","r":527,"s":65.79,"lo":339,"hi":707,"n":5,"rr":1031,"mr":525},{"m":"qwen3-swallow-30b-a3b-rl-v0.2","r":528,"s":65.72,"lo":447,"hi":754,"n":5,"rr":284,"mr":512},{"m":"gpt-oss-swallow-20b-sft-v0.1","r":529,"s":65.71,"lo":482,"hi":645,"n":5,"rr":223,"mr":510},{"m":"nemotron-3.5-lightning-30b-a3b","r":530,"s":65.7,"lo":390,"hi":777,"n":25,"rr":619,"mr":483},{"m":"glm-4.6v","r":531,"s":65.45,"lo":343,"hi":683,"n":7,"rr":1220,"mr":546},{"m":"qwen3-vl-30b-a3b-instruct","r":532,"s":65.45,"lo":467,"hi":579,"n":21,"rr":905,"mr":519},{"m":"qwen3-coder-30b-a3b-instruct","r":533,"s":65.44,"lo":390,"hi":588,"n":15,"rr":1045,"mr":527},{"m":"gpt-5-mini-minimal","r":534,"s":65.38,"lo":393,"hi":636,"n":5,"rr":1534,"mr":566},{"m":"openreasoning-nemotron-7b","r":535,"s":65.33,"lo":448,"hi":754,"n":21,"rr":1066,"mr":504},{"m":"kolibri-origin","r":536,"s":65.31,"lo":397,"hi":779,"n":8,"rr":955,"mr":526},{"m":"o1-mini-2024-09-12","r":537,"s":65.31,"lo":470,"hi":588,"n":14,"rr":305,"mr":538},{"m":"grok-3-beta","r":538,"s":65.3,"lo":426,"hi":609,"n":11,"rr":609,"mr":542},{"m":"minicpm4.1-8b","r":539,"s":65.24,"lo":473,"hi":610,"n":9,"rr":120,"mr":518},{"m":"gemini-2.0-pro","r":540,"s":65.19,"lo":395,"hi":636,"n":11,"rr":570,"mr":540},{"m":"glm-4.1v","r":541,"s":65.16,"lo":19,"hi":820,"n":4,"rr":1331,"mr":608},{"m":"glide-no-thinking","r":542,"s":65.16,"lo":345,"hi":665,"n":8,"rr":70,"mr":547},{"m":"gemini-2.0-flash","r":543,"s":65.05,"lo":479,"hi":651,"n":13,"rr":1118,"mr":548},{"m":"deepseek-r1-0120","r":544,"s":65,"lo":404,"hi":650,"n":3,"rr":884,"mr":576},{"m":"llama-3.1-405b","r":545,"s":64.98,"lo":427,"hi":653,"n":18,"rr":288,"mr":541},{"m":"qwq-bakeneko-32b","r":546,"s":64.92,"lo":500,"hi":585,"n":5,"rr":228,"mr":537},{"m":"llama-3.1-tulu-3-405b","r":547,"s":64.82,"lo":401,"hi":709,"n":9,"rr":90,"mr":567},{"m":"qwq-32b","r":548,"s":64.77,"lo":462,"hi":607,"n":19,"rr":989,"mr":536},{"m":"nanbeige4-3b-thinking-2511","r":549,"s":64.66,"lo":380,"hi":699,"n":7,"rr":1164,"mr":551},{"m":"hypernova-60b-2602","r":550,"s":64.52,"lo":467,"hi":587,"n":9,"rr":1322,"mr":553},{"m":"gpt-5.4-mini-none","r":551,"s":64.24,"lo":460,"hi":710,"n":5,"rr":1263,"mr":532},{"m":"kanana-2-30b-a3b-thinking","r":552,"s":64.23,"lo":504,"hi":729,"n":5,"rr":702,"mr":520},{"m":"iquest-coder-v1-14b-instruct","r":553,"s":64.11,"lo":257,"hi":722,"n":4,"rr":1280,"mr":583},{"m":"qwen3-omni-30b-a3b-instruct","r":554,"s":64.02,"lo":457,"hi":789,"n":16,"rr":606,"mr":552},{"m":"llama-4-maverick-17b-128e-instruct","r":555,"s":63.91,"lo":369,"hi":669,"n":8,"rr":779,"mr":550},{"m":"claude-3.5-sonnet","r":556,"s":63.88,"lo":425,"hi":669,"n":19,"rr":196,"mr":565},{"m":"magistral-medium-2506","r":557,"s":63.87,"lo":505,"hi":595,"n":6,"rr":1431,"mr":564},{"m":"apriel-nemotron-15b-thinker","r":558,"s":63.78,"lo":368,"hi":633,"n":8,"rr":189,"mr":557},{"m":"qwen3-30b-a3b","r":559,"s":63.77,"lo":502,"hi":653,"n":58,"rr":649,"mr":529},{"m":"deepseek-r1-lite-preview","r":560,"s":63.77,"lo":471,"hi":636,"n":5,"rr":828,"mr":597},{"m":"golongrl-4b","r":561,"s":63.6,"lo":517,"hi":676,"n":5,"rr":725,"mr":582},{"m":"kanana-2-30b-a3b-thinking-2601","r":562,"s":63.59,"lo":522,"hi":690,"n":5,"rr":708,"mr":530},{"m":"vllm-sr-d3-flash","r":563,"s":63.54,"lo":384,"hi":725,"n":8,"rr":86,"mr":570},{"m":"gpt-4.1-mini","r":564,"s":63.53,"lo":469,"hi":610,"n":16,"rr":1419,"mr":568},{"m":"mellum2-12b-a2.5b-thinking","r":565,"s":63.51,"lo":445,"hi":1060,"n":10,"rr":502,"mr":554},{"m":"deepseek-r1-distill-llama-70b","r":566,"s":63.49,"lo":508,"hi":752,"n":3,"rr":984,"mr":625},{"m":"instella-moe-16b-a3b-think","r":567,"s":63.43,"lo":423,"hi":713,"n":10,"rr":300,"mr":556},{"m":"phi-4-reasoning","r":568,"s":63.41,"lo":523,"hi":619,"n":4,"rr":882,"mr":578},{"m":"midm-k-2.5-pro","r":569,"s":63.38,"lo":218,"hi":1004,"n":7,"rr":1296,"mr":580},{"m":"qwen3-8b-thinking","r":570,"s":63.34,"lo":436,"hi":635,"n":28,"rr":889,"mr":544},{"m":"tri-21b-think","r":571,"s":63.32,"lo":340,"hi":699,"n":11,"rr":804,"mr":533},{"m":"gka-primed-hqwen3-8b-reasoner","r":572,"s":63.29,"lo":477,"hi":1168,"n":5,"rr":1324,"mr":622},{"m":"claude-3.5-sonnet-20240620","r":573,"s":63.28,"lo":480,"hi":640,"n":24,"rr":216,"mr":555},{"m":"olmo-3-think-7b","r":574,"s":63.25,"lo":503,"hi":654,"n":25,"rr":600,"mr":545},{"m":"acereason-nemotron-1.1","r":575,"s":63.19,"lo":521,"hi":665,"n":3,"rr":1193,"mr":586},{"m":"lg-exaone-32b","r":576,"s":63.15,"lo":357,"hi":698,"n":8,"rr":198,"mr":571},{"m":"mistral-medium-3","r":577,"s":63.13,"lo":436,"hi":666,"n":15,"rr":547,"mr":569},{"m":"trinity-large-preview","r":578,"s":63.1,"lo":528,"hi":656,"n":5,"rr":987,"mr":581},{"m":"deepseek-r1-0528-qwen3-8b","r":579,"s":63.08,"lo":453,"hi":738,"n":8,"rr":1246,"mr":558},{"m":"deberta-turingnlrv4","r":580,"s":63.07,"lo":539,"hi":740,"n":3,"rr":6,"mr":667},{"m":"turing-nlr-v5","r":581,"s":63.01,"lo":536,"hi":727,"n":3,"rr":4,"mr":688},{"m":"vibethinker-1.5b","r":582,"s":63.01,"lo":525,"hi":727,"n":4,"rr":1184,"mr":577},{"m":"o3-mini-2025-01-31","r":583,"s":62.97,"lo":496,"hi":671,"n":5,"rr":1012,"mr":638},{"m":"autotrust-gev-26b-decide","r":584,"s":62.95,"lo":379,"hi":740,"n":8,"rr":87,"mr":595},{"m":"llama-3.1-tulu-3-405b-dpo","r":585,"s":62.89,"lo":347,"hi":759,"n":9,"rr":105,"mr":593},{"m":"olmo-3-think-7b-dpo","r":586,"s":62.84,"lo":498,"hi":705,"n":16,"rr":785,"mr":562},{"m":"gpt-5.1-none","r":587,"s":62.78,"lo":524,"hi":626,"n":3,"rr":1604,"mr":603},{"m":"gpt-4o-2024-11-24","r":588,"s":62.77,"lo":366,"hi":758,"n":9,"rr":79,"mr":627},{"m":"llama-3.1-nemotron-nano-8b-v1","r":589,"s":62.77,"lo":454,"hi":809,"n":9,"rr":642,"mr":652},{"m":"magistral-small-2506","r":590,"s":62.68,"lo":524,"hi":625,"n":6,"rr":1481,"mr":592},{"m":"hunyuan-turbos","r":591,"s":62.63,"lo":417,"hi":822,"n":3,"rr":1047,"mr":663},{"m":"gpt-4o-0327","r":592,"s":62.58,"lo":464,"hi":721,"n":9,"rr":508,"mr":650},{"m":"qwen2.5-max","r":593,"s":62.55,"lo":386,"hi":728,"n":9,"rr":71,"mr":600},{"m":"granite-4.2-3b","r":594,"s":62.53,"lo":470,"hi":702,"n":20,"rr":1113,"mr":559},{"m":"vllm-sr-decision-2.0-vega-27b","r":595,"s":62.53,"lo":400,"hi":758,"n":8,"rr":113,"mr":599},{"m":"gdn-primed-hqwen3-8b-reasoner","r":596,"s":62.44,"lo":484,"hi":1180,"n":5,"rr":1368,"mr":651},{"m":"gemini-2.5-flash-lite-thinking","r":597,"s":62.44,"lo":486,"hi":702,"n":5,"rr":1265,"mr":563},{"m":"kat-dev-32b","r":598,"s":62.44,"lo":324,"hi":700,"n":13,"rr":977,"mr":598},{"m":"kimi-k2-base","r":599,"s":62.43,"lo":497,"hi":670,"n":41,"rr":178,"mr":560},{"m":"kimi-linear-instruct","r":600,"s":62.41,"lo":501,"hi":727,"n":19,"rr":1010,"mr":561},{"m":"glm-5.3-flash-base","r":601,"s":62.39,"lo":441,"hi":692,"n":5,"rr":584,"mr":616},{"m":"instella-moe-16b-a3b-dpo","r":602,"s":62.31,"lo":458,"hi":739,"n":10,"rr":340,"mr":579},{"m":"gemini-2.5-flash-lite","r":603,"s":62.22,"lo":495,"hi":749,"n":19,"rr":1293,"mr":585},{"m":"qwen3-swallow-30b-a3b-cpt-v0.2","r":604,"s":62.21,"lo":564,"hi":648,"n":5,"rr":302,"mr":574},{"m":"aliceai-foundation-80b-a3b-base","r":605,"s":62.2,"lo":536,"hi":677,"n":6,"rr":539,"mr":618},{"m":"autotrust-jev-27b","r":606,"s":62.2,"lo":428,"hi":780,"n":8,"rr":135,"mr":614},{"m":"solar-pro-3","r":607,"s":62.09,"lo":404,"hi":935,"n":4,"rr":1455,"mr":643},{"m":"glm-5-base","r":608,"s":62.07,"lo":400,"hi":721,"n":5,"rr":574,"mr":609},{"m":"ministral-3-14b-reasoning","r":609,"s":62.06,"lo":510,"hi":812,"n":9,"rr":818,"mr":573},{"m":"deepseek-v4-pro-base","r":610,"s":62,"lo":461,"hi":731,"n":21,"rr":97,"mr":584},{"m":"qwen2.5-plus-1127","r":611,"s":61.98,"lo":556,"hi":638,"n":11,"rr":209,"mr":589},{"m":"llama-nemotron-super-49b-v1.5","r":612,"s":61.94,"lo":360,"hi":739,"n":8,"rr":1321,"mr":591},{"m":"qwen3-swallow-8b-rl-v0.2","r":613,"s":61.89,"lo":538,"hi":793,"n":5,"rr":430,"mr":588},{"m":"qwen3-swallow-30b-a3b-sft-v0.2","r":614,"s":61.82,"lo":557,"hi":707,"n":5,"rr":376,"mr":587},{"m":"hunyuan-large-instruct","r":615,"s":61.71,"lo":506,"hi":674,"n":11,"rr":83,"mr":612},{"m":"qwen3.8-27b-iq2-xxs","r":616,"s":61.64,"lo":456,"hi":737,"n":10,"rr":165,"mr":606},{"m":"openpangu-r-7b-2512-fast-thinking","r":617,"s":61.63,"lo":485,"hi":711,"n":16,"rr":967,"mr":594},{"m":"rnj-1.5","r":618,"s":61.5,"lo":509,"hi":771,"n":7,"rr":718,"mr":634},{"m":"qwen3-vl-8b-instruct","r":619,"s":61.5,"lo":517,"hi":693,"n":29,"rr":793,"mr":596},{"m":"exaone-4.0-32b","r":620,"s":61.38,"lo":413,"hi":777,"n":10,"rr":1288,"mr":619},{"m":"gpt-4o-2024-11-20","r":621,"s":61.33,"lo":528,"hi":695,"n":12,"rr":1357,"mr":657},{"m":"t5-plus-udg-single-model-google-brain","r":622,"s":61.32,"lo":573,"hi":750,"n":3,"rr":5,"mr":717},{"m":"nemotron-3-ultra-base","r":623,"s":61.29,"lo":495,"hi":732,"n":18,"rr":54,"mr":610},{"m":"gpt-4o","r":624,"s":61.27,"lo":563,"hi":651,"n":51,"rr":1084,"mr":607},{"m":"mistral-medium-3.1","r":625,"s":61.16,"lo":446,"hi":730,"n":9,"rr":1198,"mr":629},{"m":"qwen3-4b-thinking-2507","r":626,"s":61.1,"lo":555,"hi":699,"n":22,"rr":983,"mr":590},{"m":"k2-think-v2","r":627,"s":61.1,"lo":303,"hi":747,"n":9,"rr":423,"mr":602},{"m":"ling-mini-2.0","r":628,"s":61.1,"lo":533,"hi":711,"n":27,"rr":622,"mr":617},{"m":"olmo-3-think-7b-sft","r":629,"s":61.01,"lo":515,"hi":739,"n":16,"rr":855,"mr":601},{"m":"instella-moe-16b-a3b-sft","r":630,"s":60.94,"lo":470,"hi":748,"n":10,"rr":382,"mr":615},{"m":"mimo-7b-rl","r":631,"s":60.9,"lo":547,"hi":797,"n":8,"rr":1301,"mr":613},{"m":"magistral-small-1.2","r":632,"s":60.83,"lo":460,"hi":741,"n":9,"rr":1326,"mr":605},{"m":"gpt-5-nano-low","r":633,"s":60.82,"lo":533,"hi":686,"n":4,"rr":1609,"mr":662},{"m":"pplx-decider-flash-v1.2","r":634,"s":60.81,"lo":448,"hi":803,"n":8,"rr":139,"mr":636},{"m":"gpt-4o-2024-08-06","r":635,"s":60.8,"lo":487,"hi":709,"n":25,"rr":487,"mr":621},{"m":"hermes-4.3-70b","r":636,"s":60.71,"lo":443,"hi":709,"n":3,"rr":834,"mr":707},{"m":"seed1.6","r":637,"s":60.64,"lo":438,"hi":730,"n":11,"rr":529,"mr":620},{"m":"gemini-2.0-flash-001","r":638,"s":60.6,"lo":458,"hi":848,"n":6,"rr":657,"mr":677},{"m":"mistral-large-instruct-2407","r":639,"s":60.56,"lo":553,"hi":698,"n":17,"rr":344,"mr":628},{"m":"plamo-3.0-prime-beta","r":640,"s":60.51,"lo":440,"hi":832,"n":5,"rr":1199,"mr":644},{"m":"kanana-2-30b-a3b-instruct-2601","r":641,"s":60.5,"lo":563,"hi":712,"n":10,"rr":350,"mr":604},{"m":"vllm-sr-d3-mini","r":642,"s":60.45,"lo":438,"hi":799,"n":8,"rr":122,"mr":642},{"m":"olmo-hybrid-think-7b-sft","r":643,"s":60.44,"lo":529,"hi":735,"n":13,"rr":819,"mr":633},{"m":"mistral-small-4","r":644,"s":60.37,"lo":512,"hi":736,"n":10,"rr":1390,"mr":611},{"m":"kimi-dev-72b","r":645,"s":60.2,"lo":364,"hi":751,"n":13,"rr":1094,"mr":654},{"m":"gemini-1.5-pro","r":646,"s":60.17,"lo":556,"hi":722,"n":30,"rr":599,"mr":624},{"m":"qwen2.5-math-72b-instruct","r":647,"s":60.12,"lo":566,"hi":711,"n":6,"rr":101,"mr":676},{"m":"llama-4-maverick","r":648,"s":60.09,"lo":550,"hi":758,"n":20,"rr":1422,"mr":637},{"m":"claude-3.5-haiku","r":649,"s":59.93,"lo":324,"hi":725,"n":5,"rr":973,"mr":706},{"m":"qwen2.5-72b-instruct","r":650,"s":59.91,"lo":583,"hi":711,"n":54,"rr":532,"mr":623},{"m":"llama-3.2-90b-vision","r":651,"s":59.89,"lo":586,"hi":722,"n":3,"rr":240,"mr":738},{"m":"k2-medium-70b","r":652,"s":59.87,"lo":579,"hi":752,"n":7,"rr":641,"mr":632},{"m":"gpt-4o-2024-05-13","r":653,"s":59.85,"lo":537,"hi":709,"n":34,"rr":595,"mr":639},{"m":"gpt-4-0125-preview","r":654,"s":59.83,"lo":603,"hi":691,"n":3,"rr":126,"mr":737},{"m":"llada2.1-mini-q","r":655,"s":59.8,"lo":543,"hi":769,"n":26,"rr":603,"mr":648},{"m":"gpt-4-turbo","r":656,"s":59.73,"lo":563,"hi":705,"n":10,"rr":531,"mr":681},{"m":"olmo-3.1-instruct-32b-dpo","r":657,"s":59.73,"lo":573,"hi":735,"n":14,"rr":747,"mr":645},{"m":"chatgpt-4o","r":658,"s":59.72,"lo":520,"hi":832,"n":3,"rr":1325,"mr":757},{"m":"youtu-llm-2b","r":659,"s":59.49,"lo":553,"hi":740,"n":16,"rr":556,"mr":626},{"m":"deepseek-v4-flash-base","r":660,"s":59.48,"lo":528,"hi":772,"n":25,"rr":258,"mr":635},{"m":"gemma-4-e4b-it","r":661,"s":59.47,"lo":599,"hi":709,"n":37,"rr":1122,"mr":630},{"m":"claude-3-opus","r":662,"s":59.45,"lo":543,"hi":743,"n":19,"rr":128,"mr":631},{"m":"ling-3.0-flash-base","r":663,"s":59.42,"lo":558,"hi":741,"n":14,"rr":422,"mr":655},{"m":"llama-3.1-tulu-3-405b-sft","r":664,"s":59.39,"lo":417,"hi":813,"n":9,"rr":173,"mr":678},{"m":"gpt-4-turbo-2024-04-09","r":665,"s":59.37,"lo":583,"hi":712,"n":24,"rr":306,"mr":647},{"m":"grok-2","r":666,"s":59.35,"lo":570,"hi":711,"n":4,"rr":339,"mr":711},{"m":"ling-2.6-1t-base","r":667,"s":59.15,"lo":563,"hi":729,"n":21,"rr":693,"mr":646},{"m":"nemotron-3-super-120b-a12b-base","r":668,"s":59.14,"lo":584,"hi":722,"n":32,"rr":225,"mr":640},{"m":"llama-3.1-405b-instruct","r":669,"s":59.04,"lo":575,"hi":726,"n":31,"rr":542,"mr":641},{"m":"glm-4.6v-flash","r":670,"s":59.03,"lo":528,"hi":800,"n":5,"rr":1421,"mr":710},{"m":"nemotron-h-47b-reasoning","r":671,"s":58.99,"lo":578,"hi":830,"n":9,"rr":1404,"mr":669},{"m":"spark-x2.5-1.7b","r":672,"s":58.89,"lo":445,"hi":778,"n":10,"rr":1497,"mr":656},{"m":"amazon-nova-premier","r":673,"s":58.82,"lo":539,"hi":774,"n":8,"rr":1454,"mr":693},{"m":"llama-4-scout-17b-16e","r":674,"s":58.71,"lo":527,"hi":903,"n":8,"rr":1151,"mr":664},{"m":"openpangu-vl-7b","r":675,"s":58.7,"lo":559,"hi":795,"n":8,"rr":324,"mr":658},{"m":"qwen3-swallow-8b-sft-v0.2","r":676,"s":58.64,"lo":586,"hi":792,"n":5,"rr":561,"mr":661},{"m":"llada2.0-mini","r":677,"s":58.61,"lo":585,"hi":785,"n":30,"rr":788,"mr":660},{"m":"gpt-4-1106-preview","r":678,"s":58.59,"lo":608,"hi":739,"n":22,"rr":138,"mr":671},{"m":"qwq-32b-preview","r":679,"s":58.59,"lo":602,"hi":768,"n":6,"rr":782,"mr":699},{"m":"olmo-3.1-instruct-32b","r":680,"s":58.56,"lo":578,"hi":766,"n":24,"rr":428,"mr":659},{"m":"llama-4-scout","r":681,"s":58.56,"lo":529,"hi":911,"n":5,"rr":1338,"mr":739},{"m":"mimo-v2-flash-base","r":682,"s":58.54,"lo":580,"hi":760,"n":29,"rr":404,"mr":649},{"m":"ernie-3.0","r":683,"s":58.5,"lo":601,"hi":810,"n":3,"rr":7,"mr":755},{"m":"llada2.1-mini-s","r":684,"s":58.44,"lo":580,"hi":798,"n":26,"rr":697,"mr":675},{"m":"gemini-1.5-pro-002","r":685,"s":58.4,"lo":596,"hi":789,"n":15,"rr":592,"mr":684},{"m":"qwen-3-235b-a22b-nonthinking","r":686,"s":58.37,"lo":532,"hi":763,"n":9,"rr":607,"mr":702},{"m":"marco-mini-instruct","r":687,"s":58.32,"lo":562,"hi":776,"n":14,"rr":286,"mr":668},{"m":"hunyuan-large","r":688,"s":58.23,"lo":560,"hi":797,"n":18,"rr":52,"mr":672},{"m":"skywork-or1-7b","r":689,"s":58.21,"lo":619,"hi":764,"n":3,"rr":1424,"mr":705},{"m":"qwen3-4b-2507","r":690,"s":58.18,"lo":556,"hi":835,"n":12,"rr":1388,"mr":665},{"m":"qwen3-14b","r":691,"s":58.16,"lo":603,"hi":733,"n":35,"rr":875,"mr":653},{"m":"qwen3-4b-instruct-2507","r":692,"s":58.06,"lo":613,"hi":759,"n":29,"rr":774,"mr":670},{"m":"jamba2-3b","r":693,"s":58.04,"lo":265,"hi":888,"n":3,"rr":838,"mr":748},{"m":"deepseek-v4.1-flash-base","r":694,"s":58.03,"lo":546,"hi":795,"n":13,"rr":289,"mr":690},{"m":"qwen3-vl-4b-thinking","r":695,"s":58,"lo":593,"hi":959,"n":4,"rr":1520,"mr":698},{"m":"openpangu-embedded-7b-v1.1","r":696,"s":57.97,"lo":637,"hi":802,"n":3,"rr":468,"mr":709},{"m":"qwen2-math-72b-instruct","r":697,"s":57.96,"lo":592,"hi":789,"n":6,"rr":182,"mr":740},{"m":"hy3-preview-base","r":698,"s":57.91,"lo":624,"hi":761,"n":29,"rr":460,"mr":674},{"m":"deepseek-v3.2-base","r":699,"s":57.86,"lo":572,"hi":803,"n":20,"rr":115,"mr":673},{"m":"command-a","r":700,"s":57.81,"lo":570,"hi":799,"n":5,"rr":957,"mr":735},{"m":"mimo-vl-7b-rl","r":701,"s":57.77,"lo":622,"hi":821,"n":5,"rr":628,"mr":695},{"m":"llama-3.1-tulu-3-70b-dpo","r":702,"s":57.75,"lo":585,"hi":806,"n":11,"rr":232,"mr":703},{"m":"llama-3.1-tulu-3-70b","r":703,"s":57.74,"lo":585,"hi":800,"n":11,"rr":226,"mr":726},{"m":"gpt-4-0613","r":704,"s":57.74,"lo":637,"hi":757,"n":6,"rr":118,"mr":744},{"m":"fanar-2-27b-instruct","r":705,"s":57.59,"lo":444,"hi":1494,"n":5,"rr":1112,"mr":708},{"m":"ministral-3-14b-instruct","r":706,"s":57.54,"lo":591,"hi":809,"n":17,"rr":827,"mr":666},{"m":"lfm2.5-2.6b","r":707,"s":57.48,"lo":510,"hi":837,"n":15,"rr":1191,"mr":689},{"m":"kanana-2-30b-a3b-instruct","r":708,"s":57.44,"lo":618,"hi":781,"n":10,"rr":473,"mr":679},{"m":"hermes-3-llama-3.1-405b","r":709,"s":57.4,"lo":569,"hi":848,"n":10,"rr":208,"mr":728},{"m":"nemotron-3-nano-4b-thinking","r":710,"s":57.32,"lo":576,"hi":881,"n":11,"rr":1290,"mr":686},{"m":"hunyuan-4b-instruct","r":711,"s":57.28,"lo":640,"hi":855,"n":6,"rr":1365,"mr":724},{"m":"qwen2.5-turbo","r":712,"s":57.23,"lo":657,"hi":753,"n":17,"rr":150,"mr":694},{"m":"lfm2.5-8b-a1b","r":713,"s":57.16,"lo":561,"hi":844,"n":17,"rr":1244,"mr":687},{"m":"bespoke-nimble-9b-v3","r":714,"s":57.01,"lo":574,"hi":810,"n":8,"rr":161,"mr":716},{"m":"qwen3-235b-a22b-base","r":715,"s":56.91,"lo":608,"hi":761,"n":9,"rr":271,"mr":683},{"m":"qwen2.5-32b-instruct","r":716,"s":56.9,"lo":665,"hi":762,"n":42,"rr":455,"mr":685},{"m":"deepseek-v2.5","r":717,"s":56.88,"lo":649,"hi":753,"n":32,"rr":604,"mr":680},{"m":"openthinker3-7b","r":718,"s":56.87,"lo":580,"hi":988,"n":14,"rr":1037,"mr":723},{"m":"nemotron-3.5-super-vl-120b-a12b-base","r":719,"s":56.86,"lo":617,"hi":780,"n":21,"rr":180,"mr":691},{"m":"gpt-4o-mini","r":720,"s":56.76,"lo":641,"hi":765,"n":28,"rr":565,"mr":712},{"m":"gpt-4o-mini-2024-07-18","r":721,"s":56.65,"lo":595,"hi":808,"n":19,"rr":885,"mr":729},{"m":"qwen3-vl-4b-instruct","r":722,"s":56.64,"lo":625,"hi":780,"n":23,"rr":843,"mr":697},{"m":"qwen3-8b","r":723,"s":56.57,"lo":641,"hi":793,"n":52,"rr":1008,"mr":682},{"m":"granite-4.1-30b","r":724,"s":56.5,"lo":655,"hi":778,"n":21,"rr":381,"mr":704},{"m":"gemini-2.0-flash-exp","r":725,"s":56.47,"lo":547,"hi":852,"n":4,"rr":1367,"mr":769},{"m":"yi-lightning","r":726,"s":56.42,"lo":559,"hi":780,"n":8,"rr":631,"mr":733},{"m":"kat-dev-72b-exp","r":727,"s":56.36,"lo":574,"hi":789,"n":12,"rr":1075,"mr":736},{"m":"mistral-large-2411","r":728,"s":56.3,"lo":624,"hi":795,"n":9,"rr":1144,"mr":759},{"m":"aquif-3-moe-17b-a2.8b","r":729,"s":56.3,"lo":612,"hi":845,"n":4,"rr":675,"mr":720},{"m":"deepseek-v3-base","r":730,"s":56.24,"lo":595,"hi":818,"n":33,"rr":237,"mr":696},{"m":"openpangu-r-7b-diffusion","r":731,"s":56.23,"lo":670,"hi":830,"n":9,"rr":111,"mr":700},{"m":"qwen2.5-math-7b-instruct","r":732,"s":56.08,"lo":650,"hi":805,"n":6,"rr":238,"mr":773},{"m":"trinity-mini","r":733,"s":56.06,"lo":626,"hi":862,"n":9,"rr":901,"mr":692},{"m":"llama-3.1-405b-instruct-bf16","r":734,"s":55.99,"lo":556,"hi":811,"n":3,"rr":389,"mr":795},{"m":"qwen-turbo-0919","r":735,"s":55.97,"lo":686,"hi":763,"n":11,"rr":488,"mr":727},{"m":"alodlm-8b","r":736,"s":55.97,"lo":665,"hi":773,"n":11,"rr":84,"mr":718},{"m":"deepseek-v3.2-exp-base","r":737,"s":55.94,"lo":599,"hi":850,"n":28,"rr":256,"mr":714},{"m":"qwen2.5-coder-32b-instruct","r":738,"s":55.89,"lo":652,"hi":795,"n":26,"rr":864,"mr":715},{"m":"iquest-coder-v1-7b-thinking","r":739,"s":55.85,"lo":512,"hi":873,"n":4,"rr":1535,"mr":745},{"m":"qwen3-4b","r":740,"s":55.79,"lo":634,"hi":808,"n":45,"rr":710,"mr":701},{"m":"grok-2-1212","r":741,"s":55.74,"lo":532,"hi":802,"n":5,"rr":1044,"mr":794},{"m":"llama-3.3-70b-instruct","r":742,"s":55.72,"lo":649,"hi":804,"n":22,"rr":448,"mr":721},{"m":"claude-3-opus-20240229","r":743,"s":55.59,"lo":638,"hi":797,"n":17,"rr":437,"mr":746},{"m":"glm-4.5-base","r":744,"s":55.56,"lo":636,"hi":802,"n":36,"rr":365,"mr":713},{"m":"telechat2-115b","r":745,"s":55.47,"lo":582,"hi":850,"n":8,"rr":46,"mr":779},{"m":"llama-3.1-405b-instruct-fp8","r":746,"s":55.4,"lo":665,"hi":780,"n":9,"rr":424,"mr":764},{"m":"gemma-3-27b-it","r":747,"s":55.37,"lo":659,"hi":803,"n":43,"rr":919,"mr":719},{"m":"motif-3-base","r":748,"s":55.37,"lo":633,"hi":827,"n":10,"rr":57,"mr":731},{"m":"llama-3.3-70b","r":749,"s":55.32,"lo":614,"hi":865,"n":26,"rr":489,"mr":722},{"m":"mistral-large-2407","r":750,"s":55.26,"lo":592,"hi":822,"n":4,"rr":285,"mr":809},{"m":"ling-1t-base","r":751,"s":55.25,"lo":663,"hi":784,"n":21,"rr":840,"mr":730},{"m":"nemotron-3-nano-4b","r":752,"s":55.16,"lo":635,"hi":880,"n":19,"rr":1287,"mr":732},{"m":"mimo-vl-7b-sft","r":753,"s":54.91,"lo":681,"hi":861,"n":5,"rr":732,"mr":753},{"m":"command-a-reasoning-08-2025","r":754,"s":54.87,"lo":605,"hi":864,"n":5,"rr":1488,"mr":772},{"m":"stable-diffcoder-8b-instruct","r":755,"s":54.78,"lo":627,"hi":845,"n":5,"rr":417,"mr":778},{"m":"mimo-v2.5-base","r":756,"s":54.71,"lo":624,"hi":845,"n":27,"rr":481,"mr":734},{"m":"qwen2.5-14b-instruct","r":757,"s":54.66,"lo":711,"hi":833,"n":23,"rr":314,"mr":741},{"m":"rnj-1","r":758,"s":54.65,"lo":647,"hi":908,"n":7,"rr":1081,"mr":765},{"m":"gemma-3-27b","r":759,"s":54.57,"lo":635,"hi":875,"n":28,"rr":354,"mr":725},{"m":"qwen3-8b-non-thinking","r":760,"s":54.4,"lo":695,"hi":839,"n":36,"rr":833,"mr":743},{"m":"ling-2.5-flash-base","r":761,"s":54.39,"lo":667,"hi":828,"n":14,"rr":664,"mr":760},{"m":"qwen3-32b-nothinking","r":762,"s":54.33,"lo":672,"hi":834,"n":26,"rr":1158,"mr":749},{"m":"nemotron-3-nano-30b-a3b-base","r":763,"s":54.21,"lo":702,"hi":817,"n":19,"rr":93,"mr":752},{"m":"deepseek-coder-v2-instruct","r":764,"s":54.08,"lo":714,"hi":811,"n":32,"rr":625,"mr":742},{"m":"lfm2-2.6b-exp","r":765,"s":54.07,"lo":559,"hi":895,"n":5,"rr":866,"mr":783},{"m":"chatgpt-4o-latest-20240903","r":766,"s":54.02,"lo":539,"hi":813,"n":3,"rr":567,"mr":830},{"m":"llama-3.1-70b","r":767,"s":54.02,"lo":651,"hi":1051,"n":23,"rr":449,"mr":756},{"m":"step-3.5-flash-base-midtrain","r":768,"s":53.99,"lo":642,"hi":859,"n":19,"rr":451,"mr":751},{"m":"step-2","r":769,"s":53.95,"lo":680,"hi":818,"n":3,"rr":63,"mr":815},{"m":"grok-beta","r":770,"s":53.94,"lo":666,"hi":925,"n":6,"rr":325,"mr":788},{"m":"step-3.5-flash-base","r":771,"s":53.86,"lo":646,"hi":831,"n":29,"rr":583,"mr":754},{"m":"claude-3.5-haiku-20241022","r":772,"s":53.83,"lo":631,"hi":886,"n":10,"rr":1200,"mr":785},{"m":"vllm-sr-decision-2.0-lux-9b","r":773,"s":53.78,"lo":637,"hi":914,"n":8,"rr":242,"mr":777},{"m":"joyai-llm-flash-base","r":774,"s":53.77,"lo":667,"hi":841,"n":8,"rr":175,"mr":750},{"m":"qwen3-4b-saferl-thinking","r":775,"s":53.76,"lo":645,"hi":1173,"n":3,"rr":1460,"mr":822},{"m":"diffusiongemma-jev","r":776,"s":53.63,"lo":678,"hi":888,"n":8,"rr":253,"mr":792},{"m":"llama-4-maverick-17b-128e-base","r":777,"s":53.58,"lo":434,"hi":915,"n":3,"rr":98,"mr":806},{"m":"gemini-1.5-pro-exp-0801","r":778,"s":53.57,"lo":614,"hi":862,"n":3,"rr":497,"mr":832},{"m":"gpt-5-nano-minimal","r":779,"s":53.49,"lo":559,"hi":844,"n":10,"rr":1564,"mr":782},{"m":"exaone-4.0-1.2b","r":780,"s":53.49,"lo":697,"hi":932,"n":11,"rr":1189,"mr":771},{"m":"deepseek-v3.1-base","r":781,"s":53.48,"lo":636,"hi":875,"n":19,"rr":443,"mr":768},{"m":"seed1.5","r":782,"s":53.42,"lo":625,"hi":846,"n":8,"rr":412,"mr":762},{"m":"kolibri-1-base","r":783,"s":53.39,"lo":687,"hi":874,"n":9,"rr":72,"mr":784},{"m":"kanana-1.5-32.5b-instruct","r":784,"s":53.37,"lo":716,"hi":835,"n":10,"rr":655,"mr":761},{"m":"llada2.1-mini","r":785,"s":53.34,"lo":626,"hi":918,"n":9,"rr":1300,"mr":781},{"m":"mistral-3.2-24b","r":786,"s":53.32,"lo":674,"hi":871,"n":12,"rr":143,"mr":758},{"m":"mistral-small-3.2-24b-instruct","r":787,"s":53.28,"lo":651,"hi":861,"n":15,"rr":865,"mr":763},{"m":"llama-4-scout-17b","r":788,"s":53.25,"lo":678,"hi":886,"n":20,"rr":721,"mr":747},{"m":"llama-3.1-70b-instruct","r":789,"s":53.12,"lo":729,"hi":838,"n":41,"rr":467,"mr":770},{"m":"granite-4.1-8b","r":790,"s":53.09,"lo":736,"hi":854,"n":21,"rr":545,"mr":775},{"m":"deepseek-v2-chat-0628","r":791,"s":53.06,"lo":733,"hi":830,"n":11,"rr":520,"mr":789},{"m":"qwen3-swallow-8b-cpt-v0.2","r":792,"s":53.02,"lo":727,"hi":857,"n":5,"rr":759,"mr":774},{"m":"ling-2.6-flash-base","r":793,"s":53,"lo":728,"hi":830,"n":21,"rr":938,"mr":776},{"m":"gemini-1.5-flash-exp-0827","r":794,"s":52.97,"lo":633,"hi":865,"n":3,"rr":554,"mr":842},{"m":"llama-3.1-tulu-3-70b-sft","r":795,"s":52.94,"lo":610,"hi":911,"n":11,"rr":398,"mr":803},{"m":"telechat2-35b","r":796,"s":52.93,"lo":630,"hi":895,"n":8,"rr":53,"mr":807},{"m":"qwen3.5-35b-a3b-base","r":797,"s":52.79,"lo":662,"hi":887,"n":17,"rr":315,"mr":780},{"m":"step-3","r":798,"s":52.71,"lo":9,"hi":1173,"n":4,"rr":1447,"mr":855},{"m":"mellum2-12b-a2.5b-instruct","r":799,"s":52.67,"lo":735,"hi":862,"n":9,"rr":659,"mr":786},{"m":"mistral-large-3-base","r":800,"s":52.66,"lo":654,"hi":891,"n":23,"rr":414,"mr":767},{"m":"mistral-small-3.1-24b-instruct","r":801,"s":52.66,"lo":714,"hi":860,"n":12,"rr":1104,"mr":791},{"m":"qwen-2.5-72b","r":802,"s":52.63,"lo":723,"hi":859,"n":35,"rr":378,"mr":766},{"m":"minicpm-o-4.5","r":803,"s":52.62,"lo":701,"hi":861,"n":7,"rr":66,"mr":796},{"m":"llada2.2-mini","r":804,"s":52.41,"lo":660,"hi":961,"n":9,"rr":1294,"mr":804},{"m":"magistral-small-2509","r":805,"s":52.38,"lo":729,"hi":924,"n":6,"rr":1022,"mr":810},{"m":"autotrust-jev-9b","r":806,"s":52.31,"lo":680,"hi":959,"n":8,"rr":312,"mr":801},{"m":"gpt-4","r":807,"s":52.26,"lo":711,"hi":881,"n":26,"rr":245,"mr":798},{"m":"skywork-o1-open-llama-3.1-8b","r":808,"s":52.13,"lo":755,"hi":864,"n":9,"rr":587,"mr":799},{"m":"qwen2-72b-instruct","r":809,"s":52.04,"lo":748,"hi":849,"n":26,"rr":503,"mr":790},{"m":"qwen2.5-math-72b","r":810,"s":52.03,"lo":739,"hi":842,"n":4,"rr":58,"mr":837},{"m":"bespoke-nimble-9b-v2","r":811,"s":52.01,"lo":708,"hi":943,"n":8,"rr":304,"mr":805},{"m":"frozen-t5-1.1-plus-spot","r":812,"s":51.97,"lo":638,"hi":952,"n":3,"rr":8,"mr":878},{"m":"stable-diffcoder-8b-base","r":813,"s":51.94,"lo":684,"hi":900,"n":4,"rr":270,"mr":828},{"m":"qwen3-8b-instruct","r":814,"s":51.89,"lo":760,"hi":874,"n":10,"rr":149,"mr":787},{"m":"deepseek-coder-v2-instruct-0724","r":815,"s":51.89,"lo":744,"hi":850,"n":8,"rr":1027,"mr":813},{"m":"jamba2-mini","r":816,"s":51.82,"lo":113,"hi":893,"n":4,"rr":1020,"mr":835},{"m":"k2-horizon-0.9b","r":817,"s":51.69,"lo":722,"hi":1128,"n":4,"rr":1126,"mr":821},{"m":"gemini-1.5-flash","r":818,"s":51.66,"lo":746,"hi":864,"n":18,"rr":777,"mr":802},{"m":"exaone-deep-2.4b","r":819,"s":51.58,"lo":719,"hi":1071,"n":10,"rr":1305,"mr":816},{"m":"k2-low-70b","r":820,"s":51.48,"lo":762,"hi":871,"n":7,"rr":1019,"mr":800},{"m":"llada2.0-flash-preview","r":821,"s":51.44,"lo":760,"hi":885,"n":19,"rr":509,"mr":793},{"m":"gpt-3.5-turbo-nov-2023","r":822,"s":51.44,"lo":709,"hi":899,"n":3,"rr":241,"mr":852},{"m":"glm-4-0520","r":823,"s":51.32,"lo":713,"hi":877,"n":8,"rr":207,"mr":829},{"m":"qwen2-math-7b-instruct","r":824,"s":51.25,"lo":772,"hi":897,"n":6,"rr":434,"mr":839},{"m":"iquest-coder-v1-7b-instruct","r":825,"s":51.19,"lo":449,"hi":936,"n":4,"rr":1565,"mr":825},{"m":"hermes-3-llama-3.1-70b","r":826,"s":51.01,"lo":686,"hi":991,"n":12,"rr":421,"mr":838},{"m":"gemma-3-12b-it","r":827,"s":50.85,"lo":746,"hi":939,"n":44,"rr":896,"mr":797},{"m":"qwen3-4b-thinking","r":828,"s":50.84,"lo":653,"hi":1189,"n":5,"rr":1518,"mr":869},{"m":"phi-4-14b","r":829,"s":50.79,"lo":743,"hi":879,"n":6,"rr":992,"mr":818},{"m":"nemotron-3.5-lightning-30b-a3b-base","r":830,"s":50.74,"lo":775,"hi":897,"n":14,"rr":151,"mr":814},{"m":"ministral-3-14b-base","r":831,"s":50.57,"lo":791,"hi":873,"n":6,"rr":259,"mr":833},{"m":"qwen2.5-coder-14b-instruct","r":832,"s":50.53,"lo":714,"hi":954,"n":22,"rr":1076,"mr":819},{"m":"opencodeinterpreter-ds-33b","r":833,"s":50.5,"lo":771,"hi":856,"n":5,"rr":213,"mr":846},{"m":"wedlm-8b-instruct","r":834,"s":50.46,"lo":790,"hi":865,"n":12,"rr":217,"mr":812},{"m":"claude-3-sonnet","r":835,"s":50.44,"lo":691,"hi":959,"n":5,"rr":155,"mr":853},{"m":"llama-3.1-nemotron-70b","r":836,"s":50.24,"lo":539,"hi":991,"n":11,"rr":360,"mr":844},{"m":"mistral-small-3.1-24b-instruct-2503","r":837,"s":50.23,"lo":718,"hi":972,"n":3,"rr":807,"mr":881},{"m":"t5","r":838,"s":50.21,"lo":629,"hi":994,"n":3,"rr":9,"mr":920},{"m":"olmo-3.1-instruct-32b-sft","r":839,"s":50.19,"lo":786,"hi":923,"n":14,"rr":1129,"mr":827},{"m":"qwen3-30b-a3b-base","r":840,"s":50.11,"lo":788,"hi":917,"n":17,"rr":319,"mr":808},{"m":"gemini-1.5-flash-002","r":841,"s":50.1,"lo":763,"hi":956,"n":13,"rr":942,"mr":840},{"m":"kimi-vl-a3b-thinking-2506","r":842,"s":50.06,"lo":35,"hi":1131,"n":4,"rr":1501,"mr":922},{"m":"ling-flash-base-2.0","r":843,"s":50.03,"lo":795,"hi":894,"n":35,"rr":753,"mr":817},{"m":"sdar-8b-chat","r":844,"s":50.01,"lo":783,"hi":958,"n":9,"rr":252,"mr":823},{"m":"falcon-h1-34b-instruct","r":845,"s":49.87,"lo":751,"hi":945,"n":20,"rr":831,"mr":811},{"m":"qwen2.5-math-1.5b-instruct","r":846,"s":49.75,"lo":783,"hi":970,"n":6,"rr":540,"mr":876},{"m":"wizardcoder-33b-v1.1","r":847,"s":49.67,"lo":811,"hi":872,"n":3,"rr":200,"mr":884},{"m":"granite-4.0-h-small","r":848,"s":49.5,"lo":778,"hi":908,"n":28,"rr":700,"mr":824},{"m":"claude-3-haiku-mar-2024","r":849,"s":49.5,"lo":751,"hi":932,"n":3,"rr":313,"mr":901},{"m":"gpt-4.1-nano","r":850,"s":49.48,"lo":623,"hi":925,"n":14,"rr":1461,"mr":843},{"m":"kev-9b","r":851,"s":49.42,"lo":741,"hi":992,"n":8,"rr":375,"mr":841},{"m":"qwen3-14b-base","r":852,"s":49.41,"lo":775,"hi":907,"n":6,"rr":292,"mr":862},{"m":"claude-3-sonnet-mar-2024","r":853,"s":49.35,"lo":683,"hi":1017,"n":3,"rr":334,"mr":926},{"m":"magicoder-s-ds-6.7b","r":854,"s":49.3,"lo":791,"hi":969,"n":8,"rr":632,"mr":868},{"m":"yuan2.0-m32","r":855,"s":49.29,"lo":680,"hi":957,"n":5,"rr":121,"mr":904},{"m":"artigenz-coder-ds-6.7b","r":856,"s":49.24,"lo":769,"hi":904,"n":5,"rr":244,"mr":874},{"m":"nemotron-labs-twotower-30b-a3b-base","r":857,"s":49.23,"lo":826,"hi":901,"n":11,"rr":102,"mr":836},{"m":"seed-coder-8b-base","r":858,"s":49.22,"lo":749,"hi":966,"n":4,"rr":407,"mr":885},{"m":"gpt-4-0314","r":859,"s":49.2,"lo":733,"hi":967,"n":9,"rr":525,"mr":886},{"m":"llama-4-maverick-base","r":860,"s":49.11,"lo":756,"hi":922,"n":12,"rr":701,"mr":820},{"m":"yi-coder-9b-chat","r":861,"s":49.08,"lo":761,"hi":983,"n":9,"rr":986,"mr":858},{"m":"midm-2.0-base-instruct","r":862,"s":49.05,"lo":777,"hi":968,"n":8,"rr":530,"mr":826},{"m":"internlm2-math-plus-mixtral8x22b","r":863,"s":49.02,"lo":742,"hi":933,"n":3,"rr":770,"mr":931},{"m":"gemma-4-e2b-it","r":864,"s":48.88,"lo":774,"hi":937,"n":32,"rr":1384,"mr":831},{"m":"mellum2-12b-a2.5b-thinking-sft","r":865,"s":48.77,"lo":397,"hi":1043,"n":7,"rr":669,"mr":849},{"m":"gpt-oss-20b-moe","r":866,"s":48.75,"lo":681,"hi":1502,"n":5,"rr":1277,"mr":939},{"m":"jamba-1.5-large","r":867,"s":48.6,"lo":756,"hi":960,"n":4,"rr":159,"mr":895},{"m":"mobilellm-r1.5-950m","r":868,"s":48.57,"lo":754,"hi":1010,"n":3,"rr":602,"mr":850},{"m":"opencodeinterpreter-ds-6.7b","r":869,"s":48.34,"lo":832,"hi":898,"n":5,"rr":298,"mr":898},{"m":"vllm-sr-decision-2.0-nox-4b","r":870,"s":48.33,"lo":747,"hi":1034,"n":8,"rr":393,"mr":857},{"m":"qwen2-math-72b","r":871,"s":48.23,"lo":820,"hi":914,"n":4,"rr":110,"mr":921},{"m":"ministral-3-8b-instruct","r":872,"s":48.19,"lo":722,"hi":1012,"n":16,"rr":749,"mr":845},{"m":"numinamath-72b-cot","r":873,"s":48.18,"lo":840,"hi":947,"n":6,"rr":624,"mr":913},{"m":"k2-v2","r":874,"s":48.14,"lo":694,"hi":1119,"n":15,"rr":268,"mr":834},{"m":"deepseek-v2-chat-sft","r":875,"s":48.14,"lo":811,"hi":938,"n":20,"rr":385,"mr":847},{"m":"claude-3-sonnet-20240229","r":876,"s":48.1,"lo":802,"hi":949,"n":12,"rr":500,"mr":892},{"m":"lfm2-350m-math","r":877,"s":48.05,"lo":773,"hi":1166,"n":3,"rr":950,"mr":907},{"m":"olmo-hybrid-instruct-7b-dpo","r":878,"s":47.99,"lo":796,"hi":1021,"n":13,"rr":1254,"mr":861},{"m":"glm-4-air-0605","r":879,"s":47.97,"lo":810,"hi":939,"n":8,"rr":307,"mr":899},{"m":"internvl-8b","r":880,"s":47.96,"lo":657,"hi":1005,"n":5,"rr":981,"mr":894},{"m":"codestral-22b-v0.1","r":881,"s":47.92,"lo":834,"hi":932,"n":9,"rr":799,"mr":887},{"m":"mistral-small-instruct-2409","r":882,"s":47.85,"lo":758,"hi":998,"n":3,"rr":979,"mr":935},{"m":"yi-large-preview","r":883,"s":47.78,"lo":754,"hi":945,"n":9,"rr":703,"mr":902},{"m":"deepseek-v2-chat","r":884,"s":47.77,"lo":831,"hi":948,"n":29,"rr":636,"mr":851},{"m":"g9v3-3b","r":885,"s":47.58,"lo":788,"hi":954,"n":3,"rr":1577,"mr":848},{"m":"llama-3.1-405b-base","r":886,"s":47.56,"lo":766,"hi":996,"n":30,"rr":261,"mr":863},{"m":"mellum2-12b-a2.5b-instruct-sft","r":887,"s":47.56,"lo":836,"hi":984,"n":9,"rr":888,"mr":864},{"m":"seed-coder-8b-instruct","r":888,"s":47.52,"lo":755,"hi":978,"n":21,"rr":1264,"mr":888},{"m":"tev1-4b-experimental","r":889,"s":47.52,"lo":780,"hi":1048,"n":8,"rr":432,"mr":871},{"m":"codegeex4-all-9b","r":890,"s":47.51,"lo":823,"hi":1070,"n":4,"rr":934,"mr":950},{"m":"llama-3-70b","r":891,"s":47.42,"lo":794,"hi":1034,"n":23,"rr":673,"mr":859},{"m":"speechless-codellama-34b-v2.0","r":892,"s":47.42,"lo":862,"hi":919,"n":5,"rr":370,"mr":916},{"m":"amazon-nova-pro-v1.0","r":893,"s":47.41,"lo":737,"hi":991,"n":5,"rr":1446,"mr":872},{"m":"trinity-large-base","r":894,"s":47.38,"lo":768,"hi":1037,"n":11,"rr":230,"mr":860},{"m":"abab6.5","r":895,"s":47.37,"lo":790,"hi":988,"n":4,"rr":221,"mr":934},{"m":"yi-34b-200k","r":896,"s":47.36,"lo":681,"hi":1232,"n":4,"rr":266,"mr":988},{"m":"gpt-3.5-turbo-1106","r":897,"s":47.35,"lo":827,"hi":954,"n":8,"rr":670,"mr":933},{"m":"olmo-3-instruct-7b-dpo","r":898,"s":47.33,"lo":804,"hi":1027,"n":15,"rr":1230,"mr":873},{"m":"qwen2.5-7b-instruct","r":899,"s":47.21,"lo":808,"hi":955,"n":41,"rr":871,"mr":867},{"m":"minicpm5-1b","r":900,"s":47.2,"lo":727,"hi":1048,"n":16,"rr":1259,"mr":854},{"m":"ling-3.0-tiny-base","r":901,"s":47.19,"lo":825,"hi":965,"n":14,"rr":909,"mr":870},{"m":"qwen-72b","r":902,"s":47.19,"lo":684,"hi":1137,"n":5,"rr":156,"mr":991},{"m":"minicpm4-8b","r":903,"s":47.19,"lo":834,"hi":974,"n":11,"rr":69,"mr":877},{"m":"llama-3-70b-instruct","r":904,"s":47.18,"lo":849,"hi":946,"n":33,"rr":617,"mr":866},{"m":"llama-4-scout-17b-16e-base","r":905,"s":47.16,"lo":520,"hi":1039,"n":3,"rr":275,"mr":923},{"m":"llada2.0-mini-preview","r":906,"s":47.13,"lo":837,"hi":1075,"n":9,"rr":383,"mr":865},{"m":"olmo-3-instruct-7b","r":907,"s":47.12,"lo":827,"hi":1017,"n":32,"rr":961,"mr":856},{"m":"opencoder-8b-instruct","r":908,"s":47.09,"lo":801,"hi":1003,"n":9,"rr":1125,"mr":914},{"m":"deepseek-coder-33b-instruct","r":909,"s":46.88,"lo":839,"hi":1014,"n":12,"rr":1205,"mr":925},{"m":"xwincoder-34b","r":910,"s":46.86,"lo":858,"hi":935,"n":5,"rr":372,"mr":929},{"m":"code-millenials-34b","r":911,"s":46.86,"lo":855,"hi":936,"n":5,"rr":369,"mr":930},{"m":"ouro-2.6b","r":912,"s":46.79,"lo":784,"hi":1007,"n":12,"rr":212,"mr":875},{"m":"qwen2.5-math-7b","r":913,"s":46.65,"lo":809,"hi":973,"n":4,"rr":218,"mr":973},{"m":"phi-3.5-moe-instruct","r":914,"s":46.64,"lo":843,"hi":996,"n":12,"rr":348,"mr":912},{"m":"qwen2.5-32b-base","r":915,"s":46.6,"lo":797,"hi":1088,"n":24,"rr":272,"mr":880},{"m":"hy-1.8b","r":916,"s":46.57,"lo":559,"hi":1222,"n":8,"rr":563,"mr":889},{"m":"codestral-2501","r":917,"s":46.48,"lo":778,"hi":1205,"n":4,"rr":1572,"mr":984},{"m":"motif-2-12.7b-base","r":918,"s":46.38,"lo":829,"hi":1036,"n":22,"rr":475,"mr":883},{"m":"starchat2-15b-v0.1","r":919,"s":46.35,"lo":882,"hi":954,"n":6,"rr":357,"mr":938},{"m":"youtu-vl-4b-instruct","r":920,"s":46.34,"lo":838,"hi":991,"n":8,"rr":605,"mr":891},{"m":"llm-jp-4-vl-9b","r":921,"s":46.27,"lo":785,"hi":1114,"n":4,"rr":1140,"mr":927},{"m":"deepseek-coder-33b","r":922,"s":46.23,"lo":813,"hi":1050,"n":5,"rr":906,"mr":987},{"m":"wavecoder-ultra-6.7b","r":923,"s":46.22,"lo":879,"hi":946,"n":5,"rr":405,"mr":943},{"m":"openreasoning-nemotron-1.5b","r":924,"s":46.18,"lo":750,"hi":1134,"n":8,"rr":1414,"mr":896},{"m":"deepseek-r1-distill-qwen-7b","r":925,"s":46.15,"lo":726,"hi":1256,"n":19,"rr":1221,"mr":910},{"m":"qwen2-72b","r":926,"s":46.15,"lo":814,"hi":1000,"n":22,"rr":329,"mr":882},{"m":"glm-4.5-air-base","r":927,"s":46.15,"lo":799,"hi":1019,"n":23,"rr":480,"mr":879},{"m":"ministral-3-8b-base","r":928,"s":46.14,"lo":881,"hi":1009,"n":6,"rr":470,"mr":919},{"m":"internlm2_5-20b-chat","r":929,"s":45.94,"lo":857,"hi":1004,"n":14,"rr":362,"mr":897},{"m":"gemma-2-27b-it","r":930,"s":45.93,"lo":857,"hi":978,"n":30,"rr":933,"mr":893},{"m":"hyperclovax-seed-omni-8b","r":931,"s":45.9,"lo":747,"hi":1086,"n":5,"rr":826,"mr":924},{"m":"kimi-linear-base","r":932,"s":45.68,"lo":878,"hi":971,"n":14,"rr":787,"mr":900},{"m":"ling-2.5-mini-base","r":933,"s":45.61,"lo":870,"hi":982,"n":14,"rr":988,"mr":911},{"m":"smollm3-3b","r":934,"s":45.59,"lo":863,"hi":1010,"n":37,"rr":1088,"mr":890},{"m":"qwen2.5-coder-32b","r":935,"s":45.49,"lo":857,"hi":1029,"n":16,"rr":402,"mr":915},{"m":"codestral-22b","r":936,"s":45.48,"lo":847,"hi":1070,"n":11,"rr":1141,"mr":993},{"m":"lfm2.5-vl-3b","r":937,"s":45.37,"lo":740,"hi":1088,"n":3,"rr":1038,"mr":975},{"m":"whiterabbitneo-33b-v1","r":938,"s":45.36,"lo":847,"hi":996,"n":5,"rr":426,"mr":963},{"m":"phi-3-small-8k-instruct","r":939,"s":45.35,"lo":833,"hi":1098,"n":5,"rr":124,"mr":952},{"m":"falcon-h1-7b","r":940,"s":45.24,"lo":865,"hi":1043,"n":20,"rr":1018,"mr":903},{"m":"qwen2-math-1.5b-instruct","r":941,"s":45.14,"lo":870,"hi":1069,"n":6,"rr":811,"mr":989},{"m":"plamo-3.0-prime","r":942,"s":45.13,"lo":769,"hi":1041,"n":5,"rr":1469,"mr":906},{"m":"athene-70b","r":943,"s":45.1,"lo":881,"hi":973,"n":3,"rr":870,"mr":982},{"m":"amazon-nova-lite-v1.0","r":944,"s":45.09,"lo":842,"hi":1053,"n":5,"rr":1503,"mr":917},{"m":"yi-large","r":945,"s":45.03,"lo":824,"hi":1051,"n":4,"rr":890,"mr":968},{"m":"nezha-plus","r":946,"s":45,"lo":785,"hi":1059,"n":3,"rr":13,"mr":997},{"m":"llama-3.1-tulu-3-8b","r":947,"s":44.95,"lo":832,"hi":1052,"n":11,"rr":754,"mr":971},{"m":"mixtral-8x22b-instruct-v0.1","r":948,"s":44.88,"lo":887,"hi":1004,"n":30,"rr":589,"mr":908},{"m":"aquif-3.5-nano-1b","r":949,"s":44.86,"lo":917,"hi":993,"n":3,"rr":1320,"mr":909},{"m":"databricks-dbrx-instruct","r":950,"s":44.81,"lo":899,"hi":996,"n":6,"rr":477,"mr":980},{"m":"glm-4-0116","r":951,"s":44.72,"lo":799,"hi":1029,"n":6,"rr":533,"mr":956},{"m":"qwen3-8b-nothinking-2504","r":952,"s":44.58,"lo":887,"hi":1065,"n":3,"rr":1550,"mr":957},{"m":"select-step-by-step","r":953,"s":44.53,"lo":819,"hi":1545,"n":3,"rr":418,"mr":1100},{"m":"intern-decision-4b","r":954,"s":44.47,"lo":863,"hi":1088,"n":8,"rr":512,"mr":942},{"m":"deepseek-r1-distill-llama-8b","r":955,"s":44.43,"lo":776,"hi":1155,"n":21,"rr":947,"mr":905},{"m":"qwen1.5-110b-chat","r":956,"s":44.39,"lo":893,"hi":1035,"n":15,"rr":766,"mr":918},{"m":"speechless-coder-ds-6.7b","r":957,"s":44.32,"lo":895,"hi":1001,"n":5,"rr":492,"mr":992},{"m":"gpt-3.5-may-2023","r":958,"s":44.28,"lo":914,"hi":990,"n":3,"rr":490,"mr":1011},{"m":"mistral-small-3-24b-base","r":959,"s":44.27,"lo":838,"hi":1046,"n":4,"rr":251,"mr":959},{"m":"claude-3-haiku-20240307","r":960,"s":44.14,"lo":913,"hi":1020,"n":13,"rr":1017,"mr":966},{"m":"kanana-2-30b-a3b-base","r":961,"s":44.1,"lo":879,"hi":1025,"n":12,"rr":280,"mr":946},{"m":"kanana-2-30b-a3b-mid-2601","r":962,"s":44.1,"lo":880,"hi":1026,"n":12,"rr":281,"mr":947},{"m":"hermes-4.3-36b-pyche","r":963,"s":44.08,"lo":452,"hi":1170,"n":3,"rr":968,"mr":1046},{"m":"internlm2.5-7b-chat","r":964,"s":44.07,"lo":907,"hi":1023,"n":14,"rr":429,"mr":936},{"m":"wizardcoder-python-34b-v1.0","r":965,"s":44.05,"lo":913,"hi":1013,"n":5,"rr":516,"mr":998},{"m":"diffucoder-7b-instruct","r":966,"s":44.04,"lo":901,"hi":1011,"n":4,"rr":499,"mr":999},{"m":"apertus-v1.5-70b-thinking","r":967,"s":44.02,"lo":926,"hi":1034,"n":6,"rr":877,"mr":951},{"m":"granite-3.2-8b-instruct","r":968,"s":44.01,"lo":754,"hi":1118,"n":12,"rr":629,"mr":976},{"m":"vllm-sr-d3-nano","r":969,"s":43.99,"lo":783,"hi":1085,"n":8,"rr":445,"mr":953},{"m":"granite-3.3-8b-instruct","r":970,"s":43.99,"lo":882,"hi":1097,"n":21,"rr":1016,"mr":948},{"m":"telechat2-7b","r":971,"s":43.98,"lo":830,"hi":1132,"n":8,"rr":205,"mr":986},{"m":"qwen2.5-coder-7b-instruct","r":972,"s":43.98,"lo":883,"hi":1083,"n":26,"rr":1269,"mr":949},{"m":"internvl2.5-26b","r":973,"s":43.9,"lo":856,"hi":1069,"n":14,"rr":397,"mr":941},{"m":"qwen3-1.7b","r":974,"s":43.89,"lo":883,"hi":1091,"n":49,"rr":1109,"mr":928},{"m":"baichuan-3","r":975,"s":43.88,"lo":853,"hi":1036,"n":6,"rr":317,"mr":972},{"m":"apertus-v1.5-8b-thinking","r":976,"s":43.87,"lo":872,"hi":1023,"n":6,"rr":845,"mr":954},{"m":"deepseek-math-7b-rl","r":977,"s":43.87,"lo":873,"hi":1026,"n":5,"rr":763,"mr":1007},{"m":"claude-3-haiku","r":978,"s":43.76,"lo":889,"hi":1046,"n":6,"rr":735,"mr":1004},{"m":"qwen1.5-72b-chat","r":979,"s":43.67,"lo":920,"hi":1028,"n":33,"rr":623,"mr":944},{"m":"reka-core-20240501","r":980,"s":43.66,"lo":886,"hi":1026,"n":3,"rr":912,"mr":1038},{"m":"llama-3.1-tulu-3-8b-dpo","r":981,"s":43.64,"lo":856,"hi":1075,"n":11,"rr":773,"mr":981},{"m":"internlm2.5-20b","r":982,"s":43.59,"lo":862,"hi":1041,"n":6,"rr":647,"mr":1013},{"m":"magicoder-s-cl-7b","r":983,"s":43.57,"lo":943,"hi":1011,"n":5,"rr":555,"mr":1010},{"m":"d1-3b","r":984,"s":43.56,"lo":817,"hi":1094,"n":10,"rr":349,"mr":965},{"m":"qwen3-8b-base","r":985,"s":43.54,"lo":930,"hi":1037,"n":26,"rr":559,"mr":940},{"m":"qwen2-57b-a14b-instruct","r":986,"s":43.5,"lo":912,"hi":1061,"n":17,"rr":835,"mr":960},{"m":"yi-1.5-34b-chat","r":987,"s":43.48,"lo":926,"hi":1021,"n":12,"rr":813,"mr":961},{"m":"qwen2.5-7b","r":988,"s":43.45,"lo":941,"hi":1030,"n":34,"rr":715,"mr":932},{"m":"hy-1.8b-2bit","r":989,"s":43.38,"lo":625,"hi":1316,"n":8,"rr":740,"mr":977},{"m":"codestral-mamba","r":990,"s":43.37,"lo":926,"hi":1046,"n":3,"rr":548,"mr":1066},{"m":"xverse-moe-a36b","r":991,"s":43.36,"lo":822,"hi":1147,"n":8,"rr":309,"mr":1012},{"m":"lfm2-24b-a2b","r":992,"s":43.32,"lo":839,"hi":1116,"n":14,"rr":858,"mr":955},{"m":"gemma-3-12b-base","r":993,"s":43.29,"lo":839,"hi":1056,"n":6,"rr":538,"mr":1015},{"m":"qwen2.5-14b","r":994,"s":43.26,"lo":887,"hi":1095,"n":17,"rr":553,"mr":937},{"m":"lfm2.5-1.2b-thinking","r":995,"s":43.2,"lo":844,"hi":1118,"n":16,"rr":1327,"mr":945},{"m":"mistral-large-2402","r":996,"s":43.09,"lo":899,"hi":1051,"n":6,"rr":498,"mr":1022},{"m":"granite-4.1-3b","r":997,"s":43.07,"lo":926,"hi":1073,"n":21,"rr":898,"mr":962},{"m":"mistral-large","r":998,"s":43.07,"lo":928,"hi":1055,"n":5,"rr":812,"mr":1020},{"m":"hy-1.8b-int4gptq","r":999,"s":43.04,"lo":737,"hi":1270,"n":8,"rr":734,"mr":974},{"m":"internlm2-math-plus-20b","r":1000,"s":42.9,"lo":932,"hi":1097,"n":7,"rr":1033,"mr":1036},{"m":"solar-pro-preview","r":1001,"s":42.83,"lo":887,"hi":1141,"n":11,"rr":514,"mr":1019},{"m":"marco-nano-instruct","r":1002,"s":42.78,"lo":844,"hi":1135,"n":14,"rr":872,"mr":979},{"m":"aquif-3.5-2.7b","r":1003,"s":42.77,"lo":844,"hi":1072,"n":4,"rr":1160,"mr":969},{"m":"olmo-hybrid-instruct-7b-sft","r":1004,"s":42.72,"lo":918,"hi":1112,"n":13,"rr":1405,"mr":985},{"m":"qwen2.5-omni-7b","r":1005,"s":42.69,"lo":916,"hi":1122,"n":6,"rr":966,"mr":990},{"m":"qwen3-1.7b-thinking","r":1006,"s":42.68,"lo":937,"hi":1072,"n":21,"rr":1278,"mr":967},{"m":"qwen2.5-coder-14b","r":1007,"s":42.66,"lo":925,"hi":1073,"n":16,"rr":526,"mr":983},{"m":"phi-4-mini","r":1008,"s":42.58,"lo":910,"hi":1133,"n":5,"rr":639,"mr":1002},{"m":"openchat-3.5-7b-0106","r":1009,"s":42.54,"lo":951,"hi":1060,"n":5,"rr":653,"mr":1034},{"m":"opencoder-8b-base","r":1010,"s":42.52,"lo":814,"hi":1143,"n":4,"rr":757,"mr":1061},{"m":"glm4-9b","r":1011,"s":42.52,"lo":921,"hi":1056,"n":15,"rr":454,"mr":1001},{"m":"ernie-4.5-21b-a3b-pt","r":1012,"s":42.5,"lo":721,"hi":1154,"n":3,"rr":1519,"mr":1016},{"m":"falcon-h1-3b","r":1013,"s":42.41,"lo":951,"hi":1108,"n":19,"rr":1120,"mr":958},{"m":"qwen3-6b","r":1014,"s":42.39,"lo":932,"hi":1160,"n":3,"rr":1177,"mr":1027},{"m":"qwen3.5-9b-base","r":1015,"s":42.36,"lo":837,"hi":1089,"n":17,"rr":894,"mr":995},{"m":"apertus-v1.5-70b","r":1016,"s":42.33,"lo":934,"hi":1067,"n":18,"rr":692,"mr":978},{"m":"qwen3-4b-saferl","r":1017,"s":42.16,"lo":889,"hi":1306,"n":3,"rr":1573,"mr":1051},{"m":"kanana-1.5-32.5b-base","r":1018,"s":42.09,"lo":919,"hi":1105,"n":12,"rr":368,"mr":994},{"m":"codellama-70b-instruct","r":1019,"s":42.05,"lo":898,"hi":1096,"n":8,"rr":953,"mr":1035},{"m":"pai-albert","r":1020,"s":42.04,"lo":798,"hi":1132,"n":3,"rr":16,"mr":1102},{"m":"yi-34b-chat-8bits","r":1021,"s":41.96,"lo":839,"hi":1111,"n":6,"rr":262,"mr":1048},{"m":"deepseek-v2","r":1022,"s":41.93,"lo":905,"hi":1115,"n":29,"rr":564,"mr":996},{"m":"hermes-4.3-36b","r":1023,"s":41.88,"lo":516,"hi":1197,"n":3,"rr":1101,"mr":1090},{"m":"phind-codellama-34b-v2","r":1024,"s":41.84,"lo":954,"hi":1082,"n":5,"rr":829,"mr":1054},{"m":"falcon-h1-1.5b-deep","r":1025,"s":41.83,"lo":964,"hi":1124,"n":19,"rr":1062,"mr":970},{"m":"speechless-starcoder2-15b","r":1026,"s":41.79,"lo":948,"hi":1062,"n":5,"rr":626,"mr":1044},{"m":"glm-4-9b-chat","r":1027,"s":41.76,"lo":989,"hi":1050,"n":17,"rr":643,"mr":1006},{"m":"hrm-text-1b","r":1028,"s":41.46,"lo":916,"hi":1164,"n":8,"rr":277,"mr":1024},{"m":"qwen3.5-4b-base","r":1029,"s":41.41,"lo":933,"hi":1105,"n":28,"rr":513,"mr":1008},{"m":"qwen3.5-2b","r":1030,"s":41.4,"lo":905,"hi":1114,"n":51,"rr":1328,"mr":964},{"m":"roberta-icets","r":1031,"s":41.35,"lo":789,"hi":1151,"n":3,"rr":17,"mr":1065},{"m":"qwen1.5-110b","r":1032,"s":41.32,"lo":917,"hi":1112,"n":16,"rr":546,"mr":1003},{"m":"gemma-2-9b-it","r":1033,"s":41.29,"lo":985,"hi":1071,"n":29,"rr":1142,"mr":1009},{"m":"bitcpm-cann-8b","r":1034,"s":41.23,"lo":968,"hi":1099,"n":11,"rr":137,"mr":1026},{"m":"gpt-3.5-turbo-0613","r":1035,"s":41.23,"lo":932,"hi":1101,"n":4,"rr":1096,"mr":1138},{"m":"llama-3-70b-base","r":1036,"s":41.11,"lo":917,"hi":1128,"n":35,"rr":515,"mr":1000},{"m":"olmo-3-32b","r":1037,"s":41.06,"lo":875,"hi":1121,"n":11,"rr":250,"mr":1023},{"m":"kanana-2-30b-a3b-base-2601","r":1038,"s":41.05,"lo":939,"hi":1102,"n":12,"rr":380,"mr":1021},{"m":"llama-3.1-70b-base","r":1039,"s":41.01,"lo":885,"hi":1124,"n":13,"rr":167,"mr":1049},{"m":"qwen2-7b-instruct","r":1040,"s":40.97,"lo":981,"hi":1084,"n":27,"rr":1065,"mr":1017},{"m":"deepseek-coder-v2-base","r":1041,"s":40.93,"lo":878,"hi":1179,"n":13,"rr":601,"mr":1052},{"m":"qwen2-math-7b","r":1042,"s":40.87,"lo":985,"hi":1072,"n":4,"rr":431,"mr":1092},{"m":"internlm2-math-plus-7b","r":1043,"s":40.85,"lo":974,"hi":1142,"n":7,"rr":1119,"mr":1079},{"m":"plamo-2.2-prime","r":1044,"s":40.77,"lo":812,"hi":1129,"n":5,"rr":1512,"mr":1063},{"m":"roberta-mtl-adv","r":1045,"s":40.69,"lo":817,"hi":1152,"n":3,"rr":21,"mr":1119},{"m":"internvl2.5-8b","r":1046,"s":40.69,"lo":932,"hi":1137,"n":14,"rr":550,"mr":1032},{"m":"roberta-ensemble","r":1047,"s":40.68,"lo":800,"hi":1163,"n":3,"rr":19,"mr":1120},{"m":"yi-34b-chat","r":1048,"s":40.54,"lo":879,"hi":1146,"n":8,"rr":408,"mr":1099},{"m":"lfm2-8b-a1b","r":1049,"s":40.52,"lo":955,"hi":1142,"n":26,"rr":1217,"mr":1005},{"m":"granite-4.0-h-micro","r":1050,"s":40.5,"lo":939,"hi":1148,"n":20,"rr":939,"mr":1028},{"m":"yi-34b-chat-4bits","r":1051,"s":40.48,"lo":869,"hi":1141,"n":6,"rr":318,"mr":1085},{"m":"internvl3.5-8b","r":1052,"s":40.45,"lo":817,"hi":1295,"n":5,"rr":1079,"mr":1068},{"m":"minicpm3-4b","r":1053,"s":40.38,"lo":1019,"hi":1089,"n":17,"rr":1042,"mr":1018},{"m":"ministral-3-3b-base","r":1054,"s":40.24,"lo":967,"hi":1195,"n":7,"rr":927,"mr":1057},{"m":"olmo-3-7b-sft","r":1055,"s":40.2,"lo":970,"hi":1230,"n":17,"rr":1451,"mr":1039},{"m":"gemma-3-4b-it","r":1056,"s":40.17,"lo":963,"hi":1159,"n":41,"rr":1192,"mr":1014},{"m":"mixtral-8x22b","r":1057,"s":40.17,"lo":971,"hi":1151,"n":34,"rr":634,"mr":1025},{"m":"mobilellm-r1-950m","r":1058,"s":40.16,"lo":876,"hi":1173,"n":6,"rr":1197,"mr":1031},{"m":"falcon3-10b","r":1059,"s":40.14,"lo":1010,"hi":1129,"n":18,"rr":1061,"mr":1030},{"m":"deepseek-math-7b-instruct","r":1060,"s":40.14,"lo":992,"hi":1160,"n":4,"rr":769,"mr":1088},{"m":"mathstral-7b","r":1061,"s":40.13,"lo":995,"hi":1115,"n":8,"rr":1228,"mr":1082},{"m":"kanana-2-3b-instruct","r":1062,"s":40.1,"lo":889,"hi":1099,"n":6,"rr":825,"mr":1045},{"m":"fanar-1-9b-instruct","r":1063,"s":39.95,"lo":960,"hi":1493,"n":5,"rr":1343,"mr":1096},{"m":"granite-4.0-micro","r":1064,"s":39.87,"lo":970,"hi":1146,"n":22,"rr":998,"mr":1033},{"m":"claude-2","r":1065,"s":39.81,"lo":987,"hi":1147,"n":5,"rr":686,"mr":1132},{"m":"qwen-2.5-3b-instruct","r":1066,"s":39.66,"lo":966,"hi":1175,"n":13,"rr":1314,"mr":1058},{"m":"numinamath-7b-cot","r":1067,"s":39.64,"lo":1017,"hi":1138,"n":5,"rr":956,"mr":1111},{"m":"marin-32b-base","r":1068,"s":39.63,"lo":867,"hi":1208,"n":4,"rr":123,"mr":1133},{"m":"lfm2.5-350m","r":1069,"s":39.61,"lo":875,"hi":1286,"n":8,"rr":1480,"mr":1042},{"m":"exaone-3.5-7.8b-instruct","r":1070,"s":39.61,"lo":937,"hi":1197,"n":8,"rr":803,"mr":1074},{"m":"granite-4.0-h-tiny","r":1071,"s":39.6,"lo":1004,"hi":1138,"n":35,"rr":1204,"mr":1029},{"m":"deepseek-coder-v2-lite-instruct","r":1072,"s":39.53,"lo":973,"hi":1167,"n":35,"rr":1224,"mr":1041},{"m":"roberta","r":1073,"s":39.49,"lo":837,"hi":1177,"n":3,"rr":25,"mr":1142},{"m":"kanana-2-1.3b-instruct","r":1074,"s":39.27,"lo":922,"hi":1116,"n":6,"rr":861,"mr":1062},{"m":"gemma-3-12b","r":1075,"s":39.24,"lo":894,"hi":1188,"n":24,"rr":798,"mr":1037},{"m":"olmo-2-0325-32b-instruct","r":1076,"s":39.24,"lo":937,"hi":1171,"n":14,"rr":1370,"mr":1070},{"m":"palm-cont-62b","r":1077,"s":39.23,"lo":942,"hi":1115,"n":4,"rr":77,"mr":1156},{"m":"phi-3-medium-4k-instruct","r":1078,"s":39.18,"lo":937,"hi":1185,"n":15,"rr":746,"mr":1072},{"m":"code-290k-6.7b-instruct","r":1079,"s":39.12,"lo":1002,"hi":1104,"n":3,"rr":821,"mr":1117},{"m":"qwen2.5-coder-7b","r":1080,"s":39.12,"lo":1012,"hi":1161,"n":17,"rr":745,"mr":1059},{"m":"lfm2.5-1.2b-instruct","r":1081,"s":39.12,"lo":899,"hi":1163,"n":9,"rr":1074,"mr":1047},{"m":"mistral-nemo-instruct-2407","r":1082,"s":39.1,"lo":1028,"hi":1125,"n":10,"rr":1299,"mr":1109},{"m":"gemini-pro","r":1083,"s":39.09,"lo":905,"hi":1192,"n":3,"rr":685,"mr":1114},{"m":"deepseek-llm-67b-chat","r":1084,"s":39.09,"lo":1016,"hi":1156,"n":26,"rr":635,"mr":1040},{"m":"gemini-1.0-pro","r":1085,"s":38.97,"lo":979,"hi":1142,"n":5,"rr":775,"mr":1108},{"m":"qwen2.5-coder-3b-instruct","r":1086,"s":38.96,"lo":972,"hi":1232,"n":16,"rr":1168,"mr":1055},{"m":"ministral-8b-instruct","r":1087,"s":38.95,"lo":737,"hi":1190,"n":11,"rr":929,"mr":1081},{"m":"bielik-11b-v3.0-instruct","r":1088,"s":38.92,"lo":952,"hi":1278,"n":6,"rr":323,"mr":1093},{"m":"phi-3-mini-4k-instruct","r":1089,"s":38.92,"lo":1047,"hi":1122,"n":12,"rr":859,"mr":1069},{"m":"qwen1.5-72b","r":1090,"s":38.9,"lo":983,"hi":1175,"n":28,"rr":696,"mr":1043},{"m":"starcoder2-15b-instruct-v0.1","r":1091,"s":38.81,"lo":952,"hi":1161,"n":8,"rr":1072,"mr":1098},{"m":"aquif-3-3.2b","r":1092,"s":38.79,"lo":843,"hi":1134,"n":4,"rr":1232,"mr":1056},{"m":"gpt-3.5-turbo-0125","r":1093,"s":38.77,"lo":1040,"hi":1141,"n":14,"rr":1060,"mr":1083},{"m":"dolphin-2.6-mixtral-8x7b","r":1094,"s":38.68,"lo":1016,"hi":1125,"n":5,"rr":805,"mr":1110},{"m":"glm-4-9b-chat-1m","r":1095,"s":38.67,"lo":967,"hi":1135,"n":15,"rr":618,"mr":1094},{"m":"yuan2.0-102b","r":1096,"s":38.62,"lo":849,"hi":1126,"n":3,"rr":558,"mr":1139},{"m":"lfm2-2.6b","r":1097,"s":38.51,"lo":1051,"hi":1133,"n":14,"rr":1145,"mr":1050},{"m":"yi-1.5-9b-chat","r":1098,"s":38.5,"lo":1028,"hi":1166,"n":15,"rr":1000,"mr":1060},{"m":"command-r-plus","r":1099,"s":38.44,"lo":1045,"hi":1138,"n":16,"rr":1028,"mr":1086},{"m":"gemma-2-27b","r":1100,"s":38.41,"lo":1017,"hi":1163,"n":24,"rr":1048,"mr":1053},{"m":"granite-3.1-8b-instruct","r":1101,"s":38.41,"lo":962,"hi":1171,"n":13,"rr":899,"mr":1095},{"m":"qwen2.5-vl-7b","r":1102,"s":38.4,"lo":1015,"hi":1153,"n":6,"rr":1316,"mr":1129},{"m":"qwen2.5-math-1.5b","r":1103,"s":38.39,"lo":1009,"hi":1176,"n":4,"rr":656,"mr":1134},{"m":"ministral-8b","r":1104,"s":38.3,"lo":951,"hi":1277,"n":4,"rr":996,"mr":1153},{"m":"alodlm-1.7b","r":1105,"s":38.28,"lo":1028,"hi":1173,"n":11,"rr":640,"mr":1067},{"m":"bielik-11b-v2.5-instruct","r":1106,"s":38.26,"lo":958,"hi":1311,"n":6,"rr":363,"mr":1140},{"m":"openpangu-7b-diffusion-base","r":1107,"s":38.2,"lo":969,"hi":1179,"n":9,"rr":654,"mr":1073},{"m":"qwen1.5-32b-chat","r":1108,"s":38.17,"lo":1047,"hi":1139,"n":21,"rr":879,"mr":1064},{"m":"aya-expanse-32b","r":1109,"s":38.1,"lo":1026,"hi":1192,"n":3,"rr":1490,"mr":1151},{"m":"ouro-1.4b","r":1110,"s":38.09,"lo":969,"hi":1236,"n":15,"rr":613,"mr":1071},{"m":"internvl2-8b","r":1111,"s":38.01,"lo":964,"hi":1200,"n":15,"rr":620,"mr":1078},{"m":"qwen-72b-chat","r":1112,"s":37.93,"lo":885,"hi":1202,"n":5,"rr":714,"mr":1155},{"m":"gpt-3.5-turbo","r":1113,"s":37.89,"lo":988,"hi":1238,"n":14,"rr":847,"mr":1124},{"m":"olmo-2-32b-base","r":1114,"s":37.88,"lo":950,"hi":1214,"n":22,"rr":494,"mr":1076},{"m":"qwen2.57b-a14b","r":1115,"s":37.77,"lo":1028,"hi":1160,"n":20,"rr":705,"mr":1077},{"m":"mimo-7b-base","r":1116,"s":37.72,"lo":1024,"hi":1172,"n":17,"rr":577,"mr":1107},{"m":"phi-3.5-mini-instruct","r":1117,"s":37.67,"lo":1061,"hi":1172,"n":21,"rr":1138,"mr":1080},{"m":"yi-1.5-34b","r":1118,"s":37.64,"lo":987,"hi":1185,"n":20,"rr":760,"mr":1075},{"m":"llama3.0-70b","r":1119,"s":37.62,"lo":928,"hi":1247,"n":13,"rr":674,"mr":1104},{"m":"apertus-v1.5-8b","r":1120,"s":37.51,"lo":1034,"hi":1171,"n":18,"rr":915,"mr":1087},{"m":"granite-3.3-2b-instruct","r":1121,"s":37.35,"lo":939,"hi":1244,"n":13,"rr":952,"mr":1106},{"m":"trinity-large-truebase","r":1122,"s":37.29,"lo":994,"hi":1189,"n":12,"rr":572,"mr":1091},{"m":"falcon3-7b","r":1123,"s":37.26,"lo":1065,"hi":1186,"n":18,"rr":1132,"mr":1089},{"m":"llama-3.1-8b-instruct","r":1124,"s":37.2,"lo":1068,"hi":1170,"n":53,"rr":1279,"mr":1097},{"m":"reka-flash-21b-20240226","r":1125,"s":37.14,"lo":1084,"hi":1163,"n":3,"rr":1231,"mr":1157},{"m":"codeqwen1.5-7b-chat","r":1126,"s":37.08,"lo":859,"hi":1276,"n":10,"rr":1219,"mr":1148},{"m":"bielik-11b-v2.6-instruct","r":1127,"s":37,"lo":997,"hi":1304,"n":6,"rr":379,"mr":1162},{"m":"llama-3.1-tulu-3-8b-sft","r":1128,"s":36.83,"lo":855,"hi":1212,"n":11,"rr":970,"mr":1125},{"m":"moonlight-base","r":1129,"s":36.77,"lo":1076,"hi":1185,"n":28,"rr":958,"mr":1103},{"m":"gemini-1.5-flash-8b-001","r":1130,"s":36.76,"lo":900,"hi":1246,"n":3,"rr":1159,"mr":1216},{"m":"codestral-12b-instruct","r":1131,"s":36.75,"lo":910,"hi":1340,"n":5,"rr":1411,"mr":1170},{"m":"instella-moe-16b-a3b-base","r":1132,"s":36.74,"lo":1061,"hi":1172,"n":16,"rr":100,"mr":1116},{"m":"eurollm-22b","r":1133,"s":36.58,"lo":1048,"hi":1211,"n":22,"rr":946,"mr":1101},{"m":"moonlight-instruct","r":1134,"s":36.57,"lo":1042,"hi":1200,"n":14,"rr":1256,"mr":1105},{"m":"falcon-h1-1.5b","r":1135,"s":36.47,"lo":1063,"hi":1251,"n":18,"rr":1227,"mr":1084},{"m":"gemma-3-27b-vl","r":1136,"s":36.45,"lo":26,"hi":1429,"n":4,"rr":1574,"mr":1202},{"m":"internlm2.5-7b","r":1137,"s":36.39,"lo":979,"hi":1187,"n":6,"rr":867,"mr":1163},{"m":"deepseek-coder-7b-instruct-v1.5","r":1138,"s":36.32,"lo":1003,"hi":1320,"n":12,"rr":768,"mr":1118},{"m":"granite-4.0-tiny-preview","r":1139,"s":36.31,"lo":915,"hi":1260,"n":12,"rr":982,"mr":1123},{"m":"qwen2.5-coder-1.5b-instruct","r":1140,"s":36.26,"lo":1023,"hi":1288,"n":7,"rr":1194,"mr":1169},{"m":"codegemma-1.1-7b","r":1141,"s":36.18,"lo":1027,"hi":1211,"n":3,"rr":937,"mr":1185},{"m":"codegemma-7b-it","r":1142,"s":36.17,"lo":1052,"hi":1185,"n":5,"rr":941,"mr":1158},{"m":"qwen2-7b","r":1143,"s":36.06,"lo":1091,"hi":1202,"n":22,"rr":836,"mr":1115},{"m":"jamba-1.5-mini","r":1144,"s":35.93,"lo":982,"hi":1475,"n":3,"rr":720,"mr":1180},{"m":"gpt-3.5","r":1145,"s":35.89,"lo":1063,"hi":1206,"n":11,"rr":575,"mr":1145},{"m":"nemotron-nano-12b-v2-base","r":1146,"s":35.86,"lo":982,"hi":1287,"n":17,"rr":433,"mr":1130},{"m":"internlm2-chat-20b","r":1147,"s":35.84,"lo":1078,"hi":1189,"n":18,"rr":902,"mr":1112},{"m":"exaone-3.5-2.4b-instruct","r":1148,"s":35.82,"lo":1054,"hi":1286,"n":8,"rr":1040,"mr":1164},{"m":"command-r-plus-08-2024","r":1149,"s":35.79,"lo":840,"hi":1220,"n":5,"rr":119,"mr":1188},{"m":"step-audio-2-mini","r":1150,"s":35.74,"lo":1082,"hi":1190,"n":4,"rr":1077,"mr":1143},{"m":"olmo-hybrid-7b","r":1151,"s":35.72,"lo":1061,"hi":1222,"n":17,"rr":648,"mr":1135},{"m":"llama-3.1-8b","r":1152,"s":35.7,"lo":1061,"hi":1247,"n":24,"rr":1083,"mr":1126},{"m":"jamba-mini-1.6","r":1153,"s":35.69,"lo":930,"hi":1350,"n":6,"rr":1339,"mr":1186},{"m":"internvl2-26b","r":1154,"s":35.64,"lo":1070,"hi":1236,"n":14,"rr":781,"mr":1121},{"m":"gpt-2","r":1155,"s":35.6,"lo":1028,"hi":1291,"n":3,"rr":1187,"mr":1200},{"m":"fast-dllm-v2-7b","r":1156,"s":35.52,"lo":1045,"hi":1264,"n":11,"rr":921,"mr":1127},{"m":"qwen2-math-1.5b","r":1157,"s":35.48,"lo":1079,"hi":1234,"n":4,"rr":816,"mr":1184},{"m":"midm-2.0-mini-instruct","r":1158,"s":35.42,"lo":1043,"hi":1327,"n":7,"rr":995,"mr":1128},{"m":"ailabs-team-transformers","r":1159,"s":35.27,"lo":811,"hi":1264,"n":3,"rr":37,"mr":1219},{"m":"deepseek-instruct-33b","r":1160,"s":35.25,"lo":1027,"hi":1254,"n":4,"rr":1210,"mr":1212},{"m":"skywork-moe-base","r":1161,"s":35.23,"lo":886,"hi":1257,"n":6,"rr":660,"mr":1187},{"m":"qwen2.5-3b","r":1162,"s":35.19,"lo":1114,"hi":1240,"n":27,"rr":1123,"mr":1113},{"m":"deepseek-coder-6.7b-instruct","r":1163,"s":35.19,"lo":972,"hi":1293,"n":19,"rr":1303,"mr":1136},{"m":"baichuan-omni","r":1164,"s":35.14,"lo":997,"hi":1239,"n":4,"rr":727,"mr":1226},{"m":"ipet-albert-few-shot-32-examples","r":1165,"s":34.98,"lo":1039,"hi":1249,"n":3,"rr":59,"mr":1223},{"m":"qwen1.5-32b","r":1166,"s":34.98,"lo":1067,"hi":1219,"n":21,"rr":824,"mr":1122},{"m":"bielik-11b-v2.3-instruct","r":1167,"s":34.92,"lo":1041,"hi":1344,"n":6,"rr":442,"mr":1198},{"m":"speechless-starcoder2-7b","r":1168,"s":34.86,"lo":1097,"hi":1203,"n":5,"rr":1005,"mr":1179},{"m":"dream-7b-base","r":1169,"s":34.84,"lo":1140,"hi":1205,"n":12,"rr":935,"mr":1141},{"m":"bielik-11b-v2.2-instruct","r":1170,"s":34.75,"lo":1045,"hi":1335,"n":6,"rr":439,"mr":1201},{"m":"trinity-mini-base","r":1171,"s":34.72,"lo":1048,"hi":1245,"n":12,"rr":610,"mr":1146},{"m":"apriel-5b-instruct","r":1172,"s":34.69,"lo":777,"hi":1236,"n":4,"rr":1329,"mr":1144},{"m":"chatglm3-6b-base","r":1173,"s":34.69,"lo":1088,"hi":1228,"n":19,"rr":713,"mr":1131},{"m":"command-r7b","r":1174,"s":34.6,"lo":1112,"hi":1403,"n":3,"rr":1587,"mr":1214},{"m":"qwen3-vl-2b-instruct","r":1175,"s":34.59,"lo":1061,"hi":1297,"n":19,"rr":1240,"mr":1137},{"m":"bielik-11b-v2.1-instruct","r":1176,"s":34.5,"lo":1052,"hi":1339,"n":6,"rr":440,"mr":1207},{"m":"internlm2-20b","r":1177,"s":34.47,"lo":1102,"hi":1221,"n":16,"rr":887,"mr":1147},{"m":"code-13b","r":1178,"s":34.4,"lo":1097,"hi":1200,"n":3,"rr":1111,"mr":1210},{"m":"rnd1-base-0910","r":1179,"s":34.38,"lo":1090,"hi":1336,"n":7,"rr":523,"mr":1166},{"m":"yi-6b-200k","r":1180,"s":34.32,"lo":909,"hi":1391,"n":4,"rr":719,"mr":1249},{"m":"wizardcoder-15b-v1.0","r":1181,"s":34.24,"lo":1125,"hi":1216,"n":5,"rr":1053,"mr":1191},{"m":"codellama-70b","r":1182,"s":34.14,"lo":1062,"hi":1289,"n":7,"rr":1284,"mr":1196},{"m":"metamath-70b","r":1183,"s":34.13,"lo":1010,"hi":1257,"n":3,"rr":873,"mr":1241},{"m":"command-r","r":1184,"s":34.11,"lo":1110,"hi":1316,"n":8,"rr":1420,"mr":1189},{"m":"bitcpm-cann-3b","r":1185,"s":34.11,"lo":1101,"hi":1273,"n":11,"rr":330,"mr":1167},{"m":"aya-expanse-8b","r":1186,"s":34.04,"lo":1094,"hi":1270,"n":3,"rr":1538,"mr":1229},{"m":"claude-instant-1-mar-2024","r":1187,"s":34,"lo":1112,"hi":1216,"n":3,"rr":1136,"mr":1215},{"m":"bort-alexa-ai","r":1188,"s":33.97,"lo":962,"hi":1279,"n":3,"rr":60,"mr":1192},{"m":"olmo-3-7b","r":1189,"s":33.95,"lo":1121,"hi":1221,"n":31,"rr":571,"mr":1160},{"m":"lfm2-vl-3b","r":1190,"s":33.91,"lo":977,"hi":1262,"n":3,"rr":1315,"mr":1213},{"m":"dream-7b-instruct","r":1191,"s":33.88,"lo":1141,"hi":1247,"n":18,"rr":916,"mr":1149},{"m":"gemma-3n-e2b-it","r":1192,"s":33.66,"lo":1104,"hi":1231,"n":7,"rr":1379,"mr":1195},{"m":"yi-1.5-6b-chat","r":1193,"s":33.59,"lo":1130,"hi":1255,"n":9,"rr":1222,"mr":1168},{"m":"deepseek-r1-distill-qwen-1.5b","r":1194,"s":33.58,"lo":1065,"hi":1330,"n":18,"rr":1361,"mr":1152},{"m":"speechless-coding-7b-16k-tora","r":1195,"s":33.56,"lo":1132,"hi":1227,"n":5,"rr":1093,"mr":1211},{"m":"internlm2-chat-20b-sft","r":1196,"s":33.48,"lo":1130,"hi":1253,"n":18,"rr":965,"mr":1159},{"m":"apertus-v1.5-70b-base","r":1197,"s":33.48,"lo":900,"hi":1357,"n":4,"rr":183,"mr":1231},{"m":"llama-3-8b-instruct","r":1198,"s":33.44,"lo":1144,"hi":1245,"n":36,"rr":1069,"mr":1154},{"m":"gemma-3-pt-27b","r":1199,"s":33.42,"lo":1095,"hi":1297,"n":20,"rr":671,"mr":1174},{"m":"yi-coder-1.5b-chat","r":1200,"s":33.4,"lo":1059,"hi":1452,"n":7,"rr":1366,"mr":1259},{"m":"ministral-3-3b-instruct","r":1201,"s":33.37,"lo":1031,"hi":1318,"n":20,"rr":1257,"mr":1150},{"m":"exaone-3.5-2.4b","r":1202,"s":33.35,"lo":996,"hi":1256,"n":4,"rr":1382,"mr":1217},{"m":"deepseek-llm-67b-base","r":1203,"s":33.32,"lo":1071,"hi":1294,"n":22,"rr":707,"mr":1165},{"m":"qwen3-4b-base","r":1204,"s":33.31,"lo":1089,"hi":1315,"n":10,"rr":733,"mr":1190},{"m":"deepseek-coder-1.3b-instruct","r":1205,"s":33.27,"lo":1103,"hi":1435,"n":8,"rr":1372,"mr":1209},{"m":"gemma-2-9b","r":1206,"s":33.09,"lo":1138,"hi":1259,"n":36,"rr":1071,"mr":1161},{"m":"code-33b","r":1207,"s":33.06,"lo":1131,"hi":1232,"n":3,"rr":1181,"mr":1237},{"m":"deepseek-math-7b","r":1208,"s":33.06,"lo":1135,"hi":1344,"n":15,"rr":990,"mr":1176},{"m":"ministral-8b-2410","r":1209,"s":32.8,"lo":1111,"hi":1285,"n":4,"rr":1514,"mr":1271},{"m":"llm-jp-4-vl-9b-beta","r":1210,"s":32.77,"lo":1063,"hi":1265,"n":4,"rr":1458,"mr":1194},{"m":"apertus-70b","r":1211,"s":32.77,"lo":1060,"hi":1300,"n":17,"rr":751,"mr":1171},{"m":"qwen3.5-2b-base","r":1212,"s":32.66,"lo":1047,"hi":1279,"n":16,"rr":201,"mr":1193},{"m":"coda-1.7b-instruct","r":1213,"s":32.63,"lo":1144,"hi":1270,"n":5,"rr":1115,"mr":1222},{"m":"yi-coder-9b","r":1214,"s":32.6,"lo":1081,"hi":1248,"n":5,"rr":1085,"mr":1234},{"m":"codellama-python-34b","r":1215,"s":32.6,"lo":1160,"hi":1233,"n":4,"rr":1166,"mr":1239},{"m":"apertus-70b-instruct","r":1216,"s":32.58,"lo":1134,"hi":1264,"n":29,"rr":1423,"mr":1172},{"m":"vllm-sr-d3-lite","r":1217,"s":32.56,"lo":1085,"hi":1289,"n":8,"rr":762,"mr":1178},{"m":"qwen-14b","r":1218,"s":32.51,"lo":1128,"hi":1298,"n":25,"rr":518,"mr":1173},{"m":"yi-1.5-9b","r":1219,"s":32.5,"lo":1068,"hi":1291,"n":11,"rr":1068,"mr":1182},{"m":"magpie-8b","r":1220,"s":32.49,"lo":911,"hi":1506,"n":10,"rr":1252,"mr":1250},{"m":"dbrx-instruct-preview","r":1221,"s":32.44,"lo":1080,"hi":1302,"n":8,"rr":830,"mr":1197},{"m":"tigerbot-70b-chat","r":1222,"s":32.38,"lo":1034,"hi":1382,"n":9,"rr":388,"mr":1281},{"m":"mixtral-8x7b","r":1223,"s":32.05,"lo":1135,"hi":1309,"n":29,"rr":1023,"mr":1177},{"m":"qwen2.5-1.5b-instruct","r":1224,"s":32.05,"lo":1157,"hi":1317,"n":18,"rr":1340,"mr":1183},{"m":"bielik-11b-v2.0-instruct","r":1225,"s":31.99,"lo":1114,"hi":1356,"n":6,"rr":521,"mr":1251},{"m":"bielik-11b-v3.0","r":1226,"s":31.98,"lo":1126,"hi":1323,"n":6,"rr":504,"mr":1221},{"m":"fsl-plus-plus-albert-few-shot-32-examples","r":1227,"s":31.9,"lo":1015,"hi":1292,"n":3,"rr":64,"mr":1312},{"m":"openchat-3.5-0106-gemma","r":1228,"s":31.89,"lo":1141,"hi":1288,"n":6,"rr":466,"mr":1242},{"m":"llama-3.1-8b-base","r":1229,"s":31.88,"lo":1155,"hi":1290,"n":35,"rr":1035,"mr":1175},{"m":"phi-2-2.7b","r":1230,"s":31.81,"lo":1105,"hi":1275,"n":4,"rr":1124,"mr":1247},{"m":"wizardmath-70b-v1.0","r":1231,"s":31.74,"lo":1021,"hi":1314,"n":3,"rr":1001,"mr":1301},{"m":"llama-3.1-3b","r":1232,"s":31.7,"lo":1097,"hi":1414,"n":6,"rr":1201,"mr":1294},{"m":"internlm2-math-plus-1.8b","r":1233,"s":31.65,"lo":734,"hi":1307,"n":3,"rr":1360,"mr":1289},{"m":"phi-4-mini-3.8b","r":1234,"s":31.58,"lo":1067,"hi":1276,"n":4,"rr":1400,"mr":1208},{"m":"marin-32b-mantis","r":1235,"s":31.57,"lo":1123,"hi":1336,"n":17,"rr":579,"mr":1203},{"m":"internlm2-7b","r":1236,"s":31.56,"lo":1143,"hi":1292,"n":16,"rr":994,"mr":1199},{"m":"llama-2-70b","r":1237,"s":31.52,"lo":1126,"hi":1335,"n":29,"rr":711,"mr":1181},{"m":"internlm2-math-base-20b","r":1238,"s":31.42,"lo":1188,"hi":1266,"n":5,"rr":1176,"mr":1269},{"m":"granite-3.2-2b-instruct","r":1239,"s":31.38,"lo":1066,"hi":1327,"n":12,"rr":1211,"mr":1233},{"m":"grok-1","r":1240,"s":31.34,"lo":1047,"hi":1311,"n":4,"rr":1041,"mr":1270},{"m":"qwen2.5-coder-3b","r":1241,"s":31.23,"lo":1192,"hi":1338,"n":16,"rr":1064,"mr":1220},{"m":"skywork-13b-math","r":1242,"s":31.22,"lo":1070,"hi":1353,"n":3,"rr":1049,"mr":1298},{"m":"openhermes-2.5-code-290k-13b","r":1243,"s":31.21,"lo":1192,"hi":1278,"n":5,"rr":1216,"mr":1260},{"m":"codellama-34b-instruct","r":1244,"s":31.13,"lo":1181,"hi":1286,"n":7,"rr":1375,"mr":1240},{"m":"granite-4.0-h-1b","r":1245,"s":31.13,"lo":1157,"hi":1300,"n":8,"rr":1323,"mr":1236},{"m":"llama-3.2-3b-instruct","r":1246,"s":31.09,"lo":1183,"hi":1305,"n":19,"rr":1464,"mr":1227},{"m":"minerva-540b","r":1247,"s":31.08,"lo":1056,"hi":1297,"n":3,"rr":1155,"mr":1252},{"m":"granite-4.0-1b","r":1248,"s":31.07,"lo":1171,"hi":1311,"n":9,"rr":1376,"mr":1204},{"m":"mixtral-8x7b-instruct-v0.1","r":1249,"s":31.06,"lo":1207,"hi":1280,"n":29,"rr":1215,"mr":1206},{"m":"marin-8b-base","r":1250,"s":30.92,"lo":1087,"hi":1375,"n":17,"rr":792,"mr":1245},{"m":"intern-decision-2b","r":1251,"s":30.86,"lo":1145,"hi":1361,"n":8,"rr":944,"mr":1218},{"m":"granite-3.1-2b-instruct","r":1252,"s":30.6,"lo":1124,"hi":1330,"n":13,"rr":1270,"mr":1243},{"m":"wizardcoder-python-7b-v1.0","r":1253,"s":30.57,"lo":1197,"hi":1289,"n":5,"rr":1223,"mr":1273},{"m":"deepseek-coder-v2-lite-base","r":1254,"s":30.43,"lo":1200,"hi":1324,"n":17,"rr":1039,"mr":1230},{"m":"xverse-65b","r":1255,"s":30.4,"lo":1049,"hi":1397,"n":8,"rr":663,"mr":1286},{"m":"xverse-65b-2","r":1256,"s":30.35,"lo":1055,"hi":1336,"n":10,"rr":784,"mr":1246},{"m":"llada-moe-7b-a1b-base","r":1257,"s":30.32,"lo":1222,"hi":1286,"n":9,"rr":1090,"mr":1232},{"m":"kanana-2-3b-base","r":1258,"s":30.31,"lo":1182,"hi":1318,"n":9,"rr":1212,"mr":1235},{"m":"telechat2-3b","r":1259,"s":30.22,"lo":1133,"hi":1335,"n":8,"rr":776,"mr":1265},{"m":"qwen3-0.6b","r":1260,"s":30.19,"lo":1149,"hi":1381,"n":28,"rr":1546,"mr":1205},{"m":"mobilellm-r1.5-360m","r":1261,"s":30.11,"lo":1091,"hi":1357,"n":3,"rr":1412,"mr":1255},{"m":"marin-8b-instruct","r":1262,"s":30.05,"lo":1204,"hi":1319,"n":18,"rr":1272,"mr":1224},{"m":"codegemma-7b","r":1263,"s":30.05,"lo":1179,"hi":1314,"n":6,"rr":1402,"mr":1264},{"m":"adapet-albert-few-shot","r":1264,"s":29.98,"lo":1052,"hi":1327,"n":3,"rr":82,"mr":1324},{"m":"install-albert-few-shot-32examples","r":1265,"s":29.94,"lo":1044,"hi":1322,"n":3,"rr":85,"mr":1297},{"m":"codellama-34b","r":1266,"s":29.83,"lo":1147,"hi":1322,"n":11,"rr":1283,"mr":1261},{"m":"gemma-3-4b","r":1267,"s":29.8,"lo":1100,"hi":1367,"n":19,"rr":1312,"mr":1225},{"m":"xverse-7b-chat","r":1268,"s":29.8,"lo":1177,"hi":1327,"n":3,"rr":1034,"mr":1344},{"m":"gemma-3-4b-base","r":1269,"s":29.75,"lo":1183,"hi":1326,"n":6,"rr":1170,"mr":1288},{"m":"smollm3-3b-base","r":1270,"s":29.71,"lo":1159,"hi":1300,"n":16,"rr":236,"mr":1258},{"m":"trinity-nano-base","r":1271,"s":29.65,"lo":1175,"hi":1329,"n":18,"rr":615,"mr":1244},{"m":"qwen3-1.7b-base","r":1272,"s":29.62,"lo":1199,"hi":1365,"n":13,"rr":1105,"mr":1248},{"m":"gopher-280b","r":1273,"s":29.57,"lo":1108,"hi":1408,"n":5,"rr":524,"mr":1330},{"m":"internvl3.5-4b","r":1274,"s":29.55,"lo":1044,"hi":1583,"n":5,"rr":1354,"mr":1311},{"m":"bolmo-7b","r":1275,"s":29.53,"lo":1203,"hi":1322,"n":3,"rr":1336,"mr":1279},{"m":"command-r-08-2024","r":1276,"s":29.49,"lo":1022,"hi":1328,"n":5,"rr":346,"mr":1321},{"m":"lfm2.5-230m","r":1277,"s":29.47,"lo":1119,"hi":1378,"n":8,"rr":1531,"mr":1238},{"m":"bielik-4.5b-v3-instruct","r":1278,"s":29.4,"lo":1172,"hi":1396,"n":6,"rr":678,"mr":1313},{"m":"llama-3-8b","r":1279,"s":29.35,"lo":1201,"hi":1358,"n":30,"rr":1089,"mr":1228},{"m":"tiny-aya-global","r":1280,"s":29.3,"lo":1126,"hi":1370,"n":3,"rr":1358,"mr":1314},{"m":"olmo-2-1124-7b-instruct","r":1281,"s":29.2,"lo":1221,"hi":1342,"n":14,"rr":1527,"mr":1274},{"m":"nemotron-flash-3b","r":1282,"s":29.17,"lo":1118,"hi":1392,"n":3,"rr":1295,"mr":1285},{"m":"mistral-codealpaca-7b","r":1283,"s":29.16,"lo":1207,"hi":1314,"n":3,"rr":1374,"mr":1318},{"m":"gemma-2-2b-it","r":1284,"s":29.12,"lo":1215,"hi":1354,"n":12,"rr":1459,"mr":1284},{"m":"vllm-sr-decision-2.0-sol-2b","r":1285,"s":29.11,"lo":1152,"hi":1386,"n":8,"rr":960,"mr":1254},{"m":"qwen1.5-14b-chat","r":1286,"s":29.08,"lo":1035,"hi":1431,"n":10,"rr":741,"mr":1304},{"m":"internlm2-chat-7b","r":1287,"s":29.07,"lo":1228,"hi":1326,"n":19,"rr":1102,"mr":1253},{"m":"falcon-180b","r":1288,"s":29.07,"lo":1195,"hi":1334,"n":9,"rr":736,"mr":1300},{"m":"bielik-11b-v2","r":1289,"s":29.05,"lo":1202,"hi":1353,"n":6,"rr":616,"mr":1308},{"m":"speechless-code-mistral-7b-v1.0","r":1290,"s":29.04,"lo":1226,"hi":1323,"n":5,"rr":1298,"mr":1305},{"m":"mistralhermes-codepro-7b-v1","r":1291,"s":28.95,"lo":1231,"hi":1320,"n":5,"rr":1308,"mr":1310},{"m":"qwen1.5-14b","r":1292,"s":28.91,"lo":1162,"hi":1341,"n":12,"rr":862,"mr":1272},{"m":"llama-3.1-swallow-8b-instruct-v0.5","r":1293,"s":28.9,"lo":1206,"hi":1358,"n":5,"rr":1467,"mr":1256},{"m":"eurollm-22b-base","r":1294,"s":28.87,"lo":931,"hi":1452,"n":4,"rr":295,"mr":1327},{"m":"lfm2-1.2b","r":1295,"s":28.87,"lo":1209,"hi":1326,"n":7,"rr":1253,"mr":1263},{"m":"internlm2-chat-7b-sft","r":1296,"s":28.86,"lo":1224,"hi":1343,"n":18,"rr":1117,"mr":1257},{"m":"llama-tfree-hat-pretrained-7b-dpo","r":1297,"s":28.64,"lo":1100,"hi":1326,"n":3,"rr":551,"mr":1320},{"m":"codellama-python-13b","r":1298,"s":28.57,"lo":1221,"hi":1330,"n":4,"rr":1337,"mr":1326},{"m":"audio-flamingo-3","r":1299,"s":28.52,"lo":1195,"hi":1332,"n":4,"rr":1341,"mr":1293},{"m":"falcon3-3b","r":1300,"s":28.5,"lo":1242,"hi":1386,"n":18,"rr":1391,"mr":1268},{"m":"solar-10.7b-instruct-v1.0","r":1301,"s":28.48,"lo":1216,"hi":1342,"n":13,"rr":848,"mr":1302},{"m":"marin-32b-bison","r":1302,"s":28.4,"lo":1152,"hi":1414,"n":17,"rr":709,"mr":1266},{"m":"llada-8b-base","r":1303,"s":28.31,"lo":1219,"hi":1363,"n":9,"rr":1162,"mr":1276},{"m":"hy-0.5b","r":1304,"s":28.29,"lo":1128,"hi":1455,"n":8,"rr":1355,"mr":1280},{"m":"aquila2-34b","r":1305,"s":28.27,"lo":1130,"hi":1379,"n":13,"rr":527,"mr":1323},{"m":"strands-decider-2b","r":1306,"s":28.26,"lo":1210,"hi":1422,"n":8,"rr":1056,"mr":1275},{"m":"llada-8b-instruct","r":1307,"s":28.19,"lo":1243,"hi":1366,"n":14,"rr":1188,"mr":1282},{"m":"chatglm3-6b","r":1308,"s":28.05,"lo":1234,"hi":1366,"n":18,"rr":1128,"mr":1278},{"m":"stablebeluga2-70b","r":1309,"s":27.93,"lo":1160,"hi":1413,"n":16,"rr":856,"mr":1287},{"m":"orion-14b-chat","r":1310,"s":27.92,"lo":1238,"hi":1346,"n":6,"rr":676,"mr":1357},{"m":"qwen2.5-1.5b","r":1311,"s":27.89,"lo":1255,"hi":1360,"n":26,"rr":1417,"mr":1262},{"m":"eurollm-9b-instruct-2512","r":1312,"s":27.85,"lo":1269,"hi":1349,"n":18,"rr":1291,"mr":1277},{"m":"deepseek-v2-lite-chat","r":1313,"s":27.84,"lo":1262,"hi":1348,"n":23,"rr":1282,"mr":1283},{"m":"apertus-v1.5-8b-base","r":1314,"s":27.72,"lo":957,"hi":1442,"n":4,"rr":326,"mr":1342},{"m":"qwen2.5-coder-0.5b-instruct","r":1315,"s":27.7,"lo":1193,"hi":1458,"n":7,"rr":1439,"mr":1360},{"m":"yi-1.5-6b","r":1316,"s":27.67,"lo":1231,"hi":1370,"n":10,"rr":1186,"mr":1291},{"m":"mobilellm-r1-950m-base","r":1317,"s":27.63,"lo":1263,"hi":1411,"n":3,"rr":1356,"mr":1328},{"m":"vita","r":1318,"s":27.59,"lo":1139,"hi":1420,"n":4,"rr":1070,"mr":1382},{"m":"granite-3.3-8b-base","r":1319,"s":27.56,"lo":1212,"hi":1405,"n":19,"rr":922,"mr":1307},{"m":"yi-34b","r":1320,"s":27.54,"lo":990,"hi":1423,"n":11,"rr":945,"mr":1315},{"m":"tigerbot-70b-base","r":1321,"s":27.51,"lo":1159,"hi":1413,"n":9,"rr":491,"mr":1348},{"m":"text-to-text-petl","r":1322,"s":27.46,"lo":1016,"hi":1396,"n":3,"rr":96,"mr":1354},{"m":"minerva-62b","r":1323,"s":27.46,"lo":1210,"hi":1361,"n":3,"rr":1363,"mr":1334},{"m":"llama-3.2-3b-base","r":1324,"s":27.39,"lo":1253,"hi":1394,"n":18,"rr":1407,"mr":1295},{"m":"falcon-h1-0.5b-instruct","r":1325,"s":27.36,"lo":1252,"hi":1398,"n":18,"rr":1436,"mr":1267},{"m":"aquilachat2-34b","r":1326,"s":27.32,"lo":844,"hi":1434,"n":6,"rr":778,"mr":1369},{"m":"xverse-13b-2","r":1327,"s":27.24,"lo":1214,"hi":1359,"n":8,"rr":797,"mr":1341},{"m":"mobilemoe-l","r":1328,"s":27.24,"lo":1233,"hi":1378,"n":19,"rr":976,"mr":1296},{"m":"apertus-8b-instruct","r":1329,"s":27.2,"lo":1278,"hi":1368,"n":24,"rr":1453,"mr":1292},{"m":"trida-7b","r":1330,"s":26.94,"lo":1256,"hi":1362,"n":8,"rr":1182,"mr":1309},{"m":"afm-4.5b","r":1331,"s":26.93,"lo":1206,"hi":1439,"n":7,"rr":1213,"mr":1325},{"m":"deepseek-coder-33b-base","r":1332,"s":26.92,"lo":1245,"hi":1450,"n":17,"rr":1286,"mr":1329},{"m":"starcoder2-15b","r":1333,"s":26.87,"lo":1274,"hi":1395,"n":18,"rr":1311,"mr":1306},{"m":"qwen-14b-chat","r":1334,"s":26.84,"lo":1250,"hi":1384,"n":21,"rr":1152,"mr":1299},{"m":"baichuan2-13b-chat-4bits","r":1335,"s":26.8,"lo":1195,"hi":1369,"n":3,"rr":985,"mr":1403},{"m":"aquif-3.5-a0.6b","r":1336,"s":26.77,"lo":1122,"hi":1369,"n":3,"rr":1307,"mr":1335},{"m":"north-micro-vision-instruct","r":1337,"s":26.75,"lo":1125,"hi":1420,"n":4,"rr":1274,"mr":1331},{"m":"internlm-20b","r":1338,"s":26.67,"lo":1255,"hi":1394,"n":25,"rr":728,"mr":1303},{"m":"kanana-2-1.3b-base","r":1339,"s":26.64,"lo":1240,"hi":1405,"n":9,"rr":1392,"mr":1316},{"m":"yi-6b-chat-8bits","r":1340,"s":26.59,"lo":1115,"hi":1414,"n":6,"rr":926,"mr":1373},{"m":"codellama-13b-instruct","r":1341,"s":26.59,"lo":1224,"hi":1391,"n":7,"rr":1435,"mr":1338},{"m":"gemma-4-e4b","r":1342,"s":26.55,"lo":998,"hi":1506,"n":16,"rr":668,"mr":1332},{"m":"codellama-python-7b","r":1343,"s":26.54,"lo":1255,"hi":1363,"n":4,"rr":1396,"mr":1362},{"m":"meta-llama-3-8b-instruct","r":1344,"s":26.46,"lo":1224,"hi":1500,"n":8,"rr":920,"mr":1378},{"m":"qwen3.5-0.8b-thinking","r":1345,"s":26.4,"lo":1222,"hi":1410,"n":19,"rr":1542,"mr":1290},{"m":"llama-3-8b-instruct-gradient-1048k","r":1346,"s":26.38,"lo":985,"hi":1446,"n":14,"rr":1055,"mr":1346},{"m":"skywork-13b","r":1347,"s":26.25,"lo":1156,"hi":1411,"n":4,"rr":1003,"mr":1393},{"m":"gemma-7b","r":1348,"s":26.22,"lo":1287,"hi":1377,"n":24,"rr":1150,"mr":1317},{"m":"aquif-3-0.4b","r":1349,"s":26.21,"lo":1186,"hi":1382,"n":3,"rr":1353,"mr":1345},{"m":"llemma-34b","r":1350,"s":26.19,"lo":1286,"hi":1376,"n":5,"rr":1401,"mr":1377},{"m":"internlm2-base-20b","r":1351,"s":25.92,"lo":1215,"hi":1401,"n":10,"rr":1082,"mr":1337},{"m":"qwen2.5-coder-1.5b","r":1352,"s":25.86,"lo":1290,"hi":1434,"n":16,"rr":1276,"mr":1336},{"m":"llama-3-8b-base","r":1353,"s":25.85,"lo":1292,"hi":1396,"n":23,"rr":1121,"mr":1319},{"m":"qwen1.5-7b","r":1354,"s":25.8,"lo":1292,"hi":1395,"n":19,"rr":1239,"mr":1322},{"m":"jamba-v0.1","r":1355,"s":25.76,"lo":1243,"hi":1407,"n":8,"rr":863,"mr":1372},{"m":"internlm2.5-1.8b","r":1356,"s":25.73,"lo":1293,"hi":1407,"n":6,"rr":1415,"mr":1371},{"m":"llama-2-70b-chat","r":1357,"s":25.58,"lo":1260,"hi":1418,"n":13,"rr":750,"mr":1374},{"m":"kwaiyii-13b-chat","r":1358,"s":25.53,"lo":1286,"hi":1380,"n":5,"rr":1092,"mr":1391},{"m":"qwen1.5-7b-chat","r":1359,"s":25.52,"lo":1311,"hi":1391,"n":25,"rr":1306,"mr":1333},{"m":"qwen1.5-moe-a2.7b","r":1360,"s":25.51,"lo":1116,"hi":1409,"n":8,"rr":1163,"mr":1363},{"m":"codellama-13b","r":1361,"s":25.49,"lo":1238,"hi":1402,"n":9,"rr":1393,"mr":1350},{"m":"telechat-12b","r":1362,"s":25.49,"lo":1194,"hi":1440,"n":9,"rr":1106,"mr":1368},{"m":"llama-3.1-nemotron-70b-instruct-hf","r":1363,"s":25.33,"lo":917,"hi":1430,"n":3,"rr":1580,"mr":1423},{"m":"bielik-4.5b-v3","r":1364,"s":25.32,"lo":1266,"hi":1432,"n":6,"rr":837,"mr":1380},{"m":"qwen1.5-4b-chat","r":1365,"s":25.31,"lo":1153,"hi":1574,"n":3,"rr":1313,"mr":1425},{"m":"deepseek-coder-7b-base-v1.5","r":1366,"s":25.28,"lo":1316,"hi":1435,"n":11,"rr":1209,"mr":1339},{"m":"internlm2-math-base-7b","r":1367,"s":25.25,"lo":875,"hi":1393,"n":3,"rr":1513,"mr":1401},{"m":"codet5-16b","r":1368,"s":25.21,"lo":1161,"hi":1446,"n":3,"rr":1387,"mr":1397},{"m":"chinchilla-70b","r":1369,"s":25.16,"lo":1034,"hi":1420,"n":5,"rr":293,"mr":1375},{"m":"map-neo-7b-instruct","r":1370,"s":25.13,"lo":1297,"hi":1430,"n":23,"rr":1268,"mr":1352},{"m":"olmo-2-1124-7b","r":1371,"s":25.07,"lo":1234,"hi":1540,"n":17,"rr":1057,"mr":1389},{"m":"kwaiyii-13b-base","r":1372,"s":25.02,"lo":1260,"hi":1397,"n":5,"rr":1091,"mr":1404},{"m":"minicpm-moe-8x2b","r":1373,"s":24.97,"lo":1257,"hi":1440,"n":8,"rr":1236,"mr":1381},{"m":"bitcpm-cann-1b","r":1374,"s":24.94,"lo":1301,"hi":1415,"n":11,"rr":731,"mr":1356},{"m":"orion-14b-base","r":1375,"s":24.93,"lo":1255,"hi":1472,"n":21,"rr":808,"mr":1343},{"m":"yi-9b","r":1376,"s":24.86,"lo":1268,"hi":1402,"n":9,"rr":1009,"mr":1361},{"m":"phi-2","r":1377,"s":24.81,"lo":1311,"hi":1434,"n":19,"rr":1275,"mr":1353},{"m":"qwen-7b","r":1378,"s":24.75,"lo":1287,"hi":1408,"n":23,"rr":886,"mr":1340},{"m":"llama-3.2-3b","r":1379,"s":24.73,"lo":1268,"hi":1489,"n":24,"rr":1281,"mr":1347},{"m":"qwen2-1.5b-instruct","r":1380,"s":24.69,"lo":1327,"hi":1416,"n":17,"rr":1449,"mr":1358},{"m":"gemma-1.1-7b-it","r":1381,"s":24.62,"lo":1320,"hi":1410,"n":11,"rr":1445,"mr":1370},{"m":"lfm2-700m","r":1382,"s":24.6,"lo":1285,"hi":1405,"n":7,"rr":1380,"mr":1351},{"m":"yi-6b-chat-4bits","r":1383,"s":24.52,"lo":1144,"hi":1452,"n":6,"rr":1015,"mr":1416},{"m":"internlm2.5-1.8b-chat","r":1384,"s":24.36,"lo":1286,"hi":1426,"n":14,"rr":1273,"mr":1379},{"m":"xdan-l1-chat-rl-v1-7b","r":1385,"s":24.35,"lo":1319,"hi":1415,"n":5,"rr":1450,"mr":1395},{"m":"qwen3-0.6b-base","r":1386,"s":24.35,"lo":1299,"hi":1507,"n":7,"rr":1165,"mr":1388},{"m":"bert-mtl","r":1387,"s":24.33,"lo":938,"hi":1443,"n":3,"rr":145,"mr":1427},{"m":"xverse-moe-a4.2b","r":1388,"s":24.23,"lo":1272,"hi":1417,"n":8,"rr":943,"mr":1412},{"m":"wizardmath-13b-v1.0","r":1389,"s":24.15,"lo":1243,"hi":1431,"n":3,"rr":1398,"mr":1431},{"m":"apertus-8b","r":1390,"s":24.13,"lo":1271,"hi":1458,"n":17,"rr":1025,"mr":1384},{"m":"palm-540b","r":1391,"s":23.95,"lo":767,"hi":1443,"n":12,"rr":474,"mr":1355},{"m":"gemma-2-7b","r":1392,"s":23.88,"lo":1333,"hi":1421,"n":15,"rr":895,"mr":1396},{"m":"deepseek-llm-7b-chat","r":1393,"s":23.84,"lo":1337,"hi":1438,"n":21,"rr":1108,"mr":1359},{"m":"minicpm-2b-sft","r":1394,"s":23.79,"lo":1335,"hi":1420,"n":12,"rr":1190,"mr":1364},{"m":"baichuan-13b-chat","r":1395,"s":23.76,"lo":1247,"hi":1421,"n":3,"rr":1127,"mr":1453},{"m":"tfree-hat-pretrained-7b-base","r":1396,"s":23.74,"lo":1286,"hi":1446,"n":3,"rr":1470,"mr":1394},{"m":"mistral-7b","r":1397,"s":23.7,"lo":1321,"hi":1437,"n":24,"rr":1174,"mr":1367},{"m":"map-neo-7b-sft","r":1398,"s":23.68,"lo":1320,"hi":1438,"n":22,"rr":1234,"mr":1385},{"m":"codellama-7b-instruct","r":1399,"s":23.64,"lo":1329,"hi":1442,"n":8,"rr":1530,"mr":1390},{"m":"bluelm-7b-chat","r":1400,"s":23.52,"lo":1209,"hi":1462,"n":8,"rr":1243,"mr":1411},{"m":"mistral-7b-instruct-v0.2","r":1401,"s":23.5,"lo":1349,"hi":1428,"n":32,"rr":1206,"mr":1366},{"m":"baichuan2-7b-chat-4bits","r":1402,"s":23.31,"lo":1262,"hi":1428,"n":3,"rr":1146,"mr":1457},{"m":"starcoder-15b","r":1403,"s":23.26,"lo":1320,"hi":1436,"n":5,"rr":1456,"mr":1418},{"m":"qwen2-1.5b","r":1404,"s":23.18,"lo":1374,"hi":1451,"n":20,"rr":1334,"mr":1383},{"m":"mobilemoe-m","r":1405,"s":23.15,"lo":1334,"hi":1446,"n":19,"rr":1157,"mr":1376},{"m":"llama-1-65b","r":1406,"s":23.12,"lo":1310,"hi":1443,"n":22,"rr":914,"mr":1365},{"m":"codet5-6b","r":1407,"s":22.98,"lo":1223,"hi":1478,"n":3,"rr":1444,"mr":1433},{"m":"mistral-7b-v0.2","r":1408,"s":22.93,"lo":1256,"hi":1464,"n":7,"rr":1029,"mr":1419},{"m":"qwen2.5-0.5b-instruct","r":1409,"s":22.8,"lo":1326,"hi":1473,"n":11,"rr":1561,"mr":1407},{"m":"lfm2.5-vl-450m","r":1410,"s":22.8,"lo":1245,"hi":1479,"n":4,"rr":1494,"mr":1399},{"m":"qwen3-0.8b","r":1411,"s":22.78,"lo":1341,"hi":1487,"n":18,"rr":1509,"mr":1349},{"m":"internlm2-base-7b","r":1412,"s":22.77,"lo":1284,"hi":1465,"n":14,"rr":1169,"mr":1386},{"m":"bert-plus-plus","r":1413,"s":22.76,"lo":1101,"hi":1460,"n":3,"rr":231,"mr":1444},{"m":"intern-decision-0.8b","r":1414,"s":22.75,"lo":1299,"hi":1483,"n":8,"rr":1242,"mr":1392},{"m":"internvl2.5-2b","r":1415,"s":22.65,"lo":1304,"hi":1454,"n":14,"rr":1332,"mr":1413},{"m":"apertus-v1.1-4b","r":1416,"s":22.62,"lo":1151,"hi":1472,"n":4,"rr":666,"mr":1426},{"m":"codegen-16b","r":1417,"s":22.6,"lo":1332,"hi":1444,"n":5,"rr":1468,"mr":1429},{"m":"deepseek-coder-6.7b-base","r":1418,"s":22.57,"lo":1330,"hi":1484,"n":19,"rr":1408,"mr":1405},{"m":"chatglm2-12b-base","r":1419,"s":22.55,"lo":1199,"hi":1447,"n":3,"rr":1131,"mr":1467},{"m":"x-omni","r":1420,"s":22.44,"lo":1317,"hi":1528,"n":4,"rr":1500,"mr":1420},{"m":"deepseek-v2-lite","r":1421,"s":22.44,"lo":1341,"hi":1442,"n":27,"rr":930,"mr":1400},{"m":"python-code-13b","r":1422,"s":22.42,"lo":1329,"hi":1435,"n":3,"rr":1537,"mr":1438},{"m":"codet5plus-16b","r":1423,"s":22.41,"lo":1324,"hi":1455,"n":5,"rr":1466,"mr":1432},{"m":"mobilellm-r1-360m","r":1424,"s":22.4,"lo":1326,"hi":1504,"n":4,"rr":1597,"mr":1417},{"m":"glm-130b","r":1425,"s":22.33,"lo":735,"hi":1482,"n":3,"rr":780,"mr":1473},{"m":"tev1-0.8b-experimental","r":1426,"s":22.2,"lo":1312,"hi":1498,"n":8,"rr":1261,"mr":1408},{"m":"mistral-7b-v0.1","r":1427,"s":22.2,"lo":1376,"hi":1448,"n":31,"rr":1271,"mr":1398},{"m":"minicpm-2b-dpo-fp32","r":1428,"s":22.16,"lo":1339,"hi":1461,"n":12,"rr":1130,"mr":1410},{"m":"deepseek-moe-16b-chat","r":1429,"s":22.07,"lo":1355,"hi":1482,"n":19,"rr":1175,"mr":1402},{"m":"stablecode-3b","r":1430,"s":22.02,"lo":1348,"hi":1459,"n":7,"rr":1478,"mr":1434},{"m":"gemma-3-1b-it","r":1431,"s":21.98,"lo":1366,"hi":1485,"n":31,"rr":1522,"mr":1387},{"m":"t5gemma-2-4b-4b","r":1432,"s":21.88,"lo":1373,"hi":1453,"n":23,"rr":1173,"mr":1409},{"m":"palm-62b","r":1433,"s":21.87,"lo":1114,"hi":1471,"n":7,"rr":361,"mr":1435},{"m":"qwen-vl","r":1434,"s":21.82,"lo":1294,"hi":1452,"n":3,"rr":1203,"mr":1483},{"m":"baichuan2-13b-base","r":1435,"s":21.76,"lo":1360,"hi":1456,"n":25,"rr":954,"mr":1406},{"m":"tigerbot-13b-chat","r":1436,"s":21.62,"lo":1375,"hi":1459,"n":9,"rr":860,"mr":1451},{"m":"evabyte-6.5b","r":1437,"s":21.6,"lo":1359,"hi":1459,"n":3,"rr":1555,"mr":1443},{"m":"qwen2.5-1.5b-pretrained","r":1438,"s":21.59,"lo":1337,"hi":1605,"n":8,"rr":1156,"mr":1486},{"m":"internvl3.5-2b","r":1439,"s":21.57,"lo":1094,"hi":1597,"n":3,"rr":1588,"mr":1471},{"m":"codeqwen1.5-7b","r":1440,"s":21.47,"lo":1306,"hi":1496,"n":17,"rr":1381,"mr":1424},{"m":"yi-6b-chat","r":1441,"s":21.4,"lo":1318,"hi":1527,"n":14,"rr":1172,"mr":1415},{"m":"chatglm2-12b","r":1442,"s":21.29,"lo":1231,"hi":1467,"n":3,"rr":1202,"mr":1485},{"m":"solar-10.7b-v1.0","r":1443,"s":21.23,"lo":1340,"hi":1491,"n":9,"rr":1185,"mr":1430},{"m":"deepseek-vl-7b","r":1444,"s":21.18,"lo":1369,"hi":1502,"n":5,"rr":1289,"mr":1448},{"m":"codegen-6b","r":1445,"s":20.96,"lo":1377,"hi":1470,"n":5,"rr":1498,"mr":1452},{"m":"internlm-chat-20b","r":1446,"s":20.8,"lo":1381,"hi":1468,"n":8,"rr":1059,"mr":1469},{"m":"llama-1-33b","r":1447,"s":20.77,"lo":1380,"hi":1482,"n":21,"rr":1030,"mr":1421},{"m":"codet5plus-6b","r":1448,"s":20.72,"lo":1367,"hi":1479,"n":5,"rr":1504,"mr":1462},{"m":"coda-1.7b-base","r":1449,"s":20.65,"lo":1385,"hi":1486,"n":5,"rr":1511,"mr":1459},{"m":"granite-4-h-300m","r":1450,"s":20.6,"lo":1120,"hi":1527,"n":10,"rr":1563,"mr":1414},{"m":"skywork-13b-base","r":1451,"s":20.57,"lo":1384,"hi":1492,"n":23,"rr":1004,"mr":1422},{"m":"gemma-7b-it","r":1452,"s":20.55,"lo":1379,"hi":1476,"n":6,"rr":1473,"mr":1474},{"m":"llemma-7b","r":1453,"s":20.51,"lo":1404,"hi":1483,"n":6,"rr":1532,"mr":1476},{"m":"yi-coder-1.5b","r":1454,"s":20.47,"lo":1328,"hi":1509,"n":5,"rr":1525,"mr":1477},{"m":"minicpm4-0.5b","r":1455,"s":20.46,"lo":1388,"hi":1489,"n":11,"rr":962,"mr":1437},{"m":"llama-3.2-1.24b","r":1456,"s":20.41,"lo":1354,"hi":1507,"n":9,"rr":1545,"mr":1454},{"m":"qwen1.5-4b","r":1457,"s":20.41,"lo":1331,"hi":1492,"n":8,"rr":1395,"mr":1445},{"m":"zephyr-7b-beta","r":1458,"s":20.41,"lo":1385,"hi":1483,"n":8,"rr":1441,"mr":1458},{"m":"lfm2.5-vl-1.6b","r":1459,"s":20.23,"lo":1131,"hi":1519,"n":5,"rr":1433,"mr":1447},{"m":"vllm-sr-d3-edge","r":1460,"s":20.19,"lo":1318,"hi":1505,"n":8,"rr":1233,"mr":1436},{"m":"lfm2-350m","r":1461,"s":20.17,"lo":1243,"hi":1509,"n":13,"rr":1559,"mr":1428},{"m":"starcoderbase-16b","r":1462,"s":20.17,"lo":1343,"hi":1515,"n":6,"rr":1521,"mr":1449},{"m":"map-neo-7b","r":1463,"s":19.89,"lo":1403,"hi":1500,"n":20,"rr":1267,"mr":1446},{"m":"codegemma-2b","r":1464,"s":19.72,"lo":1362,"hi":1514,"n":5,"rr":1507,"mr":1481},{"m":"gpt-3","r":1465,"s":19.6,"lo":1238,"hi":1508,"n":15,"rr":730,"mr":1470},{"m":"olmoe-1b-7b-base","r":1466,"s":19.54,"lo":1369,"hi":1620,"n":16,"rr":1237,"mr":1492},{"m":"qwen-7b-chat","r":1467,"s":19.5,"lo":1406,"hi":1496,"n":20,"rr":1344,"mr":1439},{"m":"mobilellm-r1-360m-base","r":1468,"s":19.42,"lo":1405,"hi":1580,"n":3,"rr":1570,"mr":1479},{"m":"janus-pro-7b","r":1469,"s":19.41,"lo":1421,"hi":1500,"n":4,"rr":1528,"mr":1484},{"m":"llama-2-13b","r":1470,"s":19.39,"lo":1409,"hi":1506,"n":25,"rr":1097,"mr":1441},{"m":"olmoe-1b-7b","r":1471,"s":19.38,"lo":1427,"hi":1494,"n":26,"rr":1416,"mr":1440},{"m":"vllm-sr-decision-2.0-eos-0.8b","r":1472,"s":19.31,"lo":1360,"hi":1533,"n":8,"rr":1351,"mr":1456},{"m":"starcoder2-7b","r":1473,"s":19.2,"lo":1425,"hi":1509,"n":17,"rr":1457,"mr":1460},{"m":"qwen3.5-0.8b","r":1474,"s":19.12,"lo":1405,"hi":1515,"n":39,"rr":1517,"mr":1442},{"m":"baichuan2-13b-chat","r":1475,"s":19.1,"lo":1415,"hi":1501,"n":19,"rr":1345,"mr":1450},{"m":"vllm-sr-decision-2.0-kai-0.6b","r":1476,"s":19.09,"lo":1387,"hi":1530,"n":8,"rr":1352,"mr":1461},{"m":"aquila2-7b","r":1477,"s":19.07,"lo":1359,"hi":1514,"n":12,"rr":850,"mr":1495},{"m":"stablelm-zephyr-3b","r":1478,"s":18.99,"lo":1434,"hi":1515,"n":12,"rr":1342,"mr":1465},{"m":"minicpm-1b-sft","r":1479,"s":18.91,"lo":1413,"hi":1507,"n":11,"rr":1348,"mr":1475},{"m":"starcoderbase-7b","r":1480,"s":18.9,"lo":1403,"hi":1512,"n":5,"rr":1562,"mr":1503},{"m":"internlm2-1.8b","r":1481,"s":18.89,"lo":1421,"hi":1497,"n":6,"rr":1533,"mr":1487},{"m":"codet5-2b","r":1482,"s":18.85,"lo":1408,"hi":1508,"n":5,"rr":1541,"mr":1497},{"m":"internlm2-chat-1.8b","r":1483,"s":18.84,"lo":1440,"hi":1497,"n":13,"rr":1409,"mr":1464},{"m":"lfm2-vl-450m","r":1484,"s":18.76,"lo":1315,"hi":1534,"n":4,"rr":1554,"mr":1488},{"m":"qwen2-audio-7b-instruct","r":1485,"s":18.75,"lo":1409,"hi":1517,"n":4,"rr":1543,"mr":1520},{"m":"d1-omni-600m","r":1486,"s":18.71,"lo":1303,"hi":1520,"n":10,"rr":1178,"mr":1463},{"m":"codegen-2b","r":1487,"s":18.64,"lo":1416,"hi":1508,"n":5,"rr":1548,"mr":1499},{"m":"phi-3.5-vision-instruct","r":1488,"s":18.6,"lo":1327,"hi":1539,"n":4,"rr":1476,"mr":1508},{"m":"telechat-7b","r":1489,"s":18.56,"lo":1353,"hi":1525,"n":9,"rr":1437,"mr":1482},{"m":"apertus-v1.1-1.5b","r":1490,"s":18.5,"lo":1198,"hi":1527,"n":4,"rr":900,"mr":1494},{"m":"granite-4-300m","r":1491,"s":18.49,"lo":1334,"hi":1542,"n":10,"rr":1586,"mr":1455},{"m":"codellama-7b","r":1492,"s":18.43,"lo":1425,"hi":1528,"n":19,"rr":1432,"mr":1480},{"m":"falcon-40b","r":1493,"s":18.23,"lo":1410,"hi":1530,"n":18,"rr":1229,"mr":1466},{"m":"mistral-7b-instruct-v0.1","r":1494,"s":17.94,"lo":1435,"hi":1536,"n":15,"rr":1318,"mr":1478},{"m":"qwen2.5-0.5b","r":1495,"s":17.91,"lo":1449,"hi":1530,"n":26,"rr":1560,"mr":1468},{"m":"llama-2-34b","r":1496,"s":17.81,"lo":1409,"hi":1518,"n":6,"rr":1492,"mr":1514},{"m":"codegeex2-6b","r":1497,"s":17.8,"lo":1390,"hi":1534,"n":4,"rr":1576,"mr":1530},{"m":"minerva-8b","r":1498,"s":17.69,"lo":1409,"hi":1570,"n":3,"rr":1595,"mr":1511},{"m":"llama-3.2-1b-instruct","r":1499,"s":17.67,"lo":1460,"hi":1533,"n":14,"rr":1596,"mr":1489},{"m":"mobilellm-p1-base","r":1500,"s":17.56,"lo":1460,"hi":1520,"n":10,"rr":1024,"mr":1507},{"m":"smollm2-1.7b-instruct","r":1501,"s":17.54,"lo":1447,"hi":1532,"n":22,"rr":1427,"mr":1472},{"m":"bitcpm-cann-0.5b","r":1502,"s":17.53,"lo":1443,"hi":1531,"n":11,"rr":1161,"mr":1496},{"m":"internlm-chat-7b","r":1503,"s":17.47,"lo":1386,"hi":1530,"n":11,"rr":1302,"mr":1512},{"m":"tigerbot-13b-base","r":1504,"s":17.41,"lo":1397,"hi":1529,"n":9,"rr":999,"mr":1532},{"m":"qwen1.5-1.8b-chat","r":1505,"s":17.38,"lo":1450,"hi":1524,"n":8,"rr":1443,"mr":1522},{"m":"starcoder2-3b","r":1506,"s":17.25,"lo":1444,"hi":1538,"n":17,"rr":1482,"mr":1493},{"m":"bielik-7b-instruct-v0.1","r":1507,"s":17.23,"lo":1430,"hi":1517,"n":6,"rr":1179,"mr":1526},{"m":"qwen2.5-coder-0.5b","r":1508,"s":17.14,"lo":1456,"hi":1541,"n":16,"rr":1489,"mr":1506},{"m":"bluelm-7b-base","r":1509,"s":17.12,"lo":1335,"hi":1532,"n":8,"rr":1426,"mr":1515},{"m":"mobilemoe-s","r":1510,"s":17.03,"lo":1454,"hi":1534,"n":19,"rr":1403,"mr":1491},{"m":"baichuan2-7b-chat","r":1511,"s":17.03,"lo":1458,"hi":1524,"n":19,"rr":1394,"mr":1490},{"m":"llama-spark-8b","r":1512,"s":16.98,"lo":1145,"hi":1586,"n":5,"rr":1552,"mr":1548},{"m":"gemma-3-1b","r":1513,"s":16.98,"lo":1367,"hi":1552,"n":27,"rr":1502,"mr":1501},{"m":"yi-6b","r":1514,"s":16.97,"lo":1388,"hi":1540,"n":12,"rr":1333,"mr":1504},{"m":"qwen2-0.5b-instruct","r":1515,"s":16.84,"lo":1464,"hi":1566,"n":12,"rr":1589,"mr":1516},{"m":"gemma-2-2b","r":1516,"s":16.75,"lo":1461,"hi":1537,"n":33,"rr":1463,"mr":1500},{"m":"olmo-2-0425-1b-instruct","r":1517,"s":16.67,"lo":1451,"hi":1546,"n":21,"rr":1438,"mr":1498},{"m":"blt-7b","r":1518,"s":16.62,"lo":1399,"hi":1538,"n":3,"rr":1598,"mr":1524},{"m":"deepseek-llm-7b-base","r":1519,"s":16.56,"lo":1460,"hi":1540,"n":21,"rr":1309,"mr":1502},{"m":"bielik-7b-v0.1","r":1520,"s":16.5,"lo":1446,"hi":1528,"n":6,"rr":1218,"mr":1537},{"m":"llama-2-13b-chat","r":1521,"s":16.41,"lo":1440,"hi":1547,"n":23,"rr":1383,"mr":1518},{"m":"baichuan2-7b-base","r":1522,"s":16.36,"lo":1444,"hi":1537,"n":23,"rr":1207,"mr":1505},{"m":"falcon3-1b","r":1523,"s":16.34,"lo":1483,"hi":1545,"n":18,"rr":1556,"mr":1513},{"m":"internvl2-2b","r":1524,"s":16.28,"lo":1465,"hi":1537,"n":14,"rr":1475,"mr":1528},{"m":"internlm-7b","r":1525,"s":16.2,"lo":1459,"hi":1541,"n":22,"rr":1238,"mr":1509},{"m":"olmo-2-0425-1b-base","r":1526,"s":16.15,"lo":1421,"hi":1547,"n":3,"rr":1558,"mr":1536},{"m":"gemma-4-e2b","r":1527,"s":16.12,"lo":1175,"hi":1560,"n":16,"rr":969,"mr":1525},{"m":"xverse-7b","r":1528,"s":16.12,"lo":1336,"hi":1570,"n":8,"rr":1249,"mr":1545},{"m":"qwen1.5-1.8b","r":1529,"s":15.96,"lo":1488,"hi":1541,"n":13,"rr":1397,"mr":1519},{"m":"mpt-30b","r":1530,"s":15.79,"lo":1461,"hi":1562,"n":18,"rr":1364,"mr":1510},{"m":"baichuan-13b-base","r":1531,"s":15.73,"lo":1457,"hi":1556,"n":18,"rr":1258,"mr":1521},{"m":"deepseek-moe-16b-base","r":1532,"s":15.72,"lo":1475,"hi":1549,"n":20,"rr":1335,"mr":1517},{"m":"vicuna-7b-v1.5","r":1533,"s":15.71,"lo":1383,"hi":1583,"n":3,"rr":1516,"mr":1563},{"m":"deepseek-coder-1.3b-base","r":1534,"s":15.64,"lo":1448,"hi":1577,"n":17,"rr":1536,"mr":1531},{"m":"smollm2-1.7b-pretrained","r":1535,"s":15.5,"lo":1422,"hi":1575,"n":8,"rr":1148,"mr":1544},{"m":"apertus-v1.1-0.5b","r":1536,"s":15.45,"lo":1205,"hi":1568,"n":4,"rr":1116,"mr":1541},{"m":"huginn-3.5b","r":1537,"s":15.42,"lo":1485,"hi":1573,"n":8,"rr":1418,"mr":1543},{"m":"gemma-2b","r":1538,"s":15.33,"lo":1493,"hi":1552,"n":17,"rr":1483,"mr":1523},{"m":"qwen2-0.5b","r":1539,"s":15.33,"lo":1499,"hi":1557,"n":19,"rr":1510,"mr":1527},{"m":"codegen2-7b","r":1540,"s":15.28,"lo":1458,"hi":1547,"n":3,"rr":1600,"mr":1551},{"m":"gemini-nano-2","r":1541,"s":15.27,"lo":1411,"hi":1554,"n":3,"rr":1544,"mr":1556},{"m":"chatglm2-6b","r":1542,"s":15.19,"lo":1486,"hi":1559,"n":20,"rr":1255,"mr":1529},{"m":"codegen2-16b","r":1543,"s":15.08,"lo":1469,"hi":1552,"n":3,"rr":1602,"mr":1553},{"m":"gemma-1.1-2b-it","r":1544,"s":15.02,"lo":1482,"hi":1558,"n":5,"rr":1594,"mr":1550},{"m":"llama-1-13b","r":1545,"s":15,"lo":1469,"hi":1558,"n":21,"rr":1248,"mr":1533},{"m":"telechat-1b","r":1546,"s":14.86,"lo":1496,"hi":1558,"n":9,"rr":1529,"mr":1547},{"m":"smollm2-1.7b-base","r":1547,"s":14.75,"lo":1494,"hi":1588,"n":13,"rr":1523,"mr":1538},{"m":"bloomz-7b1","r":1548,"s":14.65,"lo":1390,"hi":1564,"n":3,"rr":1508,"mr":1569},{"m":"chatglm2-6b-base","r":1549,"s":14.6,"lo":1500,"hi":1564,"n":12,"rr":1378,"mr":1549},{"m":"llama-2-7b","r":1550,"s":14.57,"lo":1490,"hi":1561,"n":30,"rr":1359,"mr":1535},{"m":"xverse-13b","r":1551,"s":14.51,"lo":1451,"hi":1574,"n":20,"rr":1292,"mr":1534},{"m":"starcoderbase-3b","r":1552,"s":14.5,"lo":1478,"hi":1557,"n":3,"rr":1605,"mr":1559},{"m":"smolvlm2-0.5b","r":1553,"s":14.49,"lo":1300,"hi":1605,"n":4,"rr":1599,"mr":1566},{"m":"llama-2-7b-chat","r":1554,"s":14.45,"lo":1499,"hi":1562,"n":31,"rr":1452,"mr":1539},{"m":"mobilellm-p1","r":1555,"s":14.33,"lo":1494,"hi":1567,"n":19,"rr":1430,"mr":1542},{"m":"llama-1b","r":1556,"s":14.28,"lo":1498,"hi":1561,"n":6,"rr":1330,"mr":1568},{"m":"open-llama-13b","r":1557,"s":14.27,"lo":1474,"hi":1582,"n":12,"rr":1110,"mr":1558},{"m":"llama-3.2-1.24b-base","r":1558,"s":14.09,"lo":1507,"hi":1569,"n":19,"rr":1582,"mr":1540},{"m":"olmo-1.7-7b","r":1559,"s":13.94,"lo":1508,"hi":1563,"n":19,"rr":1410,"mr":1546},{"m":"qwen-1.8b-chat","r":1560,"s":13.74,"lo":1510,"hi":1567,"n":6,"rr":1524,"mr":1565},{"m":"gemma-2b-it","r":1561,"s":13.35,"lo":1498,"hi":1573,"n":4,"rr":1601,"mr":1572},{"m":"qwen-1.8b","r":1562,"s":13.31,"lo":1522,"hi":1570,"n":16,"rr":1399,"mr":1554},{"m":"vicuna-13b","r":1563,"s":13.25,"lo":1519,"hi":1566,"n":11,"rr":1569,"mr":1557},{"m":"santacoder-1.1b","r":1564,"s":13.14,"lo":1498,"hi":1571,"n":3,"rr":1607,"mr":1570},{"m":"pythia-2.8b","r":1565,"s":13.14,"lo":1248,"hi":1572,"n":6,"rr":737,"mr":1578},{"m":"codegen2-3b","r":1566,"s":12.94,"lo":1507,"hi":1576,"n":3,"rr":1608,"mr":1571},{"m":"gliner2.5-decide","r":1567,"s":12.76,"lo":1437,"hi":1584,"n":8,"rr":1484,"mr":1555},{"m":"mobilellm-r1.5-140m","r":1568,"s":12.69,"lo":1501,"hi":1597,"n":3,"rr":1621,"mr":1560},{"m":"incoder-6.7b","r":1569,"s":12.69,"lo":1513,"hi":1578,"n":3,"rr":1610,"mr":1574},{"m":"mpt-7b","r":1570,"s":12.68,"lo":1523,"hi":1581,"n":21,"rr":1386,"mr":1552},{"m":"chinese-llama-plus-13b","r":1571,"s":12.62,"lo":1355,"hi":1578,"n":3,"rr":1499,"mr":1589},{"m":"ziya-llama-13b-pretrain","r":1572,"s":12.61,"lo":1381,"hi":1579,"n":4,"rr":1515,"mr":1583},{"m":"starcoderbase-1b","r":1573,"s":12.43,"lo":1517,"hi":1580,"n":3,"rr":1613,"mr":1577},{"m":"llama-3.2-1b","r":1574,"s":12.35,"lo":1513,"hi":1579,"n":20,"rr":1448,"mr":1562},{"m":"pythia-1.4b","r":1575,"s":12.06,"lo":1275,"hi":1580,"n":6,"rr":839,"mr":1588},{"m":"warp-albert-xxl-v2-few-shot-32-examples","r":1576,"s":12.05,"lo":1216,"hi":1586,"n":3,"rr":1095,"mr":1561},{"m":"llama-1-7b","r":1577,"s":11.85,"lo":1529,"hi":1583,"n":21,"rr":1371,"mr":1564},{"m":"t5gemma-2-1b-1b","r":1578,"s":11.57,"lo":1539,"hi":1584,"n":23,"rr":1485,"mr":1567},{"m":"gpt-j-6b","r":1579,"s":11.42,"lo":1536,"hi":1587,"n":3,"rr":1614,"mr":1585},{"m":"incoder-1.3b","r":1580,"s":11.42,"lo":1537,"hi":1588,"n":3,"rr":1615,"mr":1586},{"m":"mobilellm-r1-140m","r":1581,"s":11.35,"lo":1523,"hi":1596,"n":4,"rr":1624,"mr":1576},{"m":"qwen1.5-0.5b","r":1582,"s":11.09,"lo":1540,"hi":1591,"n":8,"rr":1584,"mr":1580},{"m":"pythia-1b","r":1583,"s":11.08,"lo":1300,"hi":1590,"n":6,"rr":931,"mr":1593},{"m":"olmo-7b-instruct","r":1584,"s":11.04,"lo":1542,"hi":1589,"n":24,"rr":1487,"mr":1575},{"m":"chinese-alpaca-plus-13b","r":1585,"s":10.88,"lo":1538,"hi":1588,"n":9,"rr":1578,"mr":1587},{"m":"vicuna-7b","r":1586,"s":10.87,"lo":1549,"hi":1587,"n":12,"rr":1491,"mr":1581},{"m":"laya","r":1587,"s":10.77,"lo":1379,"hi":1596,"n":8,"rr":1506,"mr":1573},{"m":"trlm-135m","r":1588,"s":10.76,"lo":1528,"hi":1612,"n":7,"rr":1442,"mr":1579},{"m":"falcon-7b","r":1589,"s":10.35,"lo":1537,"hi":1602,"n":19,"rr":1465,"mr":1582},{"m":"codegen2-1b","r":1590,"s":10.33,"lo":1549,"hi":1598,"n":3,"rr":1617,"mr":1592},{"m":"bloom-7b1","r":1591,"s":10.32,"lo":1382,"hi":1604,"n":3,"rr":1583,"mr":1597},{"m":"smolvlm2-2.2b","r":1592,"s":10.31,"lo":1377,"hi":1610,"n":4,"rr":1593,"mr":1591},{"m":"qwen1.5-0.5b-chat","r":1593,"s":9.93,"lo":1548,"hi":1596,"n":7,"rr":1566,"mr":1595},{"m":"amberchat","r":1594,"s":9.81,"lo":1561,"hi":1599,"n":22,"rr":1549,"mr":1584},{"m":"baichuan-7b","r":1595,"s":9.7,"lo":1547,"hi":1598,"n":12,"rr":1547,"mr":1594},{"m":"deepseek-vl-1.3b","r":1596,"s":9.36,"lo":1560,"hi":1610,"n":5,"rr":1575,"mr":1606},{"m":"emu3-8b","r":1597,"s":9.31,"lo":1448,"hi":1615,"n":4,"rr":1606,"mr":1604},{"m":"pythia-410m","r":1598,"s":9.25,"lo":1299,"hi":1603,"n":6,"rr":1080,"mr":1608},{"m":"falcon-e-1b-base","r":1599,"s":9.25,"lo":1305,"hi":1618,"n":6,"rr":1611,"mr":1603},{"m":"amber-7b","r":1600,"s":9.09,"lo":1563,"hi":1604,"n":19,"rr":1540,"mr":1590},{"m":"moss-moon-003-base","r":1601,"s":8.95,"lo":1352,"hi":1607,"n":3,"rr":1568,"mr":1612},{"m":"alpaca-7b","r":1602,"s":8.7,"lo":1566,"hi":1604,"n":9,"rr":1551,"mr":1599},{"m":"pythia-12b","r":1603,"s":8.61,"lo":1565,"hi":1608,"n":22,"rr":1486,"mr":1600},{"m":"pythia-6.9b","r":1604,"s":8.51,"lo":1570,"hi":1608,"n":22,"rr":1495,"mr":1602},{"m":"gpt-neo-2.7b","r":1605,"s":8.47,"lo":1566,"hi":1610,"n":3,"rr":1622,"mr":1607},{"m":"olmo-7b","r":1606,"s":8.45,"lo":1569,"hi":1607,"n":19,"rr":1526,"mr":1601},{"m":"smollm2-360m-instruct","r":1607,"s":8.33,"lo":1572,"hi":1610,"n":21,"rr":1571,"mr":1598},{"m":"gemma-3-270m-it","r":1608,"s":8.31,"lo":1574,"hi":1610,"n":23,"rr":1590,"mr":1596},{"m":"llama-1b-pretrained","r":1609,"s":8.15,"lo":1511,"hi":1609,"n":8,"rr":1362,"mr":1613},{"m":"polycoder-2.7b","r":1610,"s":7.69,"lo":1568,"hi":1613,"n":3,"rr":1623,"mr":1611},{"m":"smollm2-135m-instruct","r":1611,"s":7.68,"lo":1578,"hi":1614,"n":9,"rr":1592,"mr":1605},{"m":"pythia-160m","r":1612,"s":7.64,"lo":1297,"hi":1611,"n":6,"rr":1310,"mr":1616},{"m":"tinyllama-1.1b","r":1613,"s":7.51,"lo":1576,"hi":1614,"n":11,"rr":1579,"mr":1609},{"m":"smollm1-1.7b-pretrained","r":1614,"s":7.51,"lo":1542,"hi":1613,"n":9,"rr":1413,"mr":1614},{"m":"falcon-3-1b-base","r":1615,"s":7.04,"lo":1530,"hi":1620,"n":6,"rr":1616,"mr":1619},{"m":"smollm1-1.7b-instruct","r":1616,"s":6.95,"lo":1532,"hi":1617,"n":6,"rr":1474,"mr":1618},{"m":"t5gemma-2-270m-270m","r":1617,"s":6.66,"lo":1580,"hi":1615,"n":23,"rr":1567,"mr":1610},{"m":"gemma-3-pt-270m","r":1618,"s":6.42,"lo":1580,"hi":1619,"n":10,"rr":1493,"mr":1615},{"m":"pythia-70m","r":1619,"s":6.39,"lo":1296,"hi":1618,"n":6,"rr":1429,"mr":1622},{"m":"chatglm-6b","r":1620,"s":6.19,"lo":1577,"hi":1620,"n":13,"rr":1581,"mr":1620},{"m":"smollm2-360m-base","r":1621,"s":5.58,"lo":1592,"hi":1620,"n":9,"rr":1620,"mr":1617},{"m":"gemma-3-pt-1b","r":1622,"s":5.45,"lo":1514,"hi":1619,"n":3,"rr":1618,"mr":1621},{"m":"smollm2-135m-base","r":1623,"s":4.96,"lo":1585,"hi":1621,"n":10,"rr":1557,"mr":1623},{"m":"stablelm-7b","r":1624,"s":4.29,"lo":1572,"hi":1622,"n":3,"rr":1626,"mr":1624},{"m":"zyte-1b","r":1625,"s":3.75,"lo":1594,"hi":1623,"n":5,"rr":1625,"mr":1625},{"m":"smollm2-135m-pretrained","r":1626,"s":3.44,"lo":1577,"hi":1625,"n":8,"rr":1496,"mr":1626}]},"faix-visual":{"name":"Visual","n":529,"nb":91,"acc":0.8347,"raw_acc":0.7416,"rows":[{"m":"gpt-6-astra","r":1,"s":88.95,"lo":1,"hi":63,"n":10,"rr":20,"mr":1},{"m":"qwen3.8-max","r":2,"s":88.66,"lo":1,"hi":4,"n":18,"rr":13,"mr":2},{"m":"qwen3.8-omni-flash","r":3,"s":88.46,"lo":1,"hi":27,"n":6,"rr":11,"mr":3},{"m":"qwen3.8-flash-next","r":4,"s":87.52,"lo":3,"hi":10,"n":11,"rr":56,"mr":4},{"m":"claude-fable-5","r":5,"s":87.39,"lo":1,"hi":17,"n":14,"rr":44,"mr":5},{"m":"claude-mythos-5","r":6,"s":86.27,"lo":3,"hi":105,"n":4,"rr":23,"mr":6},{"m":"gemini-3.6-flash","r":7,"s":85.67,"lo":5,"hi":58,"n":8,"rr":30,"mr":12},{"m":"kimi-k3","r":8,"s":85.64,"lo":5,"hi":24,"n":8,"rr":17,"mr":11},{"m":"gpt-5.6-sol","r":9,"s":85.48,"lo":5,"hi":16,"n":21,"rr":62,"mr":7},{"m":"qwen3.7-plus","r":10,"s":85.29,"lo":5,"hi":17,"n":18,"rr":51,"mr":8},{"m":"gemini-3.1-pro","r":11,"s":85.26,"lo":5,"hi":17,"n":28,"rr":54,"mr":9},{"m":"gemini-3.5-flash","r":12,"s":85.03,"lo":7,"hi":25,"n":8,"rr":35,"mr":13},{"m":"gemini-3.8-flash","r":13,"s":84.94,"lo":2,"hi":180,"n":3,"rr":12,"mr":19},{"m":"seed2.1-pro","r":14,"s":84.92,"lo":6,"hi":24,"n":17,"rr":52,"mr":10},{"m":"muse-spark","r":15,"s":84.9,"lo":7,"hi":41,"n":5,"rr":84,"mr":14},{"m":"gpt-5.4","r":16,"s":84.41,"lo":11,"hi":28,"n":14,"rr":55,"mr":15},{"m":"claude-opus-5.5","r":17,"s":84.29,"lo":7,"hi":145,"n":5,"rr":61,"mr":25},{"m":"seed2.1-turbo","r":18,"s":84.2,"lo":11,"hi":25,"n":18,"rr":53,"mr":16},{"m":"gemini-3.7-flash","r":19,"s":84.17,"lo":8,"hi":78,"n":4,"rr":19,"mr":23},{"m":"qwen3.6-plus","r":20,"s":83.81,"lo":7,"hi":30,"n":25,"rr":50,"mr":17},{"m":"qwen3.5-397b-a17b","r":21,"s":83.74,"lo":11,"hi":29,"n":35,"rr":95,"mr":18},{"m":"seed2.0-lite-0428","r":22,"s":83.66,"lo":15,"hi":31,"n":10,"rr":46,"mr":20},{"m":"gpt-5.2-extra-high","r":23,"s":83.5,"lo":7,"hi":48,"n":4,"rr":21,"mr":29},{"m":"gpt-5.5","r":24,"s":83.34,"lo":13,"hi":37,"n":22,"rr":92,"mr":22},{"m":"dots3-note-preview","r":25,"s":83.25,"lo":20,"hi":42,"n":6,"rr":33,"mr":24},{"m":"gemini-3-pro","r":26,"s":83.1,"lo":14,"hi":36,"n":55,"rr":47,"mr":21},{"m":"claude-opus-4.8","r":27,"s":82.85,"lo":10,"hi":50,"n":21,"rr":150,"mr":30},{"m":"gpt-5.6-terra","r":28,"s":82.84,"lo":18,"hi":91,"n":5,"rr":58,"mr":34},{"m":"gemini-3-flash","r":29,"s":82.84,"lo":18,"hi":40,"n":19,"rr":72,"mr":28},{"m":"qwen3.5-122b-a10b","r":30,"s":82.81,"lo":17,"hi":35,"n":36,"rr":124,"mr":26},{"m":"seed2.0-pro","r":31,"s":82.74,"lo":20,"hi":62,"n":12,"rr":131,"mr":27},{"m":"ace-brain-0.6-9b","r":32,"s":82.24,"lo":16,"hi":235,"n":3,"rr":67,"mr":45},{"m":"ling-3.0-flash-vl","r":33,"s":82.18,"lo":18,"hi":62,"n":4,"rr":10,"mr":36},{"m":"glm-5v-turbo","r":34,"s":82.04,"lo":15,"hi":110,"n":4,"rr":107,"mr":43},{"m":"kimi-k2.5-thinking","r":35,"s":81.98,"lo":22,"hi":52,"n":14,"rr":83,"mr":35},{"m":"qwen3.8-27b","r":36,"s":81.95,"lo":11,"hi":68,"n":22,"rr":60,"mr":31},{"m":"qwen3.6-27b","r":37,"s":81.91,"lo":20,"hi":46,"n":32,"rr":45,"mr":32},{"m":"qwen3.5-27b","r":38,"s":81.89,"lo":21,"hi":45,"n":36,"rr":129,"mr":33},{"m":"kimi-k2.6-thinking","r":39,"s":81.85,"lo":28,"hi":78,"n":4,"rr":9,"mr":39},{"m":"sensenova-mars-32b","r":40,"s":81.83,"lo":7,"hi":194,"n":3,"rr":43,"mr":49},{"m":"glm-5.3-flash","r":41,"s":81.74,"lo":21,"hi":59,"n":10,"rr":143,"mr":41},{"m":"claude-opus-5","r":42,"s":81.58,"lo":24,"hi":84,"n":9,"rr":117,"mr":44},{"m":"qwen3.5-35b-a3b","r":43,"s":81.54,"lo":24,"hi":48,"n":34,"rr":132,"mr":38},{"m":"kimi-k2.5","r":44,"s":81.51,"lo":27,"hi":57,"n":32,"rr":39,"mr":37},{"m":"qwen3.6-35b-a3b","r":45,"s":81.23,"lo":33,"hi":53,"n":37,"rr":49,"mr":40},{"m":"mimo-v2.5","r":46,"s":81.14,"lo":29,"hi":156,"n":3,"rr":27,"mr":47},{"m":"seed2.0-lite","r":47,"s":81.05,"lo":34,"hi":80,"n":11,"rr":155,"mr":42},{"m":"ui-venus-1.5-30b-a3b","r":48,"s":80.91,"lo":26,"hi":86,"n":4,"rr":64,"mr":55},{"m":"holo2-235b-a22b","r":49,"s":80.9,"lo":28,"hi":79,"n":6,"rr":16,"mr":56},{"m":"muse-glimmer-30b","r":50,"s":80.47,"lo":35,"hi":91,"n":3,"rr":109,"mr":53},{"m":"intern-s2-preview","r":51,"s":80.26,"lo":40,"hi":82,"n":3,"rr":104,"mr":54},{"m":"mimo-v2-omni","r":52,"s":80.2,"lo":40,"hi":155,"n":3,"rr":38,"mr":60},{"m":"gpt-5.2-thinking-xhigh","r":53,"s":80.18,"lo":39,"hi":142,"n":10,"rr":82,"mr":51},{"m":"mai-ui-32b","r":54,"s":80.13,"lo":33,"hi":96,"n":4,"rr":105,"mr":62},{"m":"ui-venus-1.5-8b","r":55,"s":80.06,"lo":38,"hi":94,"n":4,"rr":98,"mr":63},{"m":"gemini-3.5-flash-lite","r":56,"s":80.03,"lo":27,"hi":83,"n":4,"rr":26,"mr":57},{"m":"seed1.8","r":57,"s":80,"lo":35,"hi":68,"n":25,"rr":103,"mr":46},{"m":"qwen3.5-omni-plus","r":58,"s":79.91,"lo":29,"hi":72,"n":24,"rr":71,"mr":48},{"m":"o3","r":59,"s":79.88,"lo":48,"hi":159,"n":8,"rr":312,"mr":58},{"m":"claude-opus-4.7","r":60,"s":79.71,"lo":41,"hi":79,"n":16,"rr":186,"mr":50},{"m":"minimax-m3","r":61,"s":79.71,"lo":47,"hi":151,"n":3,"rr":24,"mr":66},{"m":"sensenova-mars-8b","r":62,"s":79.6,"lo":30,"hi":224,"n":3,"rr":99,"mr":74},{"m":"holo2-30b-a3b","r":63,"s":79.29,"lo":42,"hi":113,"n":7,"rr":41,"mr":71},{"m":"gpt-5.2","r":64,"s":79.29,"lo":40,"hi":138,"n":36,"rr":113,"mr":52},{"m":"claude-opus-4.6","r":65,"s":79.1,"lo":29,"hi":88,"n":16,"rr":200,"mr":67},{"m":"nemotron-3.5-super-vl-120b-a12b","r":66,"s":79.06,"lo":46,"hi":91,"n":11,"rr":182,"mr":59},{"m":"o3-high","r":67,"s":78.94,"lo":41,"hi":118,"n":3,"rr":75,"mr":78},{"m":"vista-9b","r":68,"s":78.83,"lo":50,"hi":125,"n":3,"rr":90,"mr":75},{"m":"gpt-5.4-mini","r":69,"s":78.77,"lo":48,"hi":266,"n":3,"rr":219,"mr":80},{"m":"claude-sonnet-5","r":70,"s":78.73,"lo":57,"hi":138,"n":3,"rr":191,"mr":72},{"m":"qwen3-vl-235b-a22b-thinking","r":71,"s":78.48,"lo":53,"hi":84,"n":57,"rr":142,"mr":68},{"m":"qwen3.5-9b","r":72,"s":78.46,"lo":51,"hi":82,"n":45,"rr":106,"mr":61},{"m":"gemini-4-argon","r":73,"s":78.44,"lo":2,"hi":190,"n":4,"rr":79,"mr":96},{"m":"gemini-3.1-flash-lite","r":74,"s":78.26,"lo":51,"hi":100,"n":5,"rr":138,"mr":76},{"m":"holo1.5-72b","r":75,"s":78.25,"lo":54,"hi":109,"n":10,"rr":15,"mr":85},{"m":"minicpm-v-4.7-35b-a3b","r":76,"s":78.2,"lo":49,"hi":105,"n":17,"rr":86,"mr":65},{"m":"mai-ui-8b","r":77,"s":78.19,"lo":51,"hi":125,"n":4,"rr":164,"mr":87},{"m":"qwen3-vl-235b-a22b","r":78,"s":78.17,"lo":54,"hi":90,"n":36,"rr":177,"mr":69},{"m":"gemma-4-31b-it","r":79,"s":78.09,"lo":50,"hi":103,"n":28,"rr":140,"mr":64},{"m":"hy-embodied-vlm-1.0","r":80,"s":78.06,"lo":41,"hi":126,"n":7,"rr":171,"mr":88},{"m":"step-gui-8b","r":81,"s":77.96,"lo":55,"hi":125,"n":3,"rr":123,"mr":90},{"m":"gemini-2.5-pro","r":82,"s":77.84,"lo":57,"hi":113,"n":70,"rr":216,"mr":70},{"m":"o4-mini-high","r":83,"s":77.58,"lo":54,"hi":136,"n":3,"rr":110,"mr":97},{"m":"step3-vl-10b-pacore","r":84,"s":77.51,"lo":64,"hi":112,"n":6,"rr":22,"mr":84},{"m":"claude-opus-4.5-thinking","r":85,"s":77.37,"lo":58,"hi":179,"n":10,"rr":120,"mr":86},{"m":"ernie-5.0","r":86,"s":77.36,"lo":54,"hi":109,"n":19,"rr":77,"mr":77},{"m":"inkling-small","r":87,"s":77.13,"lo":61,"hi":270,"n":9,"rr":348,"mr":100},{"m":"gta1-32b","r":88,"s":77.13,"lo":66,"hi":135,"n":3,"rr":135,"mr":101},{"m":"rynnbrain1.1-9b","r":89,"s":77.02,"lo":52,"hi":186,"n":6,"rr":176,"mr":108},{"m":"points-gui-g-8b","r":90,"s":76.99,"lo":64,"hi":146,"n":3,"rr":148,"mr":105},{"m":"gpt-5-high","r":91,"s":76.91,"lo":60,"hi":137,"n":31,"rr":161,"mr":79},{"m":"intern-s1-pro","r":92,"s":76.84,"lo":74,"hi":118,"n":7,"rr":151,"mr":99},{"m":"ovis2.6-80b-a3b","r":93,"s":76.8,"lo":55,"hi":121,"n":23,"rr":97,"mr":73},{"m":"nemotron-3.5-super-vl-120b-a12b-nvfp4","r":94,"s":76.71,"lo":71,"hi":116,"n":11,"rr":213,"mr":83},{"m":"exaone-4.5-33b-thinking","r":95,"s":76.55,"lo":76,"hi":119,"n":12,"rr":166,"mr":82},{"m":"gemma-4-26b-a4b-it","r":96,"s":76.52,"lo":64,"hi":144,"n":14,"rr":174,"mr":91},{"m":"seed1.5-vl-thinking","r":97,"s":76.41,"lo":68,"hi":111,"n":46,"rr":209,"mr":81},{"m":"seed-1.5-vl","r":98,"s":76.27,"lo":71,"hi":118,"n":17,"rr":178,"mr":93},{"m":"zwz-8b","r":99,"s":76.26,"lo":51,"hi":165,"n":5,"rr":68,"mr":122},{"m":"ovis2.6-30b-a3b","r":100,"s":76.23,"lo":66,"hi":122,"n":29,"rr":70,"mr":89},{"m":"physbrain1.5-8b","r":101,"s":76.12,"lo":52,"hi":161,"n":6,"rr":167,"mr":120},{"m":"molmopoint-gui-8b","r":102,"s":76.07,"lo":72,"hi":161,"n":3,"rr":139,"mr":115},{"m":"claude-opus-4.5","r":103,"s":76.03,"lo":71,"hi":143,"n":30,"rr":169,"mr":92},{"m":"ui-venus-72b","r":104,"s":76.01,"lo":73,"hi":197,"n":11,"rr":63,"mr":118},{"m":"holo2-8b","r":105,"s":75.99,"lo":74,"hi":142,"n":7,"rr":118,"mr":119},{"m":"keye-vl-2.0-30b-a3b","r":106,"s":75.97,"lo":79,"hi":184,"n":3,"rr":42,"mr":121},{"m":"step-gui-4b","r":107,"s":75.97,"lo":75,"hi":142,"n":4,"rr":227,"mr":117},{"m":"vista-4b","r":108,"s":75.89,"lo":77,"hi":166,"n":3,"rr":159,"mr":126},{"m":"claude-sonnet-4.6","r":109,"s":75.88,"lo":75,"hi":253,"n":3,"rr":284,"mr":125},{"m":"qwen3-vl-32b-instruct","r":110,"s":75.79,"lo":75,"hi":122,"n":47,"rr":203,"mr":94},{"m":"qwen3-vl-32b-thinking","r":111,"s":75.75,"lo":83,"hi":135,"n":18,"rr":102,"mr":98},{"m":"skywork-r1v4","r":112,"s":75.69,"lo":76,"hi":210,"n":3,"rr":100,"mr":133},{"m":"step3-vl-10b-sere","r":113,"s":75.65,"lo":84,"hi":141,"n":6,"rr":32,"mr":111},{"m":"dots-vlm1","r":114,"s":75.52,"lo":82,"hi":126,"n":24,"rr":69,"mr":95},{"m":"holo1.5-7b","r":115,"s":75.51,"lo":84,"hi":145,"n":10,"rr":28,"mr":128},{"m":"holo2-4b","r":116,"s":75.42,"lo":82,"hi":154,"n":6,"rr":87,"mr":130},{"m":"gpt-5-mini-high","r":117,"s":75.37,"lo":88,"hi":144,"n":15,"rr":228,"mr":109},{"m":"comet-60b-a12b-fp8","r":118,"s":75.26,"lo":88,"hi":141,"n":11,"rr":250,"mr":102},{"m":"comet-60b-a12b","r":119,"s":75.18,"lo":88,"hi":148,"n":11,"rr":251,"mr":103},{"m":"zwz-4b","r":120,"s":75.15,"lo":34,"hi":179,"n":5,"rr":91,"mr":136},{"m":"qwen3.5-omni-flash","r":121,"s":75.1,"lo":87,"hi":136,"n":24,"rr":153,"mr":106},{"m":"robobrain2.5-8b","r":122,"s":75.03,"lo":75,"hi":206,"n":6,"rr":226,"mr":139},{"m":"qwen3-vl-235b-a22b-instruct","r":123,"s":75.03,"lo":87,"hi":139,"n":11,"rr":65,"mr":129},{"m":"gpt-5","r":124,"s":74.93,"lo":75,"hi":166,"n":52,"rr":173,"mr":107},{"m":"gpt-5.4-nano","r":125,"s":74.84,"lo":95,"hi":152,"n":3,"rr":308,"mr":131},{"m":"qwen3.5-4b","r":126,"s":74.8,"lo":90,"hi":144,"n":51,"rr":180,"mr":104},{"m":"comet-60b-a12b-nvfp4","r":127,"s":74.7,"lo":97,"hi":155,"n":11,"rr":262,"mr":110},{"m":"gui-owl-7b","r":128,"s":74.66,"lo":82,"hi":169,"n":4,"rr":263,"mr":141},{"m":"step3-vl-10b","r":129,"s":74.64,"lo":95,"hi":142,"n":18,"rr":154,"mr":113},{"m":"ming-flash-omni-2.0","r":130,"s":74.6,"lo":96,"hi":149,"n":15,"rr":85,"mr":123},{"m":"interfaze","r":131,"s":74.57,"lo":85,"hi":321,"n":3,"rr":136,"mr":146},{"m":"glm-4.6v","r":132,"s":74.52,"lo":102,"hi":144,"n":37,"rr":181,"mr":112},{"m":"zdtaichu5.0-9b","r":133,"s":74.51,"lo":98,"hi":170,"n":9,"rr":111,"mr":124},{"m":"nemotron-3-nano-omni-30b-a3b-reasoning","r":134,"s":74.49,"lo":95,"hi":165,"n":6,"rr":364,"mr":135},{"m":"interfaze-1.1-lite","r":135,"s":74.38,"lo":88,"hi":304,"n":3,"rr":172,"mr":144},{"m":"ui-venus-1.5-2b","r":136,"s":74.32,"lo":100,"hi":175,"n":4,"rr":288,"mr":140},{"m":"ovisocr3","r":137,"s":74.27,"lo":88,"hi":209,"n":3,"rr":188,"mr":142},{"m":"gui-owl-32b","r":138,"s":74.06,"lo":103,"hi":187,"n":3,"rr":224,"mr":147},{"m":"gpt-5-mini","r":139,"s":74.04,"lo":102,"hi":174,"n":50,"rr":195,"mr":114},{"m":"seed2.0-mini","r":140,"s":74.04,"lo":88,"hi":219,"n":5,"rr":286,"mr":149},{"m":"opencua-32b","r":141,"s":73.96,"lo":113,"hi":180,"n":3,"rr":230,"mr":148},{"m":"grok-4.2","r":142,"s":73.96,"lo":77,"hi":196,"n":4,"rr":367,"mr":143},{"m":"qwen3-vl-30b-a3b-instruct","r":143,"s":73.91,"lo":107,"hi":154,"n":62,"rr":229,"mr":116},{"m":"glm-4.5v","r":144,"s":73.87,"lo":106,"hi":154,"n":38,"rr":217,"mr":127},{"m":"claude-3.7-sonnet-thinking","r":145,"s":73.78,"lo":100,"hi":195,"n":12,"rr":223,"mr":132},{"m":"qwen3-vl-30b-a3b-thinking","r":146,"s":73.62,"lo":116,"hi":163,"n":10,"rr":165,"mr":145},{"m":"gta1-7b","r":147,"s":73.53,"lo":115,"hi":196,"n":3,"rr":232,"mr":155},{"m":"hy-embodied-0.5-mot-2b","r":148,"s":73.52,"lo":79,"hi":201,"n":7,"rr":285,"mr":154},{"m":"embodied-r1.5-8b","r":149,"s":73.4,"lo":80,"hi":227,"n":6,"rr":245,"mr":164},{"m":"ernie-4.5-vl-28b-a3b-thinking","r":150,"s":73.23,"lo":89,"hi":177,"n":17,"rr":133,"mr":137},{"m":"claude-4.5-sonnet-thinking","r":151,"s":73.02,"lo":109,"hi":218,"n":4,"rr":353,"mr":161},{"m":"molmo2-er","r":152,"s":72.89,"lo":121,"hi":204,"n":5,"rr":259,"mr":162},{"m":"claude-4.5-haiku","r":153,"s":72.79,"lo":125,"hi":174,"n":7,"rr":411,"mr":152},{"m":"mai-ui-2b","r":154,"s":72.77,"lo":115,"hi":195,"n":4,"rr":350,"mr":168},{"m":"qianfan-ocr","r":155,"s":72.69,"lo":45,"hi":240,"n":9,"rr":119,"mr":167},{"m":"deepseek-v4-flash-vision-exp","r":156,"s":72.63,"lo":105,"hi":266,"n":3,"rr":270,"mr":177},{"m":"ace-brain-0.5-8b","r":157,"s":72.61,"lo":113,"hi":223,"n":6,"rr":261,"mr":173},{"m":"ui-tars-1.5-7b","r":158,"s":72.55,"lo":102,"hi":264,"n":11,"rr":141,"mr":171},{"m":"llada-ui","r":159,"s":72.54,"lo":125,"hi":202,"n":3,"rr":302,"mr":159},{"m":"claude-sonnet-4.5","r":160,"s":72.47,"lo":105,"hi":197,"n":46,"rr":215,"mr":134},{"m":"qwen-drive-1.0-4b","r":161,"s":72.45,"lo":128,"hi":176,"n":13,"rr":297,"mr":138},{"m":"egm-8b","r":162,"s":72.44,"lo":80,"hi":235,"n":3,"rr":1,"mr":185},{"m":"molmo2-gui-8b","r":163,"s":72.21,"lo":117,"hi":246,"n":3,"rr":235,"mr":176},{"m":"ui-venus-7b","r":164,"s":72.2,"lo":129,"hi":215,"n":11,"rr":146,"mr":170},{"m":"groundnext-7b","r":165,"s":72.13,"lo":120,"hi":238,"n":3,"rr":241,"mr":180},{"m":"reka-edge-2603","r":166,"s":72.12,"lo":105,"hi":242,"n":3,"rr":76,"mr":193},{"m":"gpt-5.1","r":167,"s":72.06,"lo":90,"hi":473,"n":12,"rr":359,"mr":181},{"m":"opencua-7b","r":168,"s":71.94,"lo":144,"hi":206,"n":3,"rr":298,"mr":178},{"m":"internvl3.5-241b","r":169,"s":71.88,"lo":138,"hi":216,"n":3,"rr":193,"mr":179},{"m":"holo1.5-3b","r":170,"s":71.63,"lo":140,"hi":217,"n":10,"rr":81,"mr":183},{"m":"claude-opus-4.1","r":171,"s":71.57,"lo":138,"hi":199,"n":29,"rr":283,"mr":150},{"m":"jedi-7b","r":172,"s":71.53,"lo":148,"hi":218,"n":3,"rr":306,"mr":196},{"m":"command-a-plus-05-2026","r":173,"s":71.44,"lo":133,"hi":202,"n":5,"rr":190,"mr":163},{"m":"gpt-4.1-mini","r":174,"s":71.44,"lo":143,"hi":220,"n":3,"rr":295,"mr":184},{"m":"qwen2.5-vl-72b","r":175,"s":71.41,"lo":137,"hi":203,"n":34,"rr":162,"mr":153},{"m":"gpt-4.1","r":176,"s":71.33,"lo":102,"hi":239,"n":6,"rr":420,"mr":187},{"m":"rynnbrain-30b-a3b","r":177,"s":71.32,"lo":135,"hi":229,"n":11,"rr":149,"mr":172},{"m":"longcat-next","r":178,"s":71.29,"lo":144,"hi":199,"n":18,"rr":187,"mr":156},{"m":"glm-4.6v-flash","r":179,"s":71.25,"lo":138,"hi":188,"n":27,"rr":324,"mr":157},{"m":"pelican-vl-72b","r":180,"s":71.2,"lo":129,"hi":230,"n":11,"rr":170,"mr":194},{"m":"qwen3-vl-8b-thinking","r":181,"s":71.19,"lo":145,"hi":199,"n":27,"rr":121,"mr":165},{"m":"apriel-1.6-15b-thinker","r":182,"s":71.18,"lo":139,"hi":193,"n":11,"rr":247,"mr":160},{"m":"gemini-2.5-flash","r":183,"s":71.08,"lo":138,"hi":215,"n":47,"rr":199,"mr":151},{"m":"nova-2-omni","r":184,"s":71.04,"lo":149,"hi":283,"n":4,"rr":88,"mr":202},{"m":"gemini-2.5-flash-thinking","r":185,"s":70.79,"lo":147,"hi":222,"n":11,"rr":36,"mr":174},{"m":"qwen3-vl-8b-instruct","r":186,"s":70.75,"lo":152,"hi":197,"n":65,"rr":255,"mr":158},{"m":"rynnbrain-8b","r":187,"s":70.67,"lo":138,"hi":238,"n":11,"rr":152,"mr":191},{"m":"cogvlm-grounding-generalist","r":188,"s":70.35,"lo":114,"hi":252,"n":3,"rr":2,"mr":231},{"m":"internvl2-76b","r":189,"s":70.22,"lo":127,"hi":248,"n":3,"rr":3,"mr":224},{"m":"o1","r":190,"s":70.22,"lo":154,"hi":239,"n":3,"rr":279,"mr":199},{"m":"mimo-vl-7b-rl-2508","r":191,"s":70.19,"lo":153,"hi":209,"n":15,"rr":175,"mr":192},{"m":"qwen3-omni-30b-a3b-thinking","r":192,"s":70.18,"lo":157,"hi":212,"n":11,"rr":37,"mr":190},{"m":"mimo-vl-7b-rl","r":193,"s":69.98,"lo":157,"hi":214,"n":37,"rr":184,"mr":175},{"m":"r-4b-base","r":194,"s":69.97,"lo":157,"hi":240,"n":8,"rr":264,"mr":205},{"m":"gemini-robotics-er-1.5-thinking","r":195,"s":69.94,"lo":165,"hi":268,"n":5,"rr":319,"mr":215},{"m":"infinity-parser2-pro","r":196,"s":69.94,"lo":148,"hi":238,"n":9,"rr":29,"mr":188},{"m":"qwen3-vl-4b-thinking","r":197,"s":69.9,"lo":166,"hi":218,"n":36,"rr":310,"mr":182},{"m":"qwen2.5-vl-72b-instruct","r":198,"s":69.86,"lo":153,"hi":226,"n":50,"rr":346,"mr":169},{"m":"gemini-2.5-flash-lite","r":199,"s":69.85,"lo":166,"hi":224,"n":39,"rr":275,"mr":166},{"m":"minicpm-o-4.5-thinking","r":200,"s":69.78,"lo":159,"hi":239,"n":11,"rr":40,"mr":197},{"m":"openpangu-vl-7b","r":201,"s":69.75,"lo":140,"hi":217,"n":21,"rr":112,"mr":186},{"m":"zwz-7b","r":202,"s":69.64,"lo":97,"hi":290,"n":5,"rr":163,"mr":220},{"m":"llama-4-maverick","r":203,"s":69.58,"lo":161,"hi":221,"n":5,"rr":73,"mr":207},{"m":"llama-4-maverick-17b-128e-instruct","r":204,"s":69.58,"lo":162,"hi":222,"n":5,"rr":74,"mr":208},{"m":"physbrain1.5-2b","r":205,"s":69.48,"lo":105,"hi":260,"n":6,"rr":299,"mr":217},{"m":"grok-4","r":206,"s":69.4,"lo":111,"hi":248,"n":4,"rr":248,"mr":223},{"m":"robobrain-2.5-4b","r":207,"s":69.35,"lo":141,"hi":282,"n":6,"rr":382,"mr":226},{"m":"claude-sonnet-4","r":208,"s":69.31,"lo":176,"hi":229,"n":58,"rr":355,"mr":189},{"m":"glm-4.1v","r":209,"s":69.28,"lo":173,"hi":221,"n":30,"rr":318,"mr":198},{"m":"grok-4.1-fast","r":210,"s":69.21,"lo":152,"hi":365,"n":4,"rr":457,"mr":234},{"m":"ui-tars-72b","r":211,"s":69.19,"lo":178,"hi":248,"n":3,"rr":496,"mr":222},{"m":"ferret-v2-13b","r":212,"s":69.15,"lo":131,"hi":264,"n":3,"rr":5,"mr":247},{"m":"ferret-v2-7b","r":213,"s":69.15,"lo":130,"hi":265,"n":3,"rr":4,"mr":248},{"m":"minicpm-o-4.5","r":214,"s":69.08,"lo":176,"hi":234,"n":21,"rr":157,"mr":201},{"m":"step-3","r":215,"s":68.99,"lo":159,"hi":242,"n":22,"rr":354,"mr":204},{"m":"holotron-12b","r":216,"s":68.92,"lo":179,"hi":250,"n":5,"rr":144,"mr":232},{"m":"joyai-vl-interaction","r":217,"s":68.88,"lo":148,"hi":241,"n":5,"rr":278,"mr":227},{"m":"rynnbrain-4b","r":218,"s":68.69,"lo":163,"hi":252,"n":11,"rr":156,"mr":213},{"m":"qwen2-vl-72b-instruct","r":219,"s":68.67,"lo":146,"hi":263,"n":21,"rr":108,"mr":195},{"m":"hunyuanocr-1.5","r":220,"s":68.61,"lo":164,"hi":277,"n":3,"rr":317,"mr":238},{"m":"mimo-vl-7b-sft","r":221,"s":68.52,"lo":178,"hi":244,"n":36,"rr":205,"mr":203},{"m":"longcat-flash-omni","r":222,"s":68.45,"lo":180,"hi":246,"n":7,"rr":80,"mr":233},{"m":"penguin-vl-8b","r":223,"s":68.39,"lo":138,"hi":280,"n":17,"rr":202,"mr":214},{"m":"gpt-4.5","r":224,"s":68.38,"lo":150,"hi":254,"n":6,"rr":179,"mr":219},{"m":"qwen2.5-vl-32b-instruct","r":225,"s":68.23,"lo":177,"hi":260,"n":7,"rr":342,"mr":235},{"m":"apriel-1.5-15b-thinker","r":226,"s":68.11,"lo":190,"hi":245,"n":11,"rr":329,"mr":211},{"m":"molmopoint-8b","r":227,"s":68.02,"lo":179,"hi":266,"n":22,"rr":194,"mr":216},{"m":"mistral-medium-3","r":228,"s":67.9,"lo":157,"hi":285,"n":4,"rr":14,"mr":250},{"m":"claude-3.7-sonnet","r":229,"s":67.8,"lo":178,"hi":262,"n":30,"rr":260,"mr":210},{"m":"deepseek-v4.1-flash-base","r":230,"s":67.79,"lo":189,"hi":292,"n":4,"rr":59,"mr":236},{"m":"internvl2.5-78b","r":231,"s":67.6,"lo":180,"hi":250,"n":34,"rr":185,"mr":200},{"m":"internvl3.5-30b-a3b-flash","r":232,"s":67.6,"lo":188,"hi":257,"n":17,"rr":234,"mr":218},{"m":"texthawk2","r":233,"s":67.56,"lo":156,"hi":277,"n":3,"rr":6,"mr":265},{"m":"qwen3-omni-30b-a3b-instruct","r":234,"s":67.54,"lo":194,"hi":267,"n":36,"rr":236,"mr":206},{"m":"qwen3-vl-4b-instruct","r":235,"s":67.44,"lo":204,"hi":250,"n":67,"rr":320,"mr":209},{"m":"gemini-robotics-er-1.5","r":236,"s":67.4,"lo":209,"hi":261,"n":5,"rr":361,"mr":259},{"m":"manzano-30b","r":237,"s":67.1,"lo":203,"hi":268,"n":12,"rr":31,"mr":228},{"m":"molmo2-8b","r":238,"s":67.07,"lo":181,"hi":282,"n":22,"rr":201,"mr":237},{"m":"llama-4-scout-17b","r":239,"s":67.04,"lo":207,"hi":250,"n":5,"rr":125,"mr":245},{"m":"llama-4-scout-17b-16e","r":240,"s":67.04,"lo":208,"hi":251,"n":5,"rr":126,"mr":246},{"m":"gemma-4-12b-it","r":241,"s":67.04,"lo":126,"hi":364,"n":13,"rr":207,"mr":212},{"m":"doubao-1.5-vision-pro","r":242,"s":66.92,"lo":210,"hi":271,"n":6,"rr":341,"mr":239},{"m":"keye-vl-8b","r":243,"s":66.72,"lo":192,"hi":283,"n":11,"rr":417,"mr":241},{"m":"ui-tars-7b","r":244,"s":66.72,"lo":191,"hi":298,"n":4,"rr":472,"mr":261},{"m":"internvl3-78b","r":245,"s":66.42,"lo":185,"hi":273,"n":7,"rr":409,"mr":254},{"m":"gemini-2.0-pro","r":246,"s":66.17,"lo":220,"hi":267,"n":11,"rr":254,"mr":244},{"m":"oryx-1.5-32b","r":247,"s":66.15,"lo":234,"hi":267,"n":4,"rr":204,"mr":281},{"m":"mistral-small-3.2-24b-instruct","r":248,"s":66.11,"lo":211,"hi":285,"n":6,"rr":114,"mr":262},{"m":"youtu-vl-4b-instruct","r":249,"s":66.1,"lo":211,"hi":275,"n":27,"rr":243,"mr":229},{"m":"glm-4.1v-9b","r":250,"s":66.09,"lo":189,"hi":289,"n":12,"rr":115,"mr":260},{"m":"glm-4.1v-9b-thinking","r":251,"s":66.08,"lo":205,"hi":291,"n":20,"rr":222,"mr":257},{"m":"mistral-small-3.1-24b-instruct","r":252,"s":65.99,"lo":195,"hi":281,"n":5,"rr":34,"mr":267},{"m":"eagle2.5-8b","r":253,"s":65.96,"lo":216,"hi":283,"n":19,"rr":168,"mr":252},{"m":"qwen2-vl-72b","r":254,"s":65.92,"lo":209,"hi":285,"n":30,"rr":208,"mr":221},{"m":"holo1-7b","r":255,"s":65.72,"lo":210,"hi":317,"n":11,"rr":238,"mr":274},{"m":"cosmos3-nano","r":256,"s":65.67,"lo":202,"hi":285,"n":16,"rr":368,"mr":249},{"m":"pixtral-large-2411","r":257,"s":65.67,"lo":218,"hi":282,"n":8,"rr":257,"mr":266},{"m":"internvl2.5-38b","r":258,"s":65.67,"lo":210,"hi":275,"n":31,"rr":240,"mr":225},{"m":"gpt-4o-2024-11-20","r":259,"s":65.56,"lo":240,"hi":266,"n":3,"rr":158,"mr":273},{"m":"command-a-vision-07-2025","r":260,"s":65.51,"lo":239,"hi":276,"n":4,"rr":276,"mr":272},{"m":"claude-3.5-sonnet-20240620","r":261,"s":65.44,"lo":216,"hi":296,"n":21,"rr":221,"mr":230},{"m":"molmo2-4b","r":262,"s":65.22,"lo":199,"hi":328,"n":28,"rr":206,"mr":258},{"m":"minicpm-v-4.5-8b","r":263,"s":65.22,"lo":216,"hi":290,"n":29,"rr":197,"mr":256},{"m":"internvl2-pro","r":264,"s":65.06,"lo":210,"hi":291,"n":11,"rr":94,"mr":242},{"m":"claude-3.5-sonnet","r":265,"s":64.97,"lo":211,"hi":292,"n":24,"rr":242,"mr":243},{"m":"ovis2-8b","r":266,"s":64.9,"lo":249,"hi":273,"n":3,"rr":328,"mr":291},{"m":"kimi-vl-a3b-thinking-2506","r":267,"s":64.9,"lo":232,"hi":291,"n":31,"rr":422,"mr":255},{"m":"gpt-4o","r":268,"s":64.87,"lo":226,"hi":300,"n":56,"rr":309,"mr":240},{"m":"qwen3.5-2b","r":269,"s":64.69,"lo":231,"hi":292,"n":46,"rr":315,"mr":251},{"m":"internvl3-38b","r":270,"s":64.69,"lo":190,"hi":301,"n":7,"rr":426,"mr":279},{"m":"internvl3.5-gpt-oss-20b-a4b","r":271,"s":64.42,"lo":236,"hi":299,"n":15,"rr":96,"mr":278},{"m":"cosmos-reason2-8b","r":272,"s":64.25,"lo":244,"hi":304,"n":25,"rr":331,"mr":263},{"m":"moondream-9b-a2b","r":273,"s":64.23,"lo":126,"hi":353,"n":7,"rr":7,"mr":301},{"m":"gpt-4o-0513","r":274,"s":64.19,"lo":217,"hi":299,"n":10,"rr":66,"mr":282},{"m":"pelican-vl-7b","r":275,"s":64.08,"lo":228,"hi":312,"n":11,"rr":272,"mr":288},{"m":"gpt-4o-2024-05-13","r":276,"s":63.95,"lo":248,"hi":303,"n":31,"rr":265,"mr":253},{"m":"keye-vl-1.5-8b","r":277,"s":63.91,"lo":220,"hi":317,"n":22,"rr":210,"mr":280},{"m":"molmo-72b","r":278,"s":63.9,"lo":191,"hi":321,"n":18,"rr":127,"mr":264},{"m":"mage-vl","r":279,"s":63.81,"lo":239,"hi":302,"n":18,"rr":249,"mr":284},{"m":"internvl3-14b","r":280,"s":63.61,"lo":246,"hi":301,"n":5,"rr":296,"mr":286},{"m":"qvq-72b","r":281,"s":63.47,"lo":224,"hi":311,"n":3,"rr":404,"mr":297},{"m":"xiaomi-ocr-0","r":282,"s":63.42,"lo":233,"hi":355,"n":3,"rr":419,"mr":307},{"m":"plm-8b","r":283,"s":63.38,"lo":213,"hi":344,"n":19,"rr":252,"mr":295},{"m":"dots.mocr","r":284,"s":63.38,"lo":240,"hi":338,"n":10,"rr":134,"mr":287},{"m":"molmopoint-o-7b","r":285,"s":63.37,"lo":115,"hi":358,"n":12,"rr":116,"mr":294},{"m":"d1-3b","r":286,"s":63.29,"lo":220,"hi":328,"n":7,"rr":198,"mr":290},{"m":"gpt-5-mini-minimal","r":287,"s":63.28,"lo":255,"hi":310,"n":41,"rr":403,"mr":268},{"m":"gpt-03-cua","r":288,"s":63.25,"lo":223,"hi":333,"n":4,"rr":493,"mr":306},{"m":"mimo-embodied-7b","r":289,"s":63.18,"lo":240,"hi":350,"n":20,"rr":366,"mr":292},{"m":"gpt-5-minimal","r":290,"s":63.04,"lo":235,"hi":342,"n":21,"rr":344,"mr":270},{"m":"gemini-2.0-flash","r":291,"s":63,"lo":207,"hi":392,"n":5,"rr":307,"mr":309},{"m":"ferret-13b","r":292,"s":62.91,"lo":229,"hi":328,"n":3,"rr":8,"mr":335},{"m":"internvl3.5-8b","r":293,"s":62.9,"lo":258,"hi":311,"n":50,"rr":321,"mr":271},{"m":"ovis2-34b","r":294,"s":62.82,"lo":205,"hi":329,"n":3,"rr":246,"mr":311},{"m":"glm-ocr","r":295,"s":62.75,"lo":245,"hi":406,"n":3,"rr":451,"mr":326},{"m":"molmo2-o-7b","r":296,"s":62.63,"lo":226,"hi":347,"n":19,"rr":214,"mr":298},{"m":"minicpm-v-4.7-1b","r":297,"s":62.49,"lo":258,"hi":323,"n":16,"rr":381,"mr":269},{"m":"minicpm-v-4.6-thinking","r":298,"s":62.34,"lo":267,"hi":335,"n":18,"rr":369,"mr":283},{"m":"deepseek-vl2","r":299,"s":62.28,"lo":263,"hi":321,"n":15,"rr":57,"mr":285},{"m":"gemini-1.5-pro","r":300,"s":62.21,"lo":268,"hi":331,"n":36,"rr":289,"mr":277},{"m":"internvl2-llama-3-76b","r":301,"s":62.17,"lo":272,"hi":322,"n":37,"rr":237,"mr":276},{"m":"internvl2.5-26b","r":302,"s":61.95,"lo":256,"hi":326,"n":30,"rr":267,"mr":275},{"m":"videotemp-o3-7b","r":303,"s":61.85,"lo":167,"hi":358,"n":5,"rr":454,"mr":321},{"m":"ovis2-16b","r":304,"s":61.79,"lo":224,"hi":341,"n":3,"rr":271,"mr":328},{"m":"qwen2.5-vl-7b","r":305,"s":61.75,"lo":270,"hi":326,"n":55,"rr":396,"mr":289},{"m":"qwen3-vl-2b-thinking","r":306,"s":61.69,"lo":273,"hi":326,"n":31,"rr":437,"mr":293},{"m":"uground-v1-7b","r":307,"s":61.67,"lo":203,"hi":371,"n":4,"rr":421,"mr":334},{"m":"manzano-3b","r":308,"s":61.53,"lo":278,"hi":329,"n":12,"rr":78,"mr":318},{"m":"glm-4v-plus","r":309,"s":61.44,"lo":280,"hi":329,"n":12,"rr":147,"mr":300},{"m":"holo1-3b","r":310,"s":61.4,"lo":276,"hi":367,"n":10,"rr":316,"mr":330},{"m":"kimi-vl-a3b-thinking","r":311,"s":61.4,"lo":261,"hi":353,"n":12,"rr":233,"mr":316},{"m":"rynnbrain-2b","r":312,"s":61.3,"lo":264,"hi":348,"n":11,"rr":269,"mr":317},{"m":"kanana-1.5-o-9.8b-instruct-2602","r":313,"s":61.19,"lo":276,"hi":338,"n":12,"rr":340,"mr":305},{"m":"videochat-flash-7b","r":314,"s":60.93,"lo":256,"hi":370,"n":7,"rr":385,"mr":345},{"m":"grok-4-fast-thinking","r":315,"s":60.86,"lo":252,"hi":359,"n":11,"rr":434,"mr":319},{"m":"bagel-7b-mot","r":316,"s":60.69,"lo":277,"hi":355,"n":18,"rr":256,"mr":308},{"m":"fastvlm-7b","r":317,"s":60.63,"lo":237,"hi":366,"n":11,"rr":93,"mr":322},{"m":"minicpm-v-4.6","r":318,"s":60.58,"lo":290,"hi":345,"n":26,"rr":380,"mr":296},{"m":"internvl3.5-4b","r":319,"s":60.54,"lo":292,"hi":337,"n":46,"rr":322,"mr":299},{"m":"robobrain-2.0","r":320,"s":60.44,"lo":264,"hi":361,"n":12,"rr":268,"mr":333},{"m":"deepseek-vl2-small","r":321,"s":60.36,"lo":285,"hi":350,"n":15,"rr":89,"mr":310},{"m":"kimi-vl-a3b-instruct","r":322,"s":60.33,"lo":253,"hi":362,"n":12,"rr":253,"mr":327},{"m":"qwen3-vl-2b-instruct","r":323,"s":60.26,"lo":294,"hi":339,"n":58,"rr":435,"mr":302},{"m":"aria","r":324,"s":60.22,"lo":288,"hi":339,"n":7,"rr":101,"mr":332},{"m":"qwen2-vl-7b-instruct","r":325,"s":60.07,"lo":281,"hi":372,"n":21,"rr":220,"mr":304},{"m":"internvl-8b","r":326,"s":60.07,"lo":291,"hi":340,"n":34,"rr":282,"mr":313},{"m":"nvlm-d-72b","r":327,"s":59.92,"lo":280,"hi":344,"n":11,"rr":145,"mr":314},{"m":"zaya1-vl-8b","r":328,"s":59.87,"lo":287,"hi":361,"n":15,"rr":137,"mr":325},{"m":"penguin-vl-2b","r":329,"s":59.85,"lo":243,"hi":358,"n":17,"rr":332,"mr":324},{"m":"plm-3b","r":330,"s":59.6,"lo":283,"hi":371,"n":19,"rr":303,"mr":336},{"m":"internvl2-40b","r":331,"s":59.48,"lo":294,"hi":358,"n":31,"rr":323,"mr":303},{"m":"shikra-13b","r":332,"s":59.46,"lo":274,"hi":364,"n":4,"rr":25,"mr":373},{"m":"internvl3-9b","r":333,"s":59.13,"lo":287,"hi":352,"n":5,"rr":387,"mr":339},{"m":"gpt-5-nano","r":334,"s":59.12,"lo":274,"hi":388,"n":37,"rr":401,"mr":312},{"m":"qwen3.5-ocr","r":335,"s":59.07,"lo":300,"hi":350,"n":3,"rr":449,"mr":362},{"m":"llava-onevision-7b-si","r":336,"s":59.06,"lo":265,"hi":355,"n":3,"rr":398,"mr":358},{"m":"shikra-7b","r":337,"s":59.03,"lo":280,"hi":369,"n":3,"rr":18,"mr":381},{"m":"lfm2.5-vl-3b","r":338,"s":58.88,"lo":305,"hi":357,"n":22,"rr":277,"mr":329},{"m":"gemini-1.5-flash","r":339,"s":58.81,"lo":301,"hi":355,"n":14,"rr":225,"mr":331},{"m":"cosmos-reason1-7b","r":340,"s":58.81,"lo":306,"hi":358,"n":13,"rr":492,"mr":338},{"m":"llava-onevision-2-8b","r":341,"s":58.78,"lo":311,"hi":360,"n":11,"rr":442,"mr":323},{"m":"bagel-14b","r":342,"s":58.74,"lo":272,"hi":382,"n":11,"rr":128,"mr":349},{"m":"gemini-1.0-ultra","r":343,"s":58.69,"lo":289,"hi":369,"n":7,"rr":122,"mr":346},{"m":"internvl2.5-8b","r":344,"s":58.57,"lo":311,"hi":363,"n":33,"rr":290,"mr":315},{"m":"internvl3-8b","r":345,"s":58.4,"lo":314,"hi":363,"n":11,"rr":475,"mr":340},{"m":"llava-onevision-72b","r":346,"s":58.36,"lo":317,"hi":362,"n":31,"rr":327,"mr":320},{"m":"gpt-4o-mini","r":347,"s":58.32,"lo":308,"hi":373,"n":9,"rr":414,"mr":343},{"m":"ovis1.6-gemma2-9b","r":348,"s":58.26,"lo":297,"hi":388,"n":7,"rr":273,"mr":352},{"m":"claude-3.5-sonnet-20241022","r":349,"s":58.13,"lo":272,"hi":370,"n":3,"rr":395,"mr":359},{"m":"llava-video-7b","r":350,"s":58.05,"lo":306,"hi":384,"n":7,"rr":430,"mr":369},{"m":"videollama2-72b","r":351,"s":57.98,"lo":303,"hi":360,"n":3,"rr":363,"mr":377},{"m":"infinity-parser2-flash","r":352,"s":57.98,"lo":308,"hi":373,"n":9,"rr":192,"mr":350},{"m":"moss-vl-realtime","r":353,"s":57.84,"lo":296,"hi":364,"n":5,"rr":448,"mr":360},{"m":"llama-3.2v-90b-instruct","r":354,"s":57.8,"lo":319,"hi":363,"n":15,"rr":212,"mr":342},{"m":"qwen2.5-omni-7b","r":355,"s":57.72,"lo":317,"hi":368,"n":20,"rr":313,"mr":341},{"m":"gemma-3-27b-vl","r":356,"s":57.47,"lo":323,"hi":383,"n":30,"rr":483,"mr":347},{"m":"llada2.0-uni","r":357,"s":57.38,"lo":331,"hi":366,"n":18,"rr":280,"mr":337},{"m":"qwen2.5-vl-3b","r":358,"s":57.38,"lo":321,"hi":375,"n":30,"rr":311,"mr":344},{"m":"robobrain-2.0-7b","r":359,"s":57.25,"lo":306,"hi":441,"n":11,"rr":400,"mr":374},{"m":"jina-vlm-2.4b-20251117","r":360,"s":56.88,"lo":325,"hi":369,"n":9,"rr":183,"mr":357},{"m":"phi-4-reasoning-vision-15b","r":361,"s":56.43,"lo":309,"hi":408,"n":20,"rr":337,"mr":356},{"m":"internvl2-26b","r":362,"s":55.86,"lo":339,"hi":389,"n":31,"rr":378,"mr":348},{"m":"gpt-4o-mini-2024-07-18","r":363,"s":55.64,"lo":326,"hi":390,"n":8,"rr":281,"mr":371},{"m":"gpt-4-turbo-2024-04-09","r":364,"s":55.57,"lo":316,"hi":400,"n":11,"rr":211,"mr":367},{"m":"gpt-4v","r":365,"s":55.55,"lo":341,"hi":394,"n":31,"rr":352,"mr":353},{"m":"qwen2-vl-7b","r":366,"s":55.37,"lo":334,"hi":397,"n":37,"rr":339,"mr":351},{"m":"mm1.5-30b","r":367,"s":55.14,"lo":344,"hi":398,"n":11,"rr":160,"mr":375},{"m":"internvl2.5-4b","r":368,"s":55.08,"lo":350,"hi":389,"n":31,"rr":372,"mr":354},{"m":"internvl3.5-2b","r":369,"s":54.94,"lo":354,"hi":396,"n":31,"rr":376,"mr":361},{"m":"molmo-7b-d","r":370,"s":54.87,"lo":278,"hi":404,"n":19,"rr":231,"mr":363},{"m":"pixtral-12b","r":371,"s":54.87,"lo":346,"hi":396,"n":17,"rr":314,"mr":355},{"m":"gemma-3-27b-it","r":372,"s":54.72,"lo":338,"hi":405,"n":27,"rr":390,"mr":365},{"m":"minicpm-o-2.6","r":373,"s":54.57,"lo":327,"hi":407,"n":16,"rr":440,"mr":372},{"m":"blip-3o-4b","r":374,"s":54.4,"lo":324,"hi":405,"n":5,"rr":266,"mr":403},{"m":"ovis1.5-gemma2-9b","r":375,"s":54.37,"lo":340,"hi":393,"n":4,"rr":375,"mr":390},{"m":"lfm2-vl-3b","r":376,"s":54.35,"lo":349,"hi":400,"n":21,"rr":373,"mr":382},{"m":"cogvlm2-llama3-chinese-chat-19b","r":377,"s":54.22,"lo":317,"hi":410,"n":6,"rr":196,"mr":393},{"m":"grok-1.5v","r":378,"s":54.19,"lo":288,"hi":403,"n":6,"rr":130,"mr":394},{"m":"internlm-xcomposer2.5","r":379,"s":54.12,"lo":355,"hi":402,"n":20,"rr":294,"mr":364},{"m":"qwen3.5-0.8b-thinking","r":380,"s":53.91,"lo":357,"hi":405,"n":18,"rr":455,"mr":378},{"m":"ovis1.5-llama3-8b","r":381,"s":53.55,"lo":346,"hi":403,"n":4,"rr":389,"mr":395},{"m":"minicpm-v-2_6","r":382,"s":53.52,"lo":365,"hi":408,"n":26,"rr":416,"mr":366},{"m":"internvl2-8b","r":383,"s":53.48,"lo":366,"hi":410,"n":37,"rr":377,"mr":368},{"m":"llm-jp-4-vl-9b","r":384,"s":53.48,"lo":346,"hi":425,"n":12,"rr":393,"mr":388},{"m":"llm-jp-4-vl-9b-beta","r":385,"s":53.36,"lo":357,"hi":406,"n":12,"rr":388,"mr":386},{"m":"gpt-4-1106-vision-preview","r":386,"s":53.24,"lo":358,"hi":413,"n":17,"rr":305,"mr":370},{"m":"gemma-4-e4b-it","r":387,"s":53.24,"lo":342,"hi":421,"n":29,"rr":397,"mr":379},{"m":"llada-o","r":388,"s":53.2,"lo":352,"hi":424,"n":18,"rr":358,"mr":389},{"m":"llava-onevision-7b","r":389,"s":53.04,"lo":355,"hi":419,"n":24,"rr":357,"mr":384},{"m":"internvl3-2b","r":390,"s":53.02,"lo":373,"hi":409,"n":20,"rr":336,"mr":380},{"m":"claude-3-sonnet","r":391,"s":52.86,"lo":343,"hi":433,"n":13,"rr":347,"mr":383},{"m":"qwen3.5-0.8b","r":392,"s":52.77,"lo":368,"hi":413,"n":42,"rr":470,"mr":376},{"m":"baichuan-omni","r":393,"s":52.67,"lo":368,"hi":411,"n":11,"rr":345,"mr":401},{"m":"internvl-chat-v1.5","r":394,"s":51.89,"lo":376,"hi":427,"n":27,"rr":413,"mr":385},{"m":"llava-next-110b","r":395,"s":51.86,"lo":359,"hi":414,"n":5,"rr":239,"mr":414},{"m":"internlm-xcomposer2-4khd-7b","r":396,"s":51.47,"lo":377,"hi":425,"n":16,"rr":334,"mr":387},{"m":"llama-3.2v-11b-instruct","r":397,"s":51.32,"lo":371,"hi":423,"n":14,"rr":291,"mr":399},{"m":"north-micro-vision-instruct","r":398,"s":51.32,"lo":366,"hi":439,"n":15,"rr":326,"mr":402},{"m":"ofa-large","r":399,"s":51.21,"lo":323,"hi":464,"n":3,"rr":189,"mr":437},{"m":"reka-flash","r":400,"s":51.19,"lo":376,"hi":421,"n":4,"rr":427,"mr":418},{"m":"molmo-7b-o","r":401,"s":51.18,"lo":315,"hi":454,"n":17,"rr":258,"mr":400},{"m":"unified-io-2-xxl","r":402,"s":51.18,"lo":295,"hi":432,"n":4,"rr":48,"mr":433},{"m":"cogvlm2-llama3-chat-19b","r":403,"s":51.15,"lo":357,"hi":445,"n":12,"rr":274,"mr":407},{"m":"ministral-3-3b-instruct","r":404,"s":51.12,"lo":371,"hi":429,"n":15,"rr":349,"mr":408},{"m":"gemma-3-12b-it","r":405,"s":51.01,"lo":367,"hi":433,"n":11,"rr":446,"mr":413},{"m":"qwen-vl-max","r":406,"s":51,"lo":369,"hi":437,"n":17,"rr":379,"mr":391},{"m":"claude-3-opus","r":407,"s":50.86,"lo":367,"hi":454,"n":23,"rr":406,"mr":392},{"m":"fastvlm-1.5b","r":408,"s":50.68,"lo":376,"hi":438,"n":13,"rr":244,"mr":412},{"m":"hyperclovax-seed-omni-8b","r":409,"s":50.66,"lo":386,"hi":443,"n":14,"rr":441,"mr":411},{"m":"deepseek-vl2-tiny","r":410,"s":50.51,"lo":376,"hi":438,"n":15,"rr":218,"mr":409},{"m":"gemini-pro","r":411,"s":50.47,"lo":386,"hi":431,"n":15,"rr":343,"mr":405},{"m":"aquila-vl-2b","r":412,"s":50.32,"lo":390,"hi":429,"n":13,"rr":356,"mr":404},{"m":"gemma-4-e2b-it","r":413,"s":50.17,"lo":368,"hi":456,"n":38,"rr":453,"mr":396},{"m":"glm-4v-9b","r":414,"s":50.17,"lo":389,"hi":432,"n":15,"rr":335,"mr":397},{"m":"internvl2-4b","r":415,"s":49.9,"lo":397,"hi":439,"n":30,"rr":438,"mr":398},{"m":"moondream2","r":416,"s":49.76,"lo":123,"hi":481,"n":3,"rr":509,"mr":440},{"m":"gemini-1.5-flash-8b-0827","r":417,"s":49.42,"lo":362,"hi":442,"n":5,"rr":292,"mr":435},{"m":"minicpm-llama3-v2.5","r":418,"s":49.32,"lo":404,"hi":438,"n":16,"rr":360,"mr":406},{"m":"deepseek-ocr","r":419,"s":49.31,"lo":324,"hi":507,"n":3,"rr":524,"mr":448},{"m":"cambrian-1-34b","r":420,"s":49.24,"lo":389,"hi":450,"n":14,"rr":300,"mr":423},{"m":"gemini-1.0-pro","r":421,"s":49.13,"lo":407,"hi":444,"n":18,"rr":370,"mr":417},{"m":"llada-v","r":422,"s":49.11,"lo":391,"hi":449,"n":18,"rr":405,"mr":421},{"m":"cambrian-34b","r":423,"s":48.97,"lo":392,"hi":449,"n":19,"rr":362,"mr":415},{"m":"qwen2-vl-2b-instruct","r":424,"s":48.9,"lo":390,"hi":451,"n":21,"rr":371,"mr":420},{"m":"step-1v-32k","r":425,"s":48.77,"lo":391,"hi":456,"n":11,"rr":374,"mr":426},{"m":"claude-3-haiku","r":426,"s":48.72,"lo":390,"hi":471,"n":17,"rr":394,"mr":416},{"m":"internvl2.5-2b","r":427,"s":48.44,"lo":412,"hi":452,"n":31,"rr":444,"mr":410},{"m":"mm1.5-7b","r":428,"s":48.39,"lo":397,"hi":448,"n":9,"rr":304,"mr":429},{"m":"internvl-u","r":429,"s":48.36,"lo":399,"hi":465,"n":18,"rr":410,"mr":424},{"m":"videochat2-hd-mistral","r":430,"s":48.22,"lo":328,"hi":459,"n":4,"rr":466,"mr":452},{"m":"phi-3-vision-4b","r":431,"s":48.15,"lo":398,"hi":456,"n":16,"rr":325,"mr":419},{"m":"blip-3-4b","r":432,"s":47.92,"lo":367,"hi":457,"n":5,"rr":391,"mr":449},{"m":"internvl3-1b","r":433,"s":47.89,"lo":400,"hi":457,"n":5,"rr":501,"mr":438},{"m":"gemini-1.0-pro-vision","r":434,"s":47.49,"lo":394,"hi":467,"n":6,"rr":423,"mr":446},{"m":"bunny-llama3-8b","r":435,"s":47.37,"lo":379,"hi":473,"n":5,"rr":445,"mr":451},{"m":"mini-gemini-hd-34b","r":436,"s":47.29,"lo":407,"hi":457,"n":9,"rr":431,"mr":436},{"m":"qwen2-vl-2b","r":437,"s":47.17,"lo":413,"hi":463,"n":25,"rr":460,"mr":422},{"m":"lfm2.5-vl-1.6b","r":438,"s":46.81,"lo":420,"hi":460,"n":32,"rr":478,"mr":425},{"m":"vila1.5-40b","r":439,"s":46.65,"lo":403,"hi":474,"n":15,"rr":462,"mr":431},{"m":"gpt-5-nano-minimal","r":440,"s":46.6,"lo":400,"hi":469,"n":31,"rr":498,"mr":432},{"m":"phi-4-multimodal-instruct","r":441,"s":46.53,"lo":374,"hi":501,"n":22,"rr":468,"mr":443},{"m":"harmon-1.5b","r":442,"s":46.49,"lo":347,"hi":469,"n":3,"rr":429,"mr":461},{"m":"lfm2-vl-1.6b","r":443,"s":46.34,"lo":403,"hi":469,"n":6,"rr":484,"mr":456},{"m":"internvl3.5-1b","r":444,"s":46.33,"lo":409,"hi":470,"n":6,"rr":490,"mr":454},{"m":"mm1.5-3b","r":445,"s":46.24,"lo":422,"hi":467,"n":12,"rr":287,"mr":441},{"m":"llava-next-34b","r":446,"s":46.12,"lo":421,"hi":465,"n":19,"rr":399,"mr":434},{"m":"qwen-vl-plus","r":447,"s":46,"lo":399,"hi":475,"n":15,"rr":418,"mr":430},{"m":"sharegpt4v-13b","r":448,"s":45.93,"lo":384,"hi":464,"n":3,"rr":495,"mr":457},{"m":"phi-3.5-vision-instruct","r":449,"s":45.92,"lo":429,"hi":473,"n":26,"rr":464,"mr":427},{"m":"cambrian-1-8b","r":450,"s":45.82,"lo":424,"hi":458,"n":12,"rr":293,"mr":447},{"m":"vita","r":451,"s":45.8,"lo":425,"hi":462,"n":13,"rr":408,"mr":445},{"m":"phi-3-vision-128k-instruct","r":452,"s":45.77,"lo":410,"hi":462,"n":5,"rr":443,"mr":459},{"m":"internlm-xcomposer2-vl-7b","r":453,"s":45.45,"lo":411,"hi":482,"n":18,"rr":432,"mr":428},{"m":"molmoe-1b","r":454,"s":45.44,"lo":336,"hi":480,"n":17,"rr":330,"mr":442},{"m":"bunny-4b","r":455,"s":45.21,"lo":327,"hi":474,"n":3,"rr":333,"mr":467},{"m":"xgen-mm-interleave-4b","r":456,"s":44.96,"lo":420,"hi":480,"n":12,"rr":338,"mr":453},{"m":"gemma-3n-e2b-it","r":457,"s":44.84,"lo":434,"hi":483,"n":17,"rr":487,"mr":450},{"m":"internvl-chat-v1.2","r":458,"s":44.35,"lo":405,"hi":492,"n":12,"rr":402,"mr":455},{"m":"internvl2.5-1b","r":459,"s":43.99,"lo":446,"hi":474,"n":30,"rr":477,"mr":439},{"m":"llava-1.6-7b","r":460,"s":43.91,"lo":376,"hi":476,"n":3,"rr":456,"mr":471},{"m":"llava-llama-3-8b","r":461,"s":43.87,"lo":385,"hi":473,"n":4,"rr":471,"mr":466},{"m":"llava-next-llama3","r":462,"s":43.76,"lo":426,"hi":476,"n":7,"rr":383,"mr":462},{"m":"internvl2-2b","r":463,"s":43.51,"lo":447,"hi":479,"n":33,"rr":463,"mr":444},{"m":"paddleocr-vl-1.6","r":464,"s":43.22,"lo":343,"hi":500,"n":3,"rr":519,"mr":475},{"m":"phi-3.5-vision-4b","r":465,"s":43.12,"lo":420,"hi":487,"n":10,"rr":365,"mr":468},{"m":"idefics2-8b","r":466,"s":43,"lo":431,"hi":487,"n":9,"rr":452,"mr":458},{"m":"fastvlm-0.5b","r":467,"s":42.64,"lo":443,"hi":484,"n":11,"rr":301,"mr":465},{"m":"mm1-30b","r":468,"s":42.44,"lo":444,"hi":478,"n":12,"rr":351,"mr":463},{"m":"llava-internlm2-20b-qlora","r":469,"s":42.19,"lo":413,"hi":495,"n":8,"rr":461,"mr":473},{"m":"reka-edge","r":470,"s":42.01,"lo":413,"hi":491,"n":4,"rr":504,"mr":477},{"m":"cogagent-18b","r":471,"s":42.01,"lo":445,"hi":490,"n":10,"rr":465,"mr":464},{"m":"llama-3-vila1.5-8b","r":472,"s":42,"lo":379,"hi":488,"n":4,"rr":473,"mr":482},{"m":"llava-next-7b","r":473,"s":41.9,"lo":375,"hi":486,"n":4,"rr":480,"mr":484},{"m":"mobilevlm-v2-3b","r":474,"s":41.61,"lo":316,"hi":515,"n":3,"rr":458,"mr":490},{"m":"smolvlm2-2.2b","r":475,"s":41.56,"lo":453,"hi":492,"n":29,"rr":486,"mr":460},{"m":"docowl-1.5-chat","r":476,"s":41.46,"lo":449,"hi":489,"n":7,"rr":447,"mr":472},{"m":"dreamllm-7b","r":477,"s":41.11,"lo":325,"hi":505,"n":3,"rr":511,"mr":491},{"m":"emu3-8b","r":478,"s":41.07,"lo":449,"hi":495,"n":9,"rr":392,"mr":478},{"m":"sphinx-v2","r":479,"s":40.82,"lo":450,"hi":496,"n":3,"rr":528,"mr":480},{"m":"llava-1.6-13b","r":480,"s":40.67,"lo":459,"hi":491,"n":11,"rr":467,"mr":476},{"m":"lfm2.5-vl-450m","r":481,"s":40.58,"lo":443,"hi":498,"n":9,"rr":459,"mr":479},{"m":"llava-1.6-mistral-7b","r":482,"s":40.3,"lo":422,"hi":497,"n":4,"rr":507,"mr":483},{"m":"kosmos2","r":483,"s":40.11,"lo":312,"hi":523,"n":3,"rr":529,"mr":496},{"m":"cogvlm-17b-chat","r":484,"s":40.07,"lo":451,"hi":494,"n":19,"rr":412,"mr":470},{"m":"vila-13b","r":485,"s":40.02,"lo":329,"hi":498,"n":3,"rr":481,"mr":494},{"m":"mm1.5-1b","r":486,"s":39.97,"lo":459,"hi":496,"n":9,"rr":424,"mr":481},{"m":"deepseek-vl-7b","r":487,"s":39.06,"lo":469,"hi":501,"n":14,"rr":491,"mr":485},{"m":"paligemma-mix-3b","r":488,"s":38.88,"lo":441,"hi":507,"n":12,"rr":450,"mr":486},{"m":"internvl2-1b","r":489,"s":38.79,"lo":470,"hi":503,"n":33,"rr":485,"mr":469},{"m":"yi-vl-34b","r":490,"s":38.77,"lo":445,"hi":522,"n":8,"rr":502,"mr":489},{"m":"minicpm-v-2.0-3b","r":491,"s":38.71,"lo":471,"hi":501,"n":16,"rr":436,"mr":474},{"m":"sharegpt4v-7b","r":492,"s":38.09,"lo":464,"hi":505,"n":10,"rr":503,"mr":488},{"m":"vila1.5-3b","r":493,"s":37.12,"lo":451,"hi":506,"n":6,"rr":415,"mr":501},{"m":"janus-pro-7b","r":494,"s":37.02,"lo":465,"hi":519,"n":12,"rr":469,"mr":492},{"m":"t5gemma-2-4b-4b","r":495,"s":36.97,"lo":471,"hi":505,"n":8,"rr":433,"mr":498},{"m":"monkey","r":496,"s":36.92,"lo":459,"hi":505,"n":9,"rr":482,"mr":495},{"m":"mini-gemini-2b","r":497,"s":36.71,"lo":354,"hi":516,"n":3,"rr":515,"mr":510},{"m":"gemini-nano-2","r":498,"s":36.65,"lo":471,"hi":512,"n":7,"rr":474,"mr":497},{"m":"emu2-chat","r":499,"s":36.57,"lo":457,"hi":511,"n":10,"rr":476,"mr":499},{"m":"sphinx-2k","r":500,"s":36.54,"lo":454,"hi":508,"n":8,"rr":407,"mr":500},{"m":"nemotron-nano-12b-v2-vl","r":501,"s":36.46,"lo":308,"hi":522,"n":11,"rr":521,"mr":507},{"m":"qwen-vl-chat","r":502,"s":35.29,"lo":488,"hi":510,"n":19,"rr":386,"mr":487},{"m":"lfm2-vl-450m","r":503,"s":35.01,"lo":475,"hi":513,"n":9,"rr":488,"mr":509},{"m":"minicpm-v","r":504,"s":34.85,"lo":477,"hi":516,"n":8,"rr":497,"mr":505},{"m":"llava-onevision-0.5b","r":505,"s":34.7,"lo":487,"hi":516,"n":19,"rr":512,"mr":493},{"m":"mplug-owl2","r":506,"s":34.64,"lo":480,"hi":514,"n":10,"rr":428,"mr":503},{"m":"deepseek-vl-1.3b","r":507,"s":34.56,"lo":483,"hi":516,"n":10,"rr":479,"mr":504},{"m":"yi-vl-6b","r":508,"s":34.51,"lo":476,"hi":520,"n":9,"rr":514,"mr":506},{"m":"internlm-xcomposer","r":509,"s":33.71,"lo":449,"hi":515,"n":8,"rr":513,"mr":508},{"m":"llava-1.5-13b","r":510,"s":33.7,"lo":490,"hi":518,"n":20,"rr":489,"mr":502},{"m":"blip-2-vicuna-13b","r":511,"s":33.42,"lo":329,"hi":519,"n":3,"rr":439,"mr":518},{"m":"mplug-docowl-7b","r":512,"s":33.14,"lo":351,"hi":515,"n":3,"rr":425,"mr":519},{"m":"janus-pro-1.5b","r":513,"s":33.12,"lo":466,"hi":527,"n":10,"rr":500,"mr":512},{"m":"smolvlm2-0.256b","r":514,"s":32.83,"lo":381,"hi":524,"n":5,"rr":526,"mr":521},{"m":"ureader","r":515,"s":32.6,"lo":481,"hi":519,"n":6,"rr":510,"mr":513},{"m":"lumina-dimoo","r":516,"s":32.4,"lo":443,"hi":524,"n":18,"rr":520,"mr":511},{"m":"alpamayo-1.5-10b","r":517,"s":31.97,"lo":485,"hi":526,"n":10,"rr":527,"mr":516},{"m":"smolvlm2-0.5b","r":518,"s":31.91,"lo":488,"hi":520,"n":14,"rr":499,"mr":514},{"m":"qwen-vl","r":519,"s":30.21,"lo":484,"hi":524,"n":13,"rr":384,"mr":515},{"m":"llava-1.5-7b","r":520,"s":30.13,"lo":500,"hi":523,"n":18,"rr":505,"mr":517},{"m":"textmonkey","r":521,"s":29.68,"lo":477,"hi":525,"n":7,"rr":508,"mr":525},{"m":"t5gemma-2-1b-1b","r":522,"s":29.05,"lo":476,"hi":523,"n":8,"rr":494,"mr":524},{"m":"idefics-80b-instruct","r":523,"s":28.96,"lo":497,"hi":524,"n":10,"rr":517,"mr":520},{"m":"llava-v1-7b","r":524,"s":28.15,"lo":459,"hi":523,"n":8,"rr":516,"mr":523},{"m":"instructblip-7b","r":525,"s":27.32,"lo":496,"hi":525,"n":10,"rr":506,"mr":522},{"m":"deepseek-ocr-2","r":526,"s":24.29,"lo":392,"hi":526,"n":4,"rr":518,"mr":526},{"m":"openflamingo-v2","r":527,"s":21.62,"lo":504,"hi":527,"n":9,"rr":523,"mr":527},{"m":"minigpt-4-v1-7b","r":528,"s":20.33,"lo":479,"hi":528,"n":7,"rr":525,"mr":528},{"m":"t5gemma-2-270m-270m","r":529,"s":19.09,"lo":478,"hi":528,"n":8,"rr":522,"mr":529}]},"faix-voice":{"name":"Voice","n":67,"nb":25,"acc":0.7438,"raw_acc":0.68,"rows":[{"m":"gemini-3.1-pro","r":1,"s":93.15,"lo":1,"hi":27,"n":4,"rr":10,"mr":3},{"m":"seed2.0-lite","r":2,"s":92.24,"lo":3,"hi":35,"n":4,"rr":17,"mr":5},{"m":"gemini-3-flash","r":3,"s":92.18,"lo":2,"hi":38,"n":4,"rr":21,"mr":6},{"m":"stepaudio-3-realtime","r":4,"s":92.17,"lo":1,"hi":10,"n":11,"rr":14,"mr":1},{"m":"gemini-3.8-flash","r":5,"s":92.08,"lo":1,"hi":33,"n":3,"rr":20,"mr":8},{"m":"grok-voice-3.0","r":6,"s":91.8,"lo":1,"hi":13,"n":9,"rr":3,"mr":2},{"m":"qwen3.8-omni-flash","r":7,"s":91.59,"lo":2,"hi":39,"n":3,"rr":25,"mr":12},{"m":"eleven-realtime-v1-max","r":8,"s":90.23,"lo":1,"hi":18,"n":9,"rr":18,"mr":4},{"m":"qwen-audio-3.0-realtime-plus","r":9,"s":89.94,"lo":3,"hi":17,"n":9,"rr":12,"mr":7},{"m":"gemini-3.8-live-extended-thinking-high","r":10,"s":89.53,"lo":2,"hi":30,"n":10,"rr":15,"mr":10},{"m":"qwen3.5-omni-plus","r":11,"s":89.37,"lo":8,"hi":34,"n":3,"rr":32,"mr":15},{"m":"grok-voice-1.0","r":12,"s":89.24,"lo":3,"hi":51,"n":9,"rr":23,"mr":11},{"m":"grok-voice-2.0","r":13,"s":89.11,"lo":6,"hi":16,"n":9,"rr":9,"mr":9},{"m":"gpt-live-1-medium","r":14,"s":88.12,"lo":2,"hi":25,"n":12,"rr":8,"mr":13},{"m":"gpt-live-1-low","r":15,"s":87.51,"lo":5,"hi":22,"n":10,"rr":7,"mr":14},{"m":"muse-spark-1.2","r":16,"s":86.13,"lo":11,"hi":51,"n":3,"rr":45,"mr":24},{"m":"gpt-realtime-2.0-xhigh","r":17,"s":85.7,"lo":10,"hi":32,"n":6,"rr":35,"mr":20},{"m":"eleven-realtime-v1-mini","r":18,"s":85.47,"lo":5,"hi":38,"n":9,"rr":29,"mr":16},{"m":"gpt-realtime-2.1-high","r":19,"s":84.58,"lo":12,"hi":27,"n":13,"rr":34,"mr":17},{"m":"qwen-audio-3.0-realtime-flash","r":20,"s":84.47,"lo":10,"hi":33,"n":9,"rr":26,"mr":19},{"m":"gpt-realtime-2.0-high","r":21,"s":84.17,"lo":11,"hi":28,"n":13,"rr":36,"mr":18},{"m":"gemini-3.8-live","r":22,"s":82.93,"lo":8,"hi":39,"n":9,"rr":31,"mr":22},{"m":"longcat-flash-omni","r":23,"s":82.88,"lo":11,"hi":37,"n":6,"rr":2,"mr":28},{"m":"gpt-realtime-2.0-medium","r":24,"s":82.74,"lo":13,"hi":30,"n":8,"rr":30,"mr":21},{"m":"grok-voice-fast-1.0","r":25,"s":81.06,"lo":17,"hi":60,"n":8,"rr":47,"mr":27},{"m":"gpt-realtime-1.5","r":26,"s":80.75,"lo":14,"hi":35,"n":14,"rr":37,"mr":23},{"m":"tml-interaction-small","r":27,"s":80.62,"lo":7,"hi":38,"n":6,"rr":33,"mr":32},{"m":"qwen3-omni-flash-thinking","r":28,"s":79.7,"lo":19,"hi":38,"n":10,"rr":4,"mr":31},{"m":"gemini-2.5-pro","r":29,"s":79.59,"lo":15,"hi":43,"n":10,"rr":1,"mr":30},{"m":"gpt-realtime-2.1","r":30,"s":79.29,"lo":22,"hi":37,"n":9,"rr":27,"mr":29},{"m":"gpt-realtime-2.0","r":31,"s":79.14,"lo":16,"hi":35,"n":14,"rr":38,"mr":25},{"m":"qwen3-omni-30b-a3b-thinking","r":32,"s":79.07,"lo":20,"hi":39,"n":10,"rr":5,"mr":33},{"m":"gemini-3.1-flash-live-high","r":33,"s":78.98,"lo":18,"hi":53,"n":15,"rr":51,"mr":26},{"m":"gpt-realtime","r":34,"s":78.95,"lo":7,"hi":40,"n":11,"rr":40,"mr":34},{"m":"gpt-4o-audio","r":35,"s":78.13,"lo":22,"hi":42,"n":10,"rr":6,"mr":35},{"m":"qwen3.5-omni-plus-realtime","r":36,"s":75.86,"lo":5,"hi":50,"n":6,"rr":41,"mr":41},{"m":"gemini-2.5-flash","r":37,"s":75.75,"lo":26,"hi":51,"n":10,"rr":11,"mr":38},{"m":"gpt-realtime-2.1-mini-high","r":38,"s":75.58,"lo":11,"hi":44,"n":8,"rr":39,"mr":36},{"m":"qwen3-omni-30b-a3b-instruct","r":39,"s":74.64,"lo":29,"hi":44,"n":12,"rr":22,"mr":39},{"m":"qwen3-omni-flash-instruct","r":40,"s":74.41,"lo":26,"hi":46,"n":15,"rr":16,"mr":37},{"m":"gpt-4o-realtime-preview-2024-12-17","r":41,"s":72.79,"lo":26,"hi":46,"n":8,"rr":42,"mr":43},{"m":"gpt-realtime-2.1-mini","r":42,"s":71.31,"lo":21,"hi":48,"n":9,"rr":44,"mr":42},{"m":"gpt-realtime-mini","r":43,"s":71.03,"lo":14,"hi":48,"n":9,"rr":43,"mr":44},{"m":"gemini-3.1-flash-live","r":44,"s":70.74,"lo":32,"hi":59,"n":14,"rr":52,"mr":40},{"m":"fun-audio-chat-8b","r":45,"s":69.61,"lo":37,"hi":48,"n":6,"rr":19,"mr":47},{"m":"qwen2.5-omni","r":46,"s":67.11,"lo":42,"hi":52,"n":10,"rr":28,"mr":45},{"m":"higgs-realtime","r":47,"s":66.21,"lo":17,"hi":52,"n":8,"rr":48,"mr":46},{"m":"raon-speechchat-9b","r":48,"s":65.34,"lo":30,"hi":58,"n":5,"rr":13,"mr":49},{"m":"deepslate-opal","r":49,"s":60.96,"lo":33,"hi":56,"n":8,"rr":50,"mr":48},{"m":"kimi-audio-7b-instruct","r":50,"s":60.79,"lo":40,"hi":52,"n":8,"rr":49,"mr":50},{"m":"personaplex-7b-v1","r":51,"s":59.98,"lo":27,"hi":59,"n":5,"rr":24,"mr":51},{"m":"mimo-audio-7b-instruct","r":52,"s":59.23,"lo":48,"hi":55,"n":3,"rr":58,"mr":52},{"m":"step-audio-2-mini","r":53,"s":50.47,"lo":49,"hi":58,"n":8,"rr":56,"mr":53},{"m":"gemini-2.5-flash-native-audio-preview-12-2025","r":54,"s":47.62,"lo":46,"hi":66,"n":8,"rr":62,"mr":54},{"m":"lfm2.5-audio-1.5b","r":55,"s":47.3,"lo":34,"hi":61,"n":3,"rr":53,"mr":56},{"m":"qwen2.5-omni-3b","r":56,"s":46.5,"lo":48,"hi":60,"n":3,"rr":46,"mr":57},{"m":"lfm2-audio-1.5b","r":57,"s":44.81,"lo":49,"hi":61,"n":4,"rr":59,"mr":55},{"m":"freeze-omni","r":58,"s":43.22,"lo":6,"hi":61,"n":5,"rr":54,"mr":58},{"m":"nemotronlabs-voicechat-11b","r":59,"s":38.23,"lo":47,"hi":65,"n":12,"rr":57,"mr":59},{"m":"flm-audio","r":60,"s":33.33,"lo":51,"hi":64,"n":5,"rr":55,"mr":60},{"m":"qwen2.5-omni-7b","r":61,"s":28,"lo":52,"hi":64,"n":6,"rr":63,"mr":61},{"m":"minicpm-o-2.6","r":62,"s":24.89,"lo":55,"hi":66,"n":5,"rr":61,"mr":62},{"m":"kanana-1.5-o-9.8b-instruct-2602","r":63,"s":24.65,"lo":54,"hi":66,"n":4,"rr":66,"mr":64},{"m":"moshi","r":64,"s":21.69,"lo":46,"hi":66,"n":8,"rr":60,"mr":63},{"m":"hyperclovax-seed-omni-8b","r":65,"s":19.61,"lo":59,"hi":67,"n":4,"rr":67,"mr":65},{"m":"mini-omni2","r":66,"s":18.21,"lo":58,"hi":67,"n":3,"rr":64,"mr":66},{"m":"gemini-2.5-flash-native-audio-preview-09-2025","r":67,"s":6.25,"lo":56,"hi":67,"n":4,"rr":65,"mr":67}]}}