{"updated":"2026-08-21T16:07:44.963Z","boards":[{"name":"SWE-Bench Pro","slug":"swe-bench-pro","metric":"resolve rate","entries":[{"model":"anthropic/claude-fable-5","lab":"anthropic","score":80.3,"best_input_per_m":10,"best_output_per_m":50,"points_per_dollar":4.01},{"model":"anthropic/claude-opus-5","lab":"anthropic","score":79.2,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":7.92},{"model":"anthropic/claude-opus-4-8","lab":"anthropic","score":69.2,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":6.92},{"model":"xai/grok-4.5","lab":"xai","score":64.7,"best_input_per_m":2,"best_output_per_m":6,"points_per_dollar":21.57},{"model":"openai/gpt-5.6-sol","lab":"openai","score":64.6,"best_input_per_m":2.5,"best_output_per_m":15,"points_per_dollar":11.48},{"model":"anthropic/claude-opus-4-7","lab":"anthropic","score":64.3,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":6.43},{"model":"openai/gpt-5.6-terra","lab":"openai","score":63.4,"best_input_per_m":1,"best_output_per_m":6,"points_per_dollar":28.18},{"model":"anthropic/claude-sonnet-5","lab":"anthropic","score":63.2,"best_input_per_m":2,"best_output_per_m":10,"points_per_dollar":15.8},{"model":"openai/gpt-5.6-luna","lab":"openai","score":62.7,"best_input_per_m":0.1,"best_output_per_m":0.6,"points_per_dollar":278.67},{"model":"zhipuai/glm-5.2","lab":"zhipuai","score":62.1,"best_input_per_m":1.4,"best_output_per_m":4.4,"points_per_dollar":28.88},{"model":"meta/muse-spark-1.1","lab":"meta","score":61.5,"best_input_per_m":1.25,"best_output_per_m":4.25,"points_per_dollar":30.75},{"model":"alibaba/qwen3.7-max","lab":"alibaba","score":60.6,"best_input_per_m":2.5,"best_output_per_m":7.5,"points_per_dollar":16.16},{"model":"meituan/longcat-2.0","lab":"meituan","score":59.5,"best_input_per_m":0.3,"best_output_per_m":1.2,"points_per_dollar":113.33},{"model":"openai/gpt-5.4","lab":"openai","score":59.1,"best_input_per_m":2.2,"best_output_per_m":14,"points_per_dollar":11.48},{"model":"minimax/MiniMax-M3","lab":"minimax","score":59,"best_input_per_m":0.3,"best_output_per_m":1.2,"points_per_dollar":112.38},{"model":"google/gemini-3.6-flash","lab":"google","score":58.7,"best_input_per_m":0.75,"best_output_per_m":3.75,"points_per_dollar":39.13},{"model":"openai/gpt-5.5","lab":"openai","score":58.6,"best_input_per_m":4.5455,"best_output_per_m":27.2727,"points_per_dollar":5.73},{"model":"xiaomi/mimo-v2.5-pro","lab":"xiaomi","score":57.2,"best_input_per_m":0.435,"best_output_per_m":0.87,"points_per_dollar":105.2},{"model":"stepfun/step-3.7-flash","lab":"stepfun","score":56.3,"best_input_per_m":0.185,"best_output_per_m":1.11,"points_per_dollar":135.26},{"model":"minimax/MiniMax-M2.7","lab":"minimax","score":56.2,"best_input_per_m":0.3,"best_output_per_m":1.2,"points_per_dollar":107.05},{"model":"google/gemini-3.5-flash","lab":"google","score":55.1,"best_input_per_m":1.5,"best_output_per_m":9,"points_per_dollar":16.33},{"model":"openai/gpt-5.4-mini","lab":"openai","score":54.4,"best_input_per_m":0.68,"best_output_per_m":4,"points_per_dollar":36.03},{"model":"google/gemini-3.1-pro-preview","lab":"google","score":54.2,"best_input_per_m":2,"best_output_per_m":12,"points_per_dollar":12.04},{"model":"google/gemini-3.5-flash-lite","lab":"google","score":54.2,"best_input_per_m":0.3,"best_output_per_m":2.5,"points_per_dollar":63.76},{"model":"openai/gpt-5.4-nano","lab":"openai","score":52.4,"best_input_per_m":0.18,"best_output_per_m":1.1,"points_per_dollar":127.8},{"model":"anthropic/claude-opus-4-6","lab":"anthropic","score":51.9,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":5.19},{"model":"meta/muse-glimmer-30b","lab":"meta","score":51.2,"best_input_per_m":0.3,"best_output_per_m":1.1,"points_per_dollar":102.4},{"model":"poolside/laguna-xs-2.1","lab":"poolside","score":47.6,"best_input_per_m":0.06,"best_output_per_m":0.12,"points_per_dollar":634.67},{"model":"google/gemini-3.1-pro-preview","lab":"google","score":46.1,"best_input_per_m":2,"best_output_per_m":12,"points_per_dollar":10.24},{"model":"anthropic/claude-opus-4-5-20251101","lab":"anthropic","score":45.89,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":4.59},{"model":"anthropic/claude-opus-4-7","lab":"anthropic","score":44.9,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":4.49},{"model":"anthropic/claude-sonnet-4-5","lab":"anthropic","score":43.6,"best_input_per_m":3,"best_output_per_m":15,"points_per_dollar":7.27},{"model":"google/gemini-3-pro-preview","lab":"google","score":43.3,"best_input_per_m":2,"best_output_per_m":12,"points_per_dollar":9.62},{"model":"openai/gpt-5","lab":"openai","score":41.78,"best_input_per_m":1.1,"best_output_per_m":9,"points_per_dollar":13.59},{"model":"openai/gpt-5.2-codex","lab":"openai","score":41.04,"best_input_per_m":1.6,"best_output_per_m":13,"points_per_dollar":9.22},{"model":"cohere/north-mini-code-1-0","lab":"cohere","score":40.2,"best_input_per_m":null,"best_output_per_m":null,"points_per_dollar":null},{"model":"anthropic/claude-haiku-4-5","lab":"anthropic","score":39.45,"best_input_per_m":1,"best_output_per_m":5,"points_per_dollar":19.73},{"model":"alibaba/qwen3-coder-480b-a35b-instruct","lab":"alibaba","score":38.7,"best_input_per_m":1.5,"best_output_per_m":7.5,"points_per_dollar":12.9},{"model":"minimax/MiniMax-M2.1","lab":"minimax","score":36.81,"best_input_per_m":0.3,"best_output_per_m":1.2,"points_per_dollar":70.11},{"model":"anthropic/claude-opus-4-7","lab":"anthropic","score":36.4,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":3.64},{"model":"google/gemini-3-flash-preview","lab":"google","score":34.63,"best_input_per_m":0.5,"best_output_per_m":3,"points_per_dollar":30.78},{"model":"anthropic/claude-opus-4-7","lab":"anthropic","score":34.4,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":3.44},{"model":"openai/gpt-5.5","lab":"openai","score":30.9,"best_input_per_m":4.5455,"best_output_per_m":27.2727,"points_per_dollar":3.02},{"model":"openai/gpt-5.2","lab":"openai","score":29.94,"best_input_per_m":1.6,"best_output_per_m":13,"points_per_dollar":6.73},{"model":"moonshotai/kimi-k2.6","lab":"moonshotai","score":27.3,"best_input_per_m":0.5,"best_output_per_m":2.6,"points_per_dollar":26.63},{"model":"openai/gpt-5.5","lab":"openai","score":26.2,"best_input_per_m":4.5455,"best_output_per_m":27.2727,"points_per_dollar":2.56},{"model":"openai/gpt-5.5","lab":"openai","score":24.9,"best_input_per_m":4.5455,"best_output_per_m":27.2727,"points_per_dollar":2.43},{"model":"alibaba/qwen3-235b-a22b","lab":"alibaba","score":21.41,"best_input_per_m":0.7,"best_output_per_m":2.8,"points_per_dollar":17.48},{"model":"zhipuai/glm-5.1","lab":"zhipuai","score":19.8,"best_input_per_m":1.4,"best_output_per_m":4.4,"points_per_dollar":9.21},{"model":"openai/gpt-5.4","lab":"openai","score":18.9,"best_input_per_m":2.2,"best_output_per_m":14,"points_per_dollar":3.67},{"model":"openai/gpt-5.4","lab":"openai","score":18.4,"best_input_per_m":2.2,"best_output_per_m":14,"points_per_dollar":3.57},{"model":"deepseek/deepseek-v4-pro","lab":"deepseek","score":18,"best_input_per_m":0.435,"best_output_per_m":0.87,"points_per_dollar":33.1},{"model":"google/gemini-3.1-pro-preview","lab":"google","score":15.1,"best_input_per_m":2,"best_output_per_m":12,"points_per_dollar":3.36},{"model":"anthropic/claude-sonnet-4-6","lab":"anthropic","score":14.9,"best_input_per_m":3,"best_output_per_m":15,"points_per_dollar":2.48},{"model":"anthropic/claude-opus-4-6","lab":"anthropic","score":11.8,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":1.18},{"model":"zhipuai/glm-4.6","lab":"zhipuai","score":9.67,"best_input_per_m":0.6,"best_output_per_m":2.2,"points_per_dollar":9.67}]},{"name":"Terminal-Bench","slug":"terminal-bench","metric":"success rate","entries":[{"model":"openai/gpt-5.6-sol","lab":"openai","score":88.8,"best_input_per_m":2.5,"best_output_per_m":15,"points_per_dollar":15.79},{"model":"moonshotai/kimi-k3","lab":"moonshotai","score":88.3,"best_input_per_m":2.5,"best_output_per_m":13.5,"points_per_dollar":16.82},{"model":"anthropic/claude-fable-5","lab":"anthropic","score":88,"best_input_per_m":10,"best_output_per_m":50,"points_per_dollar":4.4},{"model":"openai/gpt-5.6-terra","lab":"openai","score":87.4,"best_input_per_m":1,"best_output_per_m":6,"points_per_dollar":38.84},{"model":"google/gemini-3.7-flash","lab":"google","score":85.8,"best_input_per_m":0.375,"best_output_per_m":1.875,"points_per_dollar":114.4},{"model":"openai/gpt-5.6-luna","lab":"openai","score":84.7,"best_input_per_m":0.1,"best_output_per_m":0.6,"points_per_dollar":376.44},{"model":"openai/gpt-5.5","lab":"openai","score":84.1,"best_input_per_m":4.5455,"best_output_per_m":27.2727,"points_per_dollar":8.22},{"model":"xai/grok-4.5","lab":"xai","score":83.3,"best_input_per_m":2,"best_output_per_m":6,"points_per_dollar":27.77},{"model":"deepseek/deepseek-v4-flash-0731","lab":"deepseek","score":82.7,"best_input_per_m":0.08,"best_output_per_m":0.18,"points_per_dollar":787.62},{"model":"openai/gpt-5.5","lab":"openai","score":82.7,"best_input_per_m":4.5455,"best_output_per_m":27.2727,"points_per_dollar":8.09},{"model":"zhipuai/glm-5.2","lab":"zhipuai","score":82.7,"best_input_per_m":1.4,"best_output_per_m":4.4,"points_per_dollar":38.47},{"model":"zhipuai/glm-5.2","lab":"zhipuai","score":81,"best_input_per_m":1.4,"best_output_per_m":4.4,"points_per_dollar":37.67},{"model":"anthropic/claude-sonnet-5","lab":"anthropic","score":80.4,"best_input_per_m":2,"best_output_per_m":10,"points_per_dollar":20.1},{"model":"meta/muse-spark-1.1","lab":"meta","score":80,"best_input_per_m":1.25,"best_output_per_m":4.25,"points_per_dollar":40},{"model":"openai/gpt-5.5","lab":"openai","score":78.2,"best_input_per_m":4.5455,"best_output_per_m":27.2727,"points_per_dollar":7.65},{"model":"google/gemini-3.6-flash","lab":"google","score":78,"best_input_per_m":0.75,"best_output_per_m":3.75,"points_per_dollar":52},{"model":"google/gemini-3.5-flash","lab":"google","score":76.2,"best_input_per_m":1.5,"best_output_per_m":9,"points_per_dollar":22.58},{"model":"openai/gpt-5.5","lab":"openai","score":75.8,"best_input_per_m":4.5455,"best_output_per_m":27.2727,"points_per_dollar":7.41},{"model":"openai/gpt-5.4","lab":"openai","score":75.1,"best_input_per_m":2.2,"best_output_per_m":14,"points_per_dollar":14.58},{"model":"anthropic/claude-opus-4-8","lab":"anthropic","score":74.6,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":7.46},{"model":"anthropic/claude-opus-4-7","lab":"anthropic","score":73.8,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":7.38},{"model":"openai/gpt-5.5","lab":"openai","score":73.4,"best_input_per_m":4.5455,"best_output_per_m":27.2727,"points_per_dollar":7.18},{"model":"anthropic/claude-opus-4-7","lab":"anthropic","score":71.4,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":7.14},{"model":"meituan/longcat-2.0","lab":"meituan","score":70.8,"best_input_per_m":0.3,"best_output_per_m":1.2,"points_per_dollar":134.86},{"model":"anthropic/claude-opus-4-7","lab":"anthropic","score":70.6,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":7.06},{"model":"google/gemini-3.1-pro-preview","lab":"google","score":70.3,"best_input_per_m":2,"best_output_per_m":12,"points_per_dollar":15.62},{"model":"anthropic/claude-opus-4-6","lab":"anthropic","score":70.2,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":7.02},{"model":"openai/gpt-5.4","lab":"openai","score":69.8,"best_input_per_m":2.2,"best_output_per_m":14,"points_per_dollar":13.55},{"model":"alibaba/qwen3.7-max","lab":"alibaba","score":69.7,"best_input_per_m":2.5,"best_output_per_m":7.5,"points_per_dollar":18.59},{"model":"google/gemini-3.1-pro-preview","lab":"google","score":68.3,"best_input_per_m":2,"best_output_per_m":12,"points_per_dollar":15.18},{"model":"anthropic/claude-sonnet-4-6","lab":"anthropic","score":67,"best_input_per_m":3,"best_output_per_m":15,"points_per_dollar":11.17},{"model":"anthropic/claude-opus-4-7","lab":"anthropic","score":66.1,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":6.61},{"model":"minimax/MiniMax-M3","lab":"minimax","score":66,"best_input_per_m":0.3,"best_output_per_m":1.2,"points_per_dollar":125.71},{"model":"zhipuai/glm-5.1","lab":"zhipuai","score":65.1,"best_input_per_m":1.4,"best_output_per_m":4.4,"points_per_dollar":30.28},{"model":"deepseek/deepseek-v4-pro","lab":"deepseek","score":64.7,"best_input_per_m":0.435,"best_output_per_m":0.87,"points_per_dollar":118.99},{"model":"openai/gpt-5.4","lab":"openai","score":64.7,"best_input_per_m":2.2,"best_output_per_m":14,"points_per_dollar":12.56},{"model":"moonshotai/kimi-k2.6","lab":"moonshotai","score":64.3,"best_input_per_m":0.5,"best_output_per_m":2.6,"points_per_dollar":62.73},{"model":"anthropic/claude-sonnet-4-6","lab":"anthropic","score":63.1,"best_input_per_m":3,"best_output_per_m":15,"points_per_dollar":10.52},{"model":"openai/gpt-5.4-mini","lab":"openai","score":60,"best_input_per_m":0.68,"best_output_per_m":4,"points_per_dollar":39.74},{"model":"stepfun/step-3.7-flash","lab":"stepfun","score":59.6,"best_input_per_m":0.185,"best_output_per_m":1.11,"points_per_dollar":143.18},{"model":"nvidia/nemotron-3-ultra-550b-a55b","lab":"nvidia","score":56.4,"best_input_per_m":0.5,"best_output_per_m":2.2,"points_per_dollar":60.97},{"model":"google/gemini-3.5-flash-lite","lab":"google","score":54,"best_input_per_m":0.3,"best_output_per_m":2.5,"points_per_dollar":63.53},{"model":"meta/muse-glimmer-30b","lab":"meta","score":51.7,"best_input_per_m":0.3,"best_output_per_m":1.1,"points_per_dollar":103.4},{"model":"minimax/MiniMax-M2.7","lab":"minimax","score":51.1,"best_input_per_m":0.3,"best_output_per_m":1.2,"points_per_dollar":97.33},{"model":"openai/gpt-5.4-nano","lab":"openai","score":46.3,"best_input_per_m":0.18,"best_output_per_m":1.1,"points_per_dollar":112.93},{"model":"poolside/laguna-xs-2.1","lab":"poolside","score":37.5,"best_input_per_m":0.06,"best_output_per_m":0.12,"points_per_dollar":500}]},{"name":"SWE-Bench Verified","slug":"swe-bench-verified","metric":"resolved","entries":[{"model":"anthropic/claude-opus-5","lab":"anthropic","score":96,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":9.6},{"model":"anthropic/claude-fable-5","lab":"anthropic","score":95,"best_input_per_m":10,"best_output_per_m":50,"points_per_dollar":4.75},{"model":"anthropic/claude-opus-4-8","lab":"anthropic","score":88.6,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":8.86},{"model":"anthropic/claude-sonnet-5","lab":"anthropic","score":85.2,"best_input_per_m":2,"best_output_per_m":10,"points_per_dollar":21.3},{"model":"deepseek/deepseek-v4-pro","lab":"deepseek","score":80.6,"best_input_per_m":0.435,"best_output_per_m":0.87,"points_per_dollar":148.23},{"model":"minimax/MiniMax-M3","lab":"minimax","score":80.5,"best_input_per_m":0.3,"best_output_per_m":1.2,"points_per_dollar":153.33},{"model":"alibaba/qwen3.7-max","lab":"alibaba","score":80.4,"best_input_per_m":2.5,"best_output_per_m":7.5,"points_per_dollar":21.44},{"model":"moonshotai/kimi-k2.6","lab":"moonshotai","score":80.2,"best_input_per_m":0.5,"best_output_per_m":2.6,"points_per_dollar":78.24},{"model":"minimax/MiniMax-M2.7","lab":"minimax","score":79.9,"best_input_per_m":0.3,"best_output_per_m":1.2,"points_per_dollar":152.19},{"model":"deepseek/deepseek-v4-flash","lab":"deepseek","score":79,"best_input_per_m":0.08106,"best_output_per_m":0.16212,"points_per_dollar":779.67},{"model":"xiaomi/mimo-v2.5-pro","lab":"xiaomi","score":78.9,"best_input_per_m":0.435,"best_output_per_m":0.87,"points_per_dollar":145.1},{"model":"tencent/hy3","lab":"tencent","score":78,"best_input_per_m":0.066,"best_output_per_m":0.26,"points_per_dollar":681.22},{"model":"mistral/mistral-medium-2604","lab":"mistral","score":77.6,"best_input_per_m":1.5,"best_output_per_m":7.5,"points_per_dollar":25.87},{"model":"mistral/mistral-medium-latest","lab":"mistral","score":77.6,"best_input_per_m":0.4,"best_output_per_m":2,"points_per_dollar":97},{"model":"alibaba/qwen3.6-27b","lab":"alibaba","score":77.2,"best_input_per_m":0.203,"best_output_per_m":2.24,"points_per_dollar":108.39},{"model":"stepfun/step-3.7-flash","lab":"stepfun","score":76.5,"best_input_per_m":0.185,"best_output_per_m":1.11,"points_per_dollar":183.78},{"model":"alibaba/qwen3.5-397b-a17b","lab":"alibaba","score":76.4,"best_input_per_m":0.6,"best_output_per_m":3.6,"points_per_dollar":56.59},{"model":"meta/muse-glimmer-30b","lab":"meta","score":76,"best_input_per_m":0.3,"best_output_per_m":1.1,"points_per_dollar":152},{"model":"minimax/MiniMax-M2.5","lab":"minimax","score":75.8,"best_input_per_m":0.3,"best_output_per_m":1.2,"points_per_dollar":144.38},{"model":"stepfun/step-3.5-flash","lab":"stepfun","score":74.4,"best_input_per_m":0.09,"best_output_per_m":0.3,"points_per_dollar":522.11},{"model":"tencent/hy3-preview","lab":"tencent","score":74.4,"best_input_per_m":0.172,"best_output_per_m":0.572,"points_per_dollar":273.53},{"model":"minimax/MiniMax-M2.1","lab":"minimax","score":74,"best_input_per_m":0.3,"best_output_per_m":1.2,"points_per_dollar":140.95},{"model":"zhipuai/glm-4.7","lab":"zhipuai","score":73.8,"best_input_per_m":0.6,"best_output_per_m":2.2,"points_per_dollar":73.8},{"model":"alibaba/qwen3.6-35b-a3b","lab":"alibaba","score":73.4,"best_input_per_m":0.19,"best_output_per_m":0.48,"points_per_dollar":279.62},{"model":"zhipuai/glm-5","lab":"zhipuai","score":72.8,"best_input_per_m":1,"best_output_per_m":3.2,"points_per_dollar":46.97},{"model":"alibaba/qwen3.5-27b","lab":"alibaba","score":72.4,"best_input_per_m":0.3,"best_output_per_m":2.4,"points_per_dollar":87.76},{"model":"alibaba/qwen3.5-122b-a10b","lab":"alibaba","score":72,"best_input_per_m":0.4,"best_output_per_m":3.2,"points_per_dollar":65.45},{"model":"moonshotai/kimi-k2-thinking","lab":"moonshotai","score":71.3,"best_input_per_m":0.47,"best_output_per_m":2,"points_per_dollar":83.64},{"model":"poolside/laguna-xs-2.1","lab":"poolside","score":70.9,"best_input_per_m":0.06,"best_output_per_m":0.12,"points_per_dollar":945.33},{"model":"moonshotai/kimi-k2.5","lab":"moonshotai","score":70.8,"best_input_per_m":0.3,"best_output_per_m":1.9,"points_per_dollar":101.14},{"model":"nvidia/nemotron-3-ultra-550b-a55b","lab":"nvidia","score":70.7,"best_input_per_m":0.5,"best_output_per_m":2.2,"points_per_dollar":76.43},{"model":"minimax/MiniMax-M2","lab":"minimax","score":69.4,"best_input_per_m":0.3,"best_output_per_m":1.2,"points_per_dollar":132.19},{"model":"cohere/north-mini-code-1-0","lab":"cohere","score":67.6,"best_input_per_m":null,"best_output_per_m":null,"points_per_dollar":null},{"model":"mistral/devstral-medium-2507","lab":"mistral","score":61.6,"best_input_per_m":null,"best_output_per_m":null,"points_per_dollar":null},{"model":"zhipuai/glm-4.7-flash","lab":"zhipuai","score":59.2,"best_input_per_m":null,"best_output_per_m":null,"points_per_dollar":null},{"model":"mistral/devstral-small-2507","lab":"mistral","score":53.6,"best_input_per_m":null,"best_output_per_m":null,"points_per_dollar":null}]},{"name":"Humanity's Last Exam","slug":"humanity-s-last-exam","metric":"accuracy","entries":[{"model":"anthropic/claude-opus-5","lab":"anthropic","score":64.7,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":6.47},{"model":"anthropic/claude-fable-5","lab":"anthropic","score":64.5,"best_input_per_m":10,"best_output_per_m":50,"points_per_dollar":3.23},{"model":"meta/muse-spark-1.1","lab":"meta","score":62.1,"best_input_per_m":1.25,"best_output_per_m":4.25,"points_per_dollar":31.05},{"model":"anthropic/claude-fable-5","lab":"anthropic","score":59,"best_input_per_m":10,"best_output_per_m":50,"points_per_dollar":2.95},{"model":"openai/gpt-5.4-pro","lab":"openai","score":58.7,"best_input_per_m":27,"best_output_per_m":160,"points_per_dollar":0.97},{"model":"anthropic/claude-opus-4-8","lab":"anthropic","score":57.9,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":5.79},{"model":"openai/gpt-5.5-pro","lab":"openai","score":57.2,"best_input_per_m":27.2727,"best_output_per_m":163.6364,"points_per_dollar":0.93},{"model":"anthropic/claude-opus-5","lab":"anthropic","score":56.3,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":5.63},{"model":"anthropic/claude-opus-4-7","lab":"anthropic","score":54.7,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":5.47},{"model":"zhipuai/glm-5.2","lab":"zhipuai","score":54.7,"best_input_per_m":1.4,"best_output_per_m":4.4,"points_per_dollar":25.44},{"model":"openai/gpt-5.5","lab":"openai","score":52.2,"best_input_per_m":4.5455,"best_output_per_m":27.2727,"points_per_dollar":5.1},{"model":"openai/gpt-5.4","lab":"openai","score":52.1,"best_input_per_m":2.2,"best_output_per_m":14,"points_per_dollar":10.12},{"model":"anthropic/claude-opus-4-8","lab":"anthropic","score":49.8,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":4.98},{"model":"stepfun/step-3.7-flash","lab":"stepfun","score":47.2,"best_input_per_m":0.185,"best_output_per_m":1.11,"points_per_dollar":113.39},{"model":"anthropic/claude-opus-4-7","lab":"anthropic","score":46.9,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":4.69},{"model":"anthropic/claude-sonnet-4-6","lab":"anthropic","score":46.8,"best_input_per_m":3,"best_output_per_m":15,"points_per_dollar":7.8},{"model":"google/gemini-3.1-pro-preview","lab":"google","score":44.4,"best_input_per_m":2,"best_output_per_m":12,"points_per_dollar":9.87},{"model":"openai/gpt-5.5-pro","lab":"openai","score":43.1,"best_input_per_m":27.2727,"best_output_per_m":163.6364,"points_per_dollar":0.7},{"model":"openai/gpt-5.4-pro","lab":"openai","score":42.7,"best_input_per_m":27,"best_output_per_m":160,"points_per_dollar":0.71},{"model":"openai/gpt-5.4-mini","lab":"openai","score":41.5,"best_input_per_m":0.68,"best_output_per_m":4,"points_per_dollar":27.48},{"model":"alibaba/qwen3.7-max","lab":"alibaba","score":41.4,"best_input_per_m":2.5,"best_output_per_m":7.5,"points_per_dollar":11.04},{"model":"openai/gpt-5.5","lab":"openai","score":41.4,"best_input_per_m":4.5455,"best_output_per_m":27.2727,"points_per_dollar":4.05},{"model":"zhipuai/glm-5.2","lab":"zhipuai","score":40.5,"best_input_per_m":1.4,"best_output_per_m":4.4,"points_per_dollar":18.84},{"model":"google/gemini-3.5-flash","lab":"google","score":40.2,"best_input_per_m":1.5,"best_output_per_m":9,"points_per_dollar":11.91},{"model":"openai/gpt-5.4","lab":"openai","score":39.8,"best_input_per_m":2.2,"best_output_per_m":14,"points_per_dollar":7.73},{"model":"openai/gpt-5.4-nano","lab":"openai","score":37.7,"best_input_per_m":0.18,"best_output_per_m":1.1,"points_per_dollar":91.95},{"model":"nvidia/nemotron-3-ultra-550b-a55b","lab":"nvidia","score":37.4,"best_input_per_m":0.5,"best_output_per_m":2.2,"points_per_dollar":40.43},{"model":"anthropic/claude-sonnet-4-6","lab":"anthropic","score":34.6,"best_input_per_m":3,"best_output_per_m":15,"points_per_dollar":5.77},{"model":"openai/gpt-5.4-mini","lab":"openai","score":28.2,"best_input_per_m":0.68,"best_output_per_m":4,"points_per_dollar":18.68},{"model":"nvidia/nemotron-3-ultra-550b-a55b","lab":"nvidia","score":26.7,"best_input_per_m":0.5,"best_output_per_m":2.2,"points_per_dollar":28.86},{"model":"openai/gpt-5.4-nano","lab":"openai","score":24.3,"best_input_per_m":0.18,"best_output_per_m":1.1,"points_per_dollar":59.27}]},{"name":"SciCode","slug":"scicode","metric":"percent correct","entries":[{"model":"sakana/fugu","lab":"sakana","score":60.1,"best_input_per_m":null,"best_output_per_m":null,"points_per_dollar":null},{"model":"sakana/fugu-ultra","lab":"sakana","score":58.7,"best_input_per_m":5,"best_output_per_m":30,"points_per_dollar":5.22},{"model":"alibaba/qwen3.7-max","lab":"alibaba","score":53.5,"best_input_per_m":2.5,"best_output_per_m":7.5,"points_per_dollar":14.27},{"model":"google/gemini-2.5-pro","lab":"google","score":42.8,"best_input_per_m":0.87,"best_output_per_m":7,"points_per_dollar":17.81},{"model":"openai/gpt-5-codex","lab":"openai","score":40.9,"best_input_per_m":1.1,"best_output_per_m":9,"points_per_dollar":13.3},{"model":"stepfun/step-3.5-flash","lab":"stepfun","score":40.4,"best_input_per_m":0.09,"best_output_per_m":0.3,"points_per_dollar":283.51},{"model":"stepfun/step-3.7-flash","lab":"stepfun","score":40,"best_input_per_m":0.185,"best_output_per_m":1.11,"points_per_dollar":96.1},{"model":"google/gemini-2.5-flash","lab":"google","score":39.4,"best_input_per_m":0.21,"best_output_per_m":1.8,"points_per_dollar":64.86},{"model":"stepfun/step-3.5-flash-2603","lab":"stepfun","score":38.5,"best_input_per_m":0.1,"best_output_per_m":0.3,"points_per_dollar":256.67},{"model":"zhipuai/glm-4.6","lab":"zhipuai","score":38.4,"best_input_per_m":0.6,"best_output_per_m":2.2,"points_per_dollar":38.4},{"model":"alibaba/qwen3-max","lab":"alibaba","score":38.3,"best_input_per_m":1.2,"best_output_per_m":6,"points_per_dollar":15.96},{"model":"mistral/mistral-small-2603","lab":"mistral","score":38,"best_input_per_m":0.15,"best_output_per_m":0.6,"points_per_dollar":144.76},{"model":"mistral/mistral-large-2512","lab":"mistral","score":36.2,"best_input_per_m":0.5,"best_output_per_m":1.5,"points_per_dollar":48.27},{"model":"deepseek/deepseek-r1","lab":"deepseek","score":35.7,"best_input_per_m":0.7,"best_output_per_m":2.5,"points_per_dollar":31.04},{"model":"zhipuai/glm-4.5","lab":"zhipuai","score":34.8,"best_input_per_m":0.6,"best_output_per_m":2.2,"points_per_dollar":34.8},{"model":"openai/gpt-4o-2024-11-20","lab":"openai","score":33.3,"best_input_per_m":2.5,"best_output_per_m":10,"points_per_dollar":7.61},{"model":"mistral/devstral-2512","lab":"mistral","score":33.1,"best_input_per_m":0.4,"best_output_per_m":2,"points_per_dollar":41.38},{"model":"mistral/mistral-medium-2505","lab":"mistral","score":33.1,"best_input_per_m":0.4,"best_output_per_m":2,"points_per_dollar":41.38},{"model":"openai/gpt-4o-2024-08-06","lab":"openai","score":33.1,"best_input_per_m":2.5,"best_output_per_m":10,"points_per_dollar":7.57},{"model":"openai/gpt-4-turbo","lab":"openai","score":31.9,"best_input_per_m":9,"best_output_per_m":27,"points_per_dollar":2.36},{"model":"openai/gpt-4o-2024-05-13","lab":"openai","score":30.9,"best_input_per_m":5,"best_output_per_m":15,"points_per_dollar":4.12},{"model":"zhipuai/glm-4.5-air","lab":"zhipuai","score":30.6,"best_input_per_m":0.2,"best_output_per_m":1.1,"points_per_dollar":72},{"model":"mistral/mistral-large-2411","lab":"mistral","score":29.2,"best_input_per_m":2,"best_output_per_m":6,"points_per_dollar":9.73},{"model":"alibaba/qwen3-coder-30b-a3b-instruct","lab":"alibaba","score":27.8,"best_input_per_m":0.45,"best_output_per_m":2.25,"points_per_dollar":30.89},{"model":"meta/llama-3.3-70b-instruct","lab":"meta","score":26,"best_input_per_m":0.22,"best_output_per_m":0.5,"points_per_dollar":89.66},{"model":"openai/gpt-4o-mini","lab":"openai","score":22.9,"best_input_per_m":0.075,"best_output_per_m":0.3,"points_per_dollar":174.48},{"model":"perplexity/sonar","lab":"perplexity","score":22.9,"best_input_per_m":0.25,"best_output_per_m":2.5,"points_per_dollar":28.18},{"model":"perplexity/sonar-pro","lab":"perplexity","score":22.6,"best_input_per_m":3,"best_output_per_m":15,"points_per_dollar":3.77},{"model":"zhipuai/glm-4.5v","lab":"zhipuai","score":22.1,"best_input_per_m":0.6,"best_output_per_m":1.8,"points_per_dollar":24.56},{"model":"google/gemini-2.5-flash-lite","lab":"google","score":19.3,"best_input_per_m":0.1,"best_output_per_m":0.1,"points_per_dollar":193}]},{"name":"Artificial Analysis Coding Index","slug":"artificial-analysis-coding-index","metric":"index","entries":[{"model":"openai/gpt-5-codex","lab":"openai","score":38.9,"best_input_per_m":1.1,"best_output_per_m":9,"points_per_dollar":12.65},{"model":"stepfun/step-3.7-flash","lab":"stepfun","score":37.1,"best_input_per_m":0.185,"best_output_per_m":1.11,"points_per_dollar":89.13},{"model":"stepfun/step-3.5-flash-2603","lab":"stepfun","score":34.6,"best_input_per_m":0.1,"best_output_per_m":0.3,"points_per_dollar":230.67},{"model":"cohere/north-mini-code-1-0","lab":"cohere","score":33.4,"best_input_per_m":null,"best_output_per_m":null,"points_per_dollar":null},{"model":"google/gemini-2.5-pro","lab":"google","score":32,"best_input_per_m":0.87,"best_output_per_m":7,"points_per_dollar":13.32},{"model":"stepfun/step-3.5-flash","lab":"stepfun","score":31.6,"best_input_per_m":0.09,"best_output_per_m":0.3,"points_per_dollar":221.75},{"model":"zhipuai/glm-4.6","lab":"zhipuai","score":29.5,"best_input_per_m":0.6,"best_output_per_m":2.2,"points_per_dollar":29.5},{"model":"alibaba/qwen3-max","lab":"alibaba","score":26.4,"best_input_per_m":1.2,"best_output_per_m":6,"points_per_dollar":11},{"model":"zhipuai/glm-4.5","lab":"zhipuai","score":26.3,"best_input_per_m":0.6,"best_output_per_m":2.2,"points_per_dollar":26.3},{"model":"mistral/mistral-small-2603","lab":"mistral","score":24.3,"best_input_per_m":0.15,"best_output_per_m":0.6,"points_per_dollar":92.57},{"model":"openai/gpt-4o-2024-05-13","lab":"openai","score":24.2,"best_input_per_m":5,"best_output_per_m":15,"points_per_dollar":3.23},{"model":"zhipuai/glm-4.5-air","lab":"zhipuai","score":23.8,"best_input_per_m":0.2,"best_output_per_m":1.1,"points_per_dollar":56},{"model":"mistral/devstral-2512","lab":"mistral","score":23.7,"best_input_per_m":0.4,"best_output_per_m":2,"points_per_dollar":29.62},{"model":"mistral/mistral-large-2512","lab":"mistral","score":22.7,"best_input_per_m":0.5,"best_output_per_m":1.5,"points_per_dollar":30.27},{"model":"google/gemini-2.5-flash","lab":"google","score":22.2,"best_input_per_m":0.21,"best_output_per_m":1.8,"points_per_dollar":36.54},{"model":"openai/gpt-4-turbo","lab":"openai","score":21.5,"best_input_per_m":9,"best_output_per_m":27,"points_per_dollar":1.59},{"model":"alibaba/qwen3-coder-30b-a3b-instruct","lab":"alibaba","score":19.4,"best_input_per_m":0.45,"best_output_per_m":2.25,"points_per_dollar":21.56},{"model":"openai/gpt-4o-2024-11-20","lab":"openai","score":16.7,"best_input_per_m":2.5,"best_output_per_m":10,"points_per_dollar":3.82},{"model":"openai/gpt-4o-2024-08-06","lab":"openai","score":16.6,"best_input_per_m":2.5,"best_output_per_m":10,"points_per_dollar":3.79},{"model":"deepseek/deepseek-r1","lab":"deepseek","score":15.9,"best_input_per_m":0.7,"best_output_per_m":2.5,"points_per_dollar":13.83},{"model":"mistral/mistral-large-2411","lab":"mistral","score":13.8,"best_input_per_m":2,"best_output_per_m":6,"points_per_dollar":4.6},{"model":"mistral/mistral-medium-2505","lab":"mistral","score":13.6,"best_input_per_m":0.4,"best_output_per_m":2,"points_per_dollar":17},{"model":"openai/gpt-4","lab":"openai","score":13.1,"best_input_per_m":30,"best_output_per_m":60,"points_per_dollar":0.35},{"model":"zhipuai/glm-4.5v","lab":"zhipuai","score":10.9,"best_input_per_m":0.6,"best_output_per_m":1.8,"points_per_dollar":12.11},{"model":"meta/llama-3.3-70b-instruct","lab":"meta","score":10.7,"best_input_per_m":0.22,"best_output_per_m":0.5,"points_per_dollar":36.9},{"model":"openai/gpt-3.5-turbo","lab":"openai","score":10.7,"best_input_per_m":0.45,"best_output_per_m":1.4,"points_per_dollar":15.56},{"model":"google/gemini-2.5-flash-lite","lab":"google","score":9.5,"best_input_per_m":0.1,"best_output_per_m":0.1,"points_per_dollar":95}]},{"name":"Aider Polyglot","slug":"aider-polyglot","metric":"percent correct","entries":[{"model":"openai/gpt-5","lab":"openai","score":88,"best_input_per_m":1.1,"best_output_per_m":9,"points_per_dollar":28.62},{"model":"openai/o3-pro","lab":"openai","score":84.9,"best_input_per_m":18,"best_output_per_m":72,"points_per_dollar":2.7},{"model":"google/gemini-2.5-pro","lab":"google","score":83.1,"best_input_per_m":0.87,"best_output_per_m":7,"points_per_dollar":34.59},{"model":"openai/o3","lab":"openai","score":81.3,"best_input_per_m":1.8,"best_output_per_m":7.2,"points_per_dollar":25.81},{"model":"deepseek/deepseek-reasoner","lab":"deepseek","score":74.2,"best_input_per_m":0.14,"best_output_per_m":0.28,"points_per_dollar":424},{"model":"anthropic/claude-opus-4-20250514","lab":"anthropic","score":72,"best_input_per_m":15,"best_output_per_m":75,"points_per_dollar":2.4},{"model":"openai/o4-mini","lab":"openai","score":72,"best_input_per_m":0.99,"best_output_per_m":4,"points_per_dollar":41.32},{"model":"deepseek/deepseek-chat","lab":"deepseek","score":70.2,"best_input_per_m":0.14,"best_output_per_m":0.28,"points_per_dollar":401.14},{"model":"anthropic/claude-3-7-sonnet-20250219","lab":"anthropic","score":64.9,"best_input_per_m":3,"best_output_per_m":15,"points_per_dollar":10.82},{"model":"openai/o1","lab":"openai","score":61.7,"best_input_per_m":14,"best_output_per_m":54,"points_per_dollar":2.57},{"model":"anthropic/claude-sonnet-4-20250514","lab":"anthropic","score":61.3,"best_input_per_m":3,"best_output_per_m":15,"points_per_dollar":10.22},{"model":"openai/o3-mini","lab":"openai","score":60.4,"best_input_per_m":0.99,"best_output_per_m":4,"points_per_dollar":34.66},{"model":"alibaba/qwen3-235b-a22b","lab":"alibaba","score":59.6,"best_input_per_m":0.7,"best_output_per_m":2.8,"points_per_dollar":48.65},{"model":"deepseek/deepseek-r1","lab":"deepseek","score":56.9,"best_input_per_m":0.7,"best_output_per_m":2.5,"points_per_dollar":49.48},{"model":"google/gemini-2.5-flash","lab":"google","score":55.1,"best_input_per_m":0.21,"best_output_per_m":1.8,"points_per_dollar":90.7},{"model":"openai/gpt-4.1","lab":"openai","score":52.4,"best_input_per_m":1.8,"best_output_per_m":7.2,"points_per_dollar":16.63},{"model":"alibaba/qwen3-32b","lab":"alibaba","score":40,"best_input_per_m":0.7,"best_output_per_m":2.8,"points_per_dollar":32.65},{"model":"openai/gpt-4.1-mini","lab":"openai","score":32.4,"best_input_per_m":0.36,"best_output_per_m":1.4,"points_per_dollar":52.26},{"model":"openai/gpt-4o","lab":"openai","score":23.1,"best_input_per_m":1.25,"best_output_per_m":5,"points_per_dollar":10.56},{"model":"openai/gpt-4o-2024-08-06","lab":"openai","score":23.1,"best_input_per_m":2.5,"best_output_per_m":10,"points_per_dollar":5.28},{"model":"alibaba/qwen-max","lab":"alibaba","score":21.8,"best_input_per_m":1.6,"best_output_per_m":6.4,"points_per_dollar":7.79},{"model":"openai/gpt-4o-2024-11-20","lab":"openai","score":18.2,"best_input_per_m":2.5,"best_output_per_m":10,"points_per_dollar":4.16},{"model":"cohere/command-a-03-2025","lab":"cohere","score":12,"best_input_per_m":2.5,"best_output_per_m":10,"points_per_dollar":2.74},{"model":"mistral/codestral-latest","lab":"mistral","score":11.1,"best_input_per_m":0.3,"best_output_per_m":0.9,"points_per_dollar":24.67},{"model":"openai/gpt-4.1-nano","lab":"openai","score":8.9,"best_input_per_m":0.09,"best_output_per_m":0.36,"points_per_dollar":56.51},{"model":"openai/gpt-4o-mini","lab":"openai","score":3.6,"best_input_per_m":0.075,"best_output_per_m":0.3,"points_per_dollar":27.43}]},{"name":"SWE-Atlas Codebase QnA","slug":"swe-atlas-codebase-qna","metric":"score","entries":[{"model":"anthropic/claude-opus-4-7","lab":"anthropic","score":81,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":8.1},{"model":"openai/gpt-5.5","lab":"openai","score":80.8,"best_input_per_m":4.5455,"best_output_per_m":27.2727,"points_per_dollar":7.9},{"model":"openai/gpt-5.5","lab":"openai","score":79.1,"best_input_per_m":4.5455,"best_output_per_m":27.2727,"points_per_dollar":7.73},{"model":"anthropic/claude-opus-4-7","lab":"anthropic","score":78.4,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":7.84},{"model":"openai/gpt-5.5","lab":"openai","score":75,"best_input_per_m":4.5455,"best_output_per_m":27.2727,"points_per_dollar":7.33},{"model":"zhipuai/glm-5.1","lab":"zhipuai","score":73.2,"best_input_per_m":1.4,"best_output_per_m":4.4,"points_per_dollar":34.05},{"model":"openai/gpt-5.4","lab":"openai","score":72.9,"best_input_per_m":2.2,"best_output_per_m":14,"points_per_dollar":14.16},{"model":"openai/gpt-5.4","lab":"openai","score":72.4,"best_input_per_m":2.2,"best_output_per_m":14,"points_per_dollar":14.06},{"model":"anthropic/claude-opus-4-6","lab":"anthropic","score":71.9,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":7.19},{"model":"anthropic/claude-opus-4-7","lab":"anthropic","score":71.7,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":7.17},{"model":"anthropic/claude-sonnet-4-6","lab":"anthropic","score":70.3,"best_input_per_m":3,"best_output_per_m":15,"points_per_dollar":11.72},{"model":"deepseek/deepseek-v4-pro","lab":"deepseek","score":67.8,"best_input_per_m":0.435,"best_output_per_m":0.87,"points_per_dollar":124.69},{"model":"moonshotai/kimi-k2.6","lab":"moonshotai","score":59.8,"best_input_per_m":0.5,"best_output_per_m":2.6,"points_per_dollar":58.34},{"model":"google/gemini-3.1-pro-preview","lab":"google","score":45.6,"best_input_per_m":2,"best_output_per_m":12,"points_per_dollar":10.13},{"model":"openai/gpt-5.5","lab":"openai","score":45.43,"best_input_per_m":4.5455,"best_output_per_m":27.2727,"points_per_dollar":4.44},{"model":"openai/gpt-5.4","lab":"openai","score":40.8,"best_input_per_m":2.2,"best_output_per_m":14,"points_per_dollar":7.92},{"model":"openai/gpt-5.4","lab":"openai","score":36.3,"best_input_per_m":2.2,"best_output_per_m":14,"points_per_dollar":7.05},{"model":"anthropic/claude-opus-4-6","lab":"anthropic","score":33.3,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":3.33},{"model":"openai/gpt-5.3-codex","lab":"openai","score":32.6,"best_input_per_m":1.6,"best_output_per_m":13,"points_per_dollar":7.33},{"model":"anthropic/claude-sonnet-4-6","lab":"anthropic","score":31.2,"best_input_per_m":3,"best_output_per_m":15,"points_per_dollar":5.2},{"model":"anthropic/claude-opus-4-6","lab":"anthropic","score":30,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":3},{"model":"zhipuai/glm-5","lab":"zhipuai","score":20.5,"best_input_per_m":1,"best_output_per_m":3.2,"points_per_dollar":13.23},{"model":"google/gemini-3.1-pro-preview","lab":"google","score":13.5,"best_input_per_m":2,"best_output_per_m":12,"points_per_dollar":3},{"model":"moonshotai/kimi-k2.5","lab":"moonshotai","score":13.1,"best_input_per_m":0.3,"best_output_per_m":1.9,"points_per_dollar":18.71},{"model":"minimax/MiniMax-M2.5","lab":"minimax","score":10.3,"best_input_per_m":0.3,"best_output_per_m":1.2,"points_per_dollar":19.62},{"model":"google/gemini-3-flash-preview","lab":"google","score":8.2,"best_input_per_m":0.5,"best_output_per_m":3,"points_per_dollar":7.29}]},{"name":"Terminal-Bench Hard","slug":"terminal-bench-hard","metric":"success rate","entries":[{"model":"openai/gpt-5-codex","lab":"openai","score":37.9,"best_input_per_m":1.1,"best_output_per_m":9,"points_per_dollar":12.33},{"model":"stepfun/step-3.7-flash","lab":"stepfun","score":35.6,"best_input_per_m":0.185,"best_output_per_m":1.11,"points_per_dollar":85.53},{"model":"stepfun/step-3.5-flash-2603","lab":"stepfun","score":32.6,"best_input_per_m":0.1,"best_output_per_m":0.3,"points_per_dollar":217.33},{"model":"stepfun/step-3.5-flash","lab":"stepfun","score":27.3,"best_input_per_m":0.09,"best_output_per_m":0.3,"points_per_dollar":191.58},{"model":"google/gemini-2.5-pro","lab":"google","score":26.5,"best_input_per_m":0.87,"best_output_per_m":7,"points_per_dollar":11.03},{"model":"zhipuai/glm-4.6","lab":"zhipuai","score":25,"best_input_per_m":0.6,"best_output_per_m":2.2,"points_per_dollar":25},{"model":"zhipuai/glm-4.5","lab":"zhipuai","score":22,"best_input_per_m":0.6,"best_output_per_m":2.2,"points_per_dollar":22},{"model":"alibaba/qwen3-max","lab":"alibaba","score":20.5,"best_input_per_m":1.2,"best_output_per_m":6,"points_per_dollar":8.54},{"model":"zhipuai/glm-4.5-air","lab":"zhipuai","score":20.5,"best_input_per_m":0.2,"best_output_per_m":1.1,"points_per_dollar":48.24},{"model":"mistral/devstral-2512","lab":"mistral","score":18.9,"best_input_per_m":0.4,"best_output_per_m":2,"points_per_dollar":23.62},{"model":"mistral/mistral-small-2603","lab":"mistral","score":17.4,"best_input_per_m":0.15,"best_output_per_m":0.6,"points_per_dollar":66.29},{"model":"mistral/mistral-large-2512","lab":"mistral","score":15.9,"best_input_per_m":0.5,"best_output_per_m":1.5,"points_per_dollar":21.2},{"model":"alibaba/qwen3-coder-30b-a3b-instruct","lab":"alibaba","score":15.2,"best_input_per_m":0.45,"best_output_per_m":2.25,"points_per_dollar":16.89},{"model":"google/gemini-2.5-flash","lab":"google","score":13.6,"best_input_per_m":0.21,"best_output_per_m":1.8,"points_per_dollar":22.39},{"model":"openai/gpt-4o-2024-08-06","lab":"openai","score":8.3,"best_input_per_m":2.5,"best_output_per_m":10,"points_per_dollar":1.9},{"model":"openai/gpt-4o-2024-11-20","lab":"openai","score":8.3,"best_input_per_m":2.5,"best_output_per_m":10,"points_per_dollar":1.9},{"model":"deepseek/deepseek-r1","lab":"deepseek","score":6.1,"best_input_per_m":0.7,"best_output_per_m":2.5,"points_per_dollar":5.3},{"model":"mistral/mistral-large-2411","lab":"mistral","score":6.1,"best_input_per_m":2,"best_output_per_m":6,"points_per_dollar":2.03},{"model":"zhipuai/glm-4.5v","lab":"zhipuai","score":5.3,"best_input_per_m":0.6,"best_output_per_m":1.8,"points_per_dollar":5.89},{"model":"google/gemini-2.5-flash-lite","lab":"google","score":4.5,"best_input_per_m":0.1,"best_output_per_m":0.1,"points_per_dollar":45},{"model":"mistral/mistral-medium-2505","lab":"mistral","score":3.8,"best_input_per_m":0.4,"best_output_per_m":2,"points_per_dollar":4.75},{"model":"meta/llama-3.3-70b-instruct","lab":"meta","score":3,"best_input_per_m":0.22,"best_output_per_m":0.5,"points_per_dollar":10.34}]},{"name":"GPQA Diamond","slug":"gpqa-diamond","metric":"accuracy","entries":[{"model":"sakana/fugu","lab":"sakana","score":95.5,"best_input_per_m":null,"best_output_per_m":null,"points_per_dollar":null},{"model":"sakana/fugu-ultra","lab":"sakana","score":95.5,"best_input_per_m":5,"best_output_per_m":30,"points_per_dollar":8.49},{"model":"openai/gpt-5.6-sol","lab":"openai","score":94.6,"best_input_per_m":2.5,"best_output_per_m":15,"points_per_dollar":16.82},{"model":"openai/gpt-5.4-pro","lab":"openai","score":94.4,"best_input_per_m":27,"best_output_per_m":160,"points_per_dollar":1.57},{"model":"google/gemini-3.1-pro-preview","lab":"google","score":94.3,"best_input_per_m":2,"best_output_per_m":12,"points_per_dollar":20.96},{"model":"anthropic/claude-opus-4-7","lab":"anthropic","score":94.2,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":9.42},{"model":"openai/gpt-5.5","lab":"openai","score":93.6,"best_input_per_m":4.5455,"best_output_per_m":27.2727,"points_per_dollar":9.15},{"model":"openai/gpt-5.6-terra","lab":"openai","score":92.9,"best_input_per_m":1,"best_output_per_m":6,"points_per_dollar":41.29},{"model":"openai/gpt-5.4","lab":"openai","score":92.8,"best_input_per_m":2.2,"best_output_per_m":14,"points_per_dollar":18.02},{"model":"alibaba/qwen3.7-max","lab":"alibaba","score":92.4,"best_input_per_m":2.5,"best_output_per_m":7.5,"points_per_dollar":24.64},{"model":"openai/gpt-5.6-luna","lab":"openai","score":92.3,"best_input_per_m":0.1,"best_output_per_m":0.6,"points_per_dollar":410.22},{"model":"zhipuai/glm-5.2","lab":"zhipuai","score":91.2,"best_input_per_m":1.4,"best_output_per_m":4.4,"points_per_dollar":42.42},{"model":"meituan/longcat-2.0","lab":"meituan","score":88.9,"best_input_per_m":0.3,"best_output_per_m":1.2,"points_per_dollar":169.33},{"model":"openai/gpt-5.4-mini","lab":"openai","score":88,"best_input_per_m":0.68,"best_output_per_m":4,"points_per_dollar":58.28},{"model":"xiaomi/mimo-v2.5-pro","lab":"xiaomi","score":86.6,"best_input_per_m":0.435,"best_output_per_m":0.87,"points_per_dollar":159.26},{"model":"meta/muse-glimmer-30b","lab":"meta","score":83.5,"best_input_per_m":0.3,"best_output_per_m":1.1,"points_per_dollar":167},{"model":"openai/gpt-5.4-nano","lab":"openai","score":82.8,"best_input_per_m":0.18,"best_output_per_m":1.1,"points_per_dollar":201.95}]},{"name":"Artificial Analysis Coding Agent Index","slug":"artificial-analysis-coding-agent-index","metric":"average pass@1","entries":[{"model":"openai/gpt-5.6-sol","lab":"openai","score":80,"best_input_per_m":2.5,"best_output_per_m":15,"points_per_dollar":14.22},{"model":"openai/gpt-5.6-terra","lab":"openai","score":77.4,"best_input_per_m":1,"best_output_per_m":6,"points_per_dollar":34.4},{"model":"openai/gpt-5.6-luna","lab":"openai","score":74.6,"best_input_per_m":0.1,"best_output_per_m":0.6,"points_per_dollar":331.56},{"model":"anthropic/claude-opus-4-7","lab":"anthropic","score":66.6,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":6.66},{"model":"openai/gpt-5.5","lab":"openai","score":65.3,"best_input_per_m":4.5455,"best_output_per_m":27.2727,"points_per_dollar":6.38},{"model":"anthropic/claude-opus-4-7","lab":"anthropic","score":61.2,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":6.12},{"model":"openai/gpt-5.5","lab":"openai","score":60.4,"best_input_per_m":4.5455,"best_output_per_m":27.2727,"points_per_dollar":5.91},{"model":"anthropic/claude-opus-4-7","lab":"anthropic","score":59.9,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":5.99},{"model":"openai/gpt-5.5","lab":"openai","score":57.8,"best_input_per_m":4.5455,"best_output_per_m":27.2727,"points_per_dollar":5.65},{"model":"openai/gpt-5.4","lab":"openai","score":53.6,"best_input_per_m":2.2,"best_output_per_m":14,"points_per_dollar":10.41},{"model":"zhipuai/glm-5.1","lab":"zhipuai","score":52.7,"best_input_per_m":1.4,"best_output_per_m":4.4,"points_per_dollar":24.51},{"model":"openai/gpt-5.4","lab":"openai","score":52.2,"best_input_per_m":2.2,"best_output_per_m":14,"points_per_dollar":10.14},{"model":"anthropic/claude-opus-4-6","lab":"anthropic","score":51.3,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":5.13},{"model":"moonshotai/kimi-k2.6","lab":"moonshotai","score":50.5,"best_input_per_m":0.5,"best_output_per_m":2.6,"points_per_dollar":49.27},{"model":"deepseek/deepseek-v4-pro","lab":"deepseek","score":50.1,"best_input_per_m":0.435,"best_output_per_m":0.87,"points_per_dollar":92.14},{"model":"anthropic/claude-sonnet-4-6","lab":"anthropic","score":49.4,"best_input_per_m":3,"best_output_per_m":15,"points_per_dollar":8.23},{"model":"google/gemini-3.1-pro-preview","lab":"google","score":43,"best_input_per_m":2,"best_output_per_m":12,"points_per_dollar":9.56}]},{"name":"OSWorld-Verified","slug":"osworld-verified","metric":"success rate","entries":[{"model":"anthropic/claude-fable-5","lab":"anthropic","score":85,"best_input_per_m":10,"best_output_per_m":50,"points_per_dollar":4.25},{"model":"anthropic/claude-opus-4-8","lab":"anthropic","score":83.4,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":8.34},{"model":"google/gemini-3.6-flash","lab":"google","score":83,"best_input_per_m":0.75,"best_output_per_m":3.75,"points_per_dollar":55.33},{"model":"anthropic/claude-sonnet-5","lab":"anthropic","score":81.2,"best_input_per_m":2,"best_output_per_m":10,"points_per_dollar":20.3},{"model":"meta/muse-spark-1.1","lab":"meta","score":80.8,"best_input_per_m":1.25,"best_output_per_m":4.25,"points_per_dollar":40.4},{"model":"openai/gpt-5.5","lab":"openai","score":78.7,"best_input_per_m":4.5455,"best_output_per_m":27.2727,"points_per_dollar":7.7},{"model":"anthropic/claude-sonnet-4-6","lab":"anthropic","score":78.5,"best_input_per_m":3,"best_output_per_m":15,"points_per_dollar":13.08},{"model":"google/gemini-3.5-flash","lab":"google","score":78.4,"best_input_per_m":1.5,"best_output_per_m":9,"points_per_dollar":23.23},{"model":"anthropic/claude-opus-4-7","lab":"anthropic","score":78,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":7.8},{"model":"google/gemini-3.1-pro-preview","lab":"google","score":76.2,"best_input_per_m":2,"best_output_per_m":12,"points_per_dollar":16.93},{"model":"openai/gpt-5.4","lab":"openai","score":75,"best_input_per_m":2.2,"best_output_per_m":14,"points_per_dollar":14.56},{"model":"google/gemini-3.5-flash-lite","lab":"google","score":74,"best_input_per_m":0.3,"best_output_per_m":2.5,"points_per_dollar":87.06},{"model":"openai/gpt-5.4-mini","lab":"openai","score":72.1,"best_input_per_m":0.68,"best_output_per_m":4,"points_per_dollar":47.75},{"model":"minimax/MiniMax-M3","lab":"minimax","score":70.06,"best_input_per_m":0.3,"best_output_per_m":1.2,"points_per_dollar":133.45},{"model":"meta/muse-glimmer-30b","lab":"meta","score":65.9,"best_input_per_m":0.3,"best_output_per_m":1.1,"points_per_dollar":131.8},{"model":"openai/gpt-5.4-nano","lab":"openai","score":39,"best_input_per_m":0.18,"best_output_per_m":1.1,"points_per_dollar":95.12}]},{"name":"BrowseComp","slug":"browsecomp","metric":"accuracy","entries":[{"model":"moonshotai/kimi-k3","lab":"moonshotai","score":91.2,"best_input_per_m":2.5,"best_output_per_m":13.5,"points_per_dollar":17.37},{"model":"anthropic/claude-opus-5","lab":"anthropic","score":90.8,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":9.08},{"model":"openai/gpt-5.6-sol","lab":"openai","score":90.4,"best_input_per_m":2.5,"best_output_per_m":15,"points_per_dollar":16.07},{"model":"openai/gpt-5.5-pro","lab":"openai","score":90.1,"best_input_per_m":27.2727,"best_output_per_m":163.6364,"points_per_dollar":1.47},{"model":"openai/gpt-5.4-pro","lab":"openai","score":89.3,"best_input_per_m":27,"best_output_per_m":160,"points_per_dollar":1.48},{"model":"openai/gpt-5.6-terra","lab":"openai","score":87.5,"best_input_per_m":1,"best_output_per_m":6,"points_per_dollar":38.89},{"model":"anthropic/claude-sonnet-5","lab":"anthropic","score":84.7,"best_input_per_m":2,"best_output_per_m":10,"points_per_dollar":21.18},{"model":"openai/gpt-5.5","lab":"openai","score":84.4,"best_input_per_m":4.5455,"best_output_per_m":27.2727,"points_per_dollar":8.25},{"model":"minimax/MiniMax-M3","lab":"minimax","score":83.52,"best_input_per_m":0.3,"best_output_per_m":1.2,"points_per_dollar":159.09},{"model":"openai/gpt-5.6-luna","lab":"openai","score":83.3,"best_input_per_m":0.1,"best_output_per_m":0.6,"points_per_dollar":370.22},{"model":"openai/gpt-5.4","lab":"openai","score":82.7,"best_input_per_m":2.2,"best_output_per_m":14,"points_per_dollar":16.06},{"model":"meituan/longcat-2.0","lab":"meituan","score":79.9,"best_input_per_m":0.3,"best_output_per_m":1.2,"points_per_dollar":152.19},{"model":"stepfun/step-3.7-flash","lab":"stepfun","score":75.8,"best_input_per_m":0.185,"best_output_per_m":1.11,"points_per_dollar":182.1},{"model":"nvidia/nemotron-3-ultra-550b-a55b","lab":"nvidia","score":44.4,"best_input_per_m":0.5,"best_output_per_m":2.2,"points_per_dollar":48}]},{"name":"SWE-Atlas Test Writing","slug":"swe-atlas-test-writing","metric":"score","entries":[{"model":"openai/gpt-5.4","lab":"openai","score":44.36,"best_input_per_m":2.2,"best_output_per_m":14,"points_per_dollar":8.61},{"model":"openai/gpt-5.5","lab":"openai","score":42.59,"best_input_per_m":4.5455,"best_output_per_m":27.2727,"points_per_dollar":4.16},{"model":"openai/gpt-5.4","lab":"openai","score":40,"best_input_per_m":2.2,"best_output_per_m":14,"points_per_dollar":7.77},{"model":"openai/gpt-5.3-codex","lab":"openai","score":38.98,"best_input_per_m":1.6,"best_output_per_m":13,"points_per_dollar":8.76},{"model":"anthropic/claude-opus-4-6","lab":"anthropic","score":36.67,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":3.67},{"model":"anthropic/claude-opus-4-6","lab":"anthropic","score":36.08,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":3.61},{"model":"anthropic/claude-sonnet-4-6","lab":"anthropic","score":31.76,"best_input_per_m":3,"best_output_per_m":15,"points_per_dollar":5.29},{"model":"google/gemini-3-flash-preview","lab":"google","score":30.3,"best_input_per_m":0.5,"best_output_per_m":3,"points_per_dollar":26.93},{"model":"google/gemini-3.1-pro-preview","lab":"google","score":29.84,"best_input_per_m":2,"best_output_per_m":12,"points_per_dollar":6.63},{"model":"zhipuai/glm-5","lab":"zhipuai","score":28.74,"best_input_per_m":1,"best_output_per_m":3.2,"points_per_dollar":18.54},{"model":"moonshotai/kimi-k2.5","lab":"moonshotai","score":25.77,"best_input_per_m":0.3,"best_output_per_m":1.9,"points_per_dollar":36.81},{"model":"minimax/MiniMax-M2.5","lab":"minimax","score":18.6,"best_input_per_m":0.3,"best_output_per_m":1.2,"points_per_dollar":35.43}]},{"name":"DeepSWE","slug":"deepswe","metric":"resolve rate","entries":[{"model":"openai/gpt-5.6-sol","lab":"openai","score":72.7,"best_input_per_m":2.5,"best_output_per_m":15,"points_per_dollar":12.92},{"model":"openai/gpt-5.6-terra","lab":"openai","score":69.6,"best_input_per_m":1,"best_output_per_m":6,"points_per_dollar":30.93},{"model":"anthropic/claude-opus-5","lab":"anthropic","score":68.8,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":6.88},{"model":"moonshotai/kimi-k3","lab":"moonshotai","score":67.5,"best_input_per_m":2.5,"best_output_per_m":13.5,"points_per_dollar":12.86},{"model":"openai/gpt-5.6-luna","lab":"openai","score":67.2,"best_input_per_m":0.1,"best_output_per_m":0.6,"points_per_dollar":298.67},{"model":"google/gemini-3.7-flash","lab":"google","score":65.3,"best_input_per_m":0.375,"best_output_per_m":1.875,"points_per_dollar":87.07},{"model":"xai/grok-4.5","lab":"xai","score":62,"best_input_per_m":2,"best_output_per_m":6,"points_per_dollar":20.67},{"model":"deepseek/deepseek-v4-flash-0731","lab":"deepseek","score":54.4,"best_input_per_m":0.08,"best_output_per_m":0.18,"points_per_dollar":518.1},{"model":"meta/muse-spark-1.1","lab":"meta","score":53.3,"best_input_per_m":1.25,"best_output_per_m":4.25,"points_per_dollar":26.65},{"model":"xai/grok-4.5","lab":"xai","score":53,"best_input_per_m":2,"best_output_per_m":6,"points_per_dollar":17.67},{"model":"google/gemini-3.6-flash","lab":"google","score":49,"best_input_per_m":0.75,"best_output_per_m":3.75,"points_per_dollar":32.67},{"model":"zhipuai/glm-5.2","lab":"zhipuai","score":46.2,"best_input_per_m":1.4,"best_output_per_m":4.4,"points_per_dollar":21.49}]},{"name":"MCP Atlas","slug":"mcp-atlas","metric":"success rate","entries":[{"model":"meta/muse-spark-1.1","lab":"meta","score":88.1,"best_input_per_m":1.25,"best_output_per_m":4.25,"points_per_dollar":44.05},{"model":"google/gemini-3.5-flash","lab":"google","score":83.6,"best_input_per_m":1.5,"best_output_per_m":9,"points_per_dollar":24.77},{"model":"google/gemini-3.1-pro-preview","lab":"google","score":78.2,"best_input_per_m":2,"best_output_per_m":12,"points_per_dollar":17.38},{"model":"zhipuai/glm-5.2","lab":"zhipuai","score":76.8,"best_input_per_m":1.4,"best_output_per_m":4.4,"points_per_dollar":35.72},{"model":"alibaba/qwen3.7-max","lab":"alibaba","score":76.4,"best_input_per_m":2.5,"best_output_per_m":7.5,"points_per_dollar":20.37},{"model":"moonshotai/kimi-k2.7-code","lab":"moonshotai","score":76,"best_input_per_m":0.67,"best_output_per_m":3.4,"points_per_dollar":56.19},{"model":"meta/muse-glimmer-30b","lab":"meta","score":75.5,"best_input_per_m":0.3,"best_output_per_m":1.1,"points_per_dollar":151},{"model":"openai/gpt-5.5","lab":"openai","score":75.3,"best_input_per_m":4.5455,"best_output_per_m":27.2727,"points_per_dollar":7.36},{"model":"minimax/MiniMax-M3","lab":"minimax","score":74.2,"best_input_per_m":0.3,"best_output_per_m":1.2,"points_per_dollar":141.33},{"model":"openai/gpt-5.4-mini","lab":"openai","score":57.7,"best_input_per_m":0.68,"best_output_per_m":4,"points_per_dollar":38.21},{"model":"openai/gpt-5.4-nano","lab":"openai","score":56.1,"best_input_per_m":0.18,"best_output_per_m":1.1,"points_per_dollar":136.83}]},{"name":"SWE-Atlas Refactoring","slug":"swe-atlas-refactoring","metric":"score","entries":[{"model":"anthropic/claude-opus-4-7","lab":"anthropic","score":48.57,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":4.86},{"model":"openai/gpt-5.5","lab":"openai","score":44.79,"best_input_per_m":4.5455,"best_output_per_m":27.2727,"points_per_dollar":4.38},{"model":"openai/gpt-5.4","lab":"openai","score":44.29,"best_input_per_m":2.2,"best_output_per_m":14,"points_per_dollar":8.6},{"model":"openai/gpt-5.3-codex","lab":"openai","score":42.38,"best_input_per_m":1.6,"best_output_per_m":13,"points_per_dollar":9.52},{"model":"anthropic/claude-opus-4-6","lab":"anthropic","score":35.58,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":3.56},{"model":"google/gemini-3.1-pro-preview","lab":"google","score":33.81,"best_input_per_m":2,"best_output_per_m":12,"points_per_dollar":7.51},{"model":"anthropic/claude-sonnet-4-6","lab":"anthropic","score":32.21,"best_input_per_m":3,"best_output_per_m":15,"points_per_dollar":5.37},{"model":"zhipuai/glm-5","lab":"zhipuai","score":24.24,"best_input_per_m":1,"best_output_per_m":3.2,"points_per_dollar":15.64},{"model":"moonshotai/kimi-k2.5","lab":"moonshotai","score":20.95,"best_input_per_m":0.3,"best_output_per_m":1.9,"points_per_dollar":29.93},{"model":"minimax/MiniMax-M2.5","lab":"minimax","score":19.52,"best_input_per_m":0.3,"best_output_per_m":1.2,"points_per_dollar":37.18},{"model":"google/gemini-3-flash-preview","lab":"google","score":10,"best_input_per_m":0.5,"best_output_per_m":3,"points_per_dollar":8.89}]},{"name":"MMMU Pro","slug":"mmmu-pro","metric":"accuracy","entries":[{"model":"google/gemini-3.5-flash","lab":"google","score":83.6,"best_input_per_m":1.5,"best_output_per_m":9,"points_per_dollar":24.77},{"model":"openai/gpt-5.6-sol","lab":"openai","score":83,"best_input_per_m":2.5,"best_output_per_m":15,"points_per_dollar":14.76},{"model":"openai/gpt-5.4","lab":"openai","score":81.2,"best_input_per_m":2.2,"best_output_per_m":14,"points_per_dollar":15.77},{"model":"openai/gpt-5.5","lab":"openai","score":81.2,"best_input_per_m":4.5455,"best_output_per_m":27.2727,"points_per_dollar":7.94},{"model":"openai/gpt-5.6-terra","lab":"openai","score":80.7,"best_input_per_m":1,"best_output_per_m":6,"points_per_dollar":35.87},{"model":"google/gemini-3.1-pro-preview","lab":"google","score":80.5,"best_input_per_m":2,"best_output_per_m":12,"points_per_dollar":17.89},{"model":"openai/gpt-5.6-luna","lab":"openai","score":78.4,"best_input_per_m":0.1,"best_output_per_m":0.6,"points_per_dollar":348.44},{"model":"openai/gpt-5.4-mini","lab":"openai","score":78,"best_input_per_m":0.68,"best_output_per_m":4,"points_per_dollar":51.66},{"model":"openai/gpt-5.4-mini","lab":"openai","score":76.6,"best_input_per_m":0.68,"best_output_per_m":4,"points_per_dollar":50.73},{"model":"openai/gpt-5.4-nano","lab":"openai","score":69.5,"best_input_per_m":0.18,"best_output_per_m":1.1,"points_per_dollar":169.51},{"model":"openai/gpt-5.4-nano","lab":"openai","score":66.1,"best_input_per_m":0.18,"best_output_per_m":1.1,"points_per_dollar":161.22}]},{"name":"CharXiv Reasoning","slug":"charxiv-reasoning","metric":"accuracy","entries":[{"model":"moonshotai/kimi-k3","lab":"moonshotai","score":91.3,"best_input_per_m":2.5,"best_output_per_m":13.5,"points_per_dollar":17.39},{"model":"google/gemini-3.6-flash","lab":"google","score":89.4,"best_input_per_m":0.75,"best_output_per_m":3.75,"points_per_dollar":59.6},{"model":"meta/muse-spark-1.1","lab":"meta","score":88.4,"best_input_per_m":1.25,"best_output_per_m":4.25,"points_per_dollar":44.2},{"model":"sakana/fugu-ultra","lab":"sakana","score":86.6,"best_input_per_m":5,"best_output_per_m":30,"points_per_dollar":7.7},{"model":"google/gemini-3.6-flash","lab":"google","score":85.2,"best_input_per_m":0.75,"best_output_per_m":3.75,"points_per_dollar":56.8},{"model":"sakana/fugu","lab":"sakana","score":85.1,"best_input_per_m":null,"best_output_per_m":null,"points_per_dollar":null},{"model":"google/gemini-3.5-flash","lab":"google","score":84.2,"best_input_per_m":1.5,"best_output_per_m":9,"points_per_dollar":24.95},{"model":"google/gemini-3.1-pro-preview","lab":"google","score":83.3,"best_input_per_m":2,"best_output_per_m":12,"points_per_dollar":18.51},{"model":"meta/muse-glimmer-30b","lab":"meta","score":78.8,"best_input_per_m":0.3,"best_output_per_m":1.1,"points_per_dollar":157.6},{"model":"google/gemini-3.5-flash-lite","lab":"google","score":76.5,"best_input_per_m":0.3,"best_output_per_m":2.5,"points_per_dollar":90},{"model":"google/gemini-3.5-flash-lite","lab":"google","score":74.5,"best_input_per_m":0.3,"best_output_per_m":2.5,"points_per_dollar":87.65}]},{"name":"FrontierMath","slug":"frontiermath","metric":"accuracy","entries":[{"model":"openai/gpt-5.6-sol","lab":"openai","score":89,"best_input_per_m":2.5,"best_output_per_m":15,"points_per_dollar":15.82},{"model":"openai/gpt-5.6-terra","lab":"openai","score":84.9,"best_input_per_m":1,"best_output_per_m":6,"points_per_dollar":37.73},{"model":"openai/gpt-5.6-luna","lab":"openai","score":78.6,"best_input_per_m":0.1,"best_output_per_m":0.6,"points_per_dollar":349.33},{"model":"openai/gpt-5.5-pro","lab":"openai","score":52.4,"best_input_per_m":27.2727,"best_output_per_m":163.6364,"points_per_dollar":0.85},{"model":"openai/gpt-5.5","lab":"openai","score":51.7,"best_input_per_m":4.5455,"best_output_per_m":27.2727,"points_per_dollar":5.06},{"model":"openai/gpt-5.4-pro","lab":"openai","score":50,"best_input_per_m":27,"best_output_per_m":160,"points_per_dollar":0.83},{"model":"openai/gpt-5.4","lab":"openai","score":47.6,"best_input_per_m":2.2,"best_output_per_m":14,"points_per_dollar":9.24},{"model":"openai/gpt-5.5-pro","lab":"openai","score":39.6,"best_input_per_m":27.2727,"best_output_per_m":163.6364,"points_per_dollar":0.65},{"model":"openai/gpt-5.4-pro","lab":"openai","score":38,"best_input_per_m":27,"best_output_per_m":160,"points_per_dollar":0.63},{"model":"openai/gpt-5.5","lab":"openai","score":35.4,"best_input_per_m":4.5455,"best_output_per_m":27.2727,"points_per_dollar":3.46},{"model":"openai/gpt-5.4","lab":"openai","score":27.1,"best_input_per_m":2.2,"best_output_per_m":14,"points_per_dollar":5.26}]},{"name":"GDPval-AA","slug":"gdpval-aa","metric":"Elo","entries":[{"model":"anthropic/claude-fable-5","lab":"anthropic","score":1932,"best_input_per_m":10,"best_output_per_m":50,"points_per_dollar":96.6},{"model":"anthropic/claude-opus-5","lab":"anthropic","score":1861,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":186.1},{"model":"moonshotai/kimi-k3","lab":"moonshotai","score":1668,"best_input_per_m":2.5,"best_output_per_m":13.5,"points_per_dollar":317.71},{"model":"google/gemini-3.5-flash","lab":"google","score":1656,"best_input_per_m":1.5,"best_output_per_m":9,"points_per_dollar":490.67},{"model":"xai/grok-4.3","lab":"xai","score":1500,"best_input_per_m":1.25,"best_output_per_m":2.5,"points_per_dollar":960},{"model":"google/gemini-3.6-flash","lab":"google","score":1421,"best_input_per_m":0.75,"best_output_per_m":3.75,"points_per_dollar":947.33},{"model":"google/gemini-3.1-pro-preview","lab":"google","score":1314,"best_input_per_m":2,"best_output_per_m":12,"points_per_dollar":292},{"model":"google/gemini-3.5-flash-lite","lab":"google","score":1140,"best_input_per_m":0.3,"best_output_per_m":2.5,"points_per_dollar":1341.18},{"model":"cohere/north-mini-code-1-0","lab":"cohere","score":14,"best_input_per_m":null,"best_output_per_m":null,"points_per_dollar":null}]},{"name":"Toolathlon","slug":"toolathlon","metric":"success rate","entries":[{"model":"openai/gpt-5.6-sol","lab":"openai","score":58,"best_input_per_m":2.5,"best_output_per_m":15,"points_per_dollar":10.31},{"model":"google/gemini-3.5-flash","lab":"google","score":56.5,"best_input_per_m":1.5,"best_output_per_m":9,"points_per_dollar":16.74},{"model":"openai/gpt-5.5","lab":"openai","score":55.6,"best_input_per_m":4.5455,"best_output_per_m":27.2727,"points_per_dollar":5.44},{"model":"openai/gpt-5.6-luna","lab":"openai","score":53.4,"best_input_per_m":0.1,"best_output_per_m":0.6,"points_per_dollar":237.33},{"model":"openai/gpt-5.6-terra","lab":"openai","score":53.1,"best_input_per_m":1,"best_output_per_m":6,"points_per_dollar":23.6},{"model":"stepfun/step-3.7-flash","lab":"stepfun","score":49.5,"best_input_per_m":0.185,"best_output_per_m":1.11,"points_per_dollar":118.92},{"model":"openai/gpt-5.4-mini","lab":"openai","score":42.9,"best_input_per_m":0.68,"best_output_per_m":4,"points_per_dollar":28.41},{"model":"openai/gpt-5.4-nano","lab":"openai","score":35.5,"best_input_per_m":0.18,"best_output_per_m":1.1,"points_per_dollar":86.59}]},{"name":"SWE-Bench Multilingual","slug":"swe-bench-multilingual","metric":"resolve rate","entries":[{"model":"anthropic/claude-opus-5","lab":"anthropic","score":89.5,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":8.95},{"model":"alibaba/qwen3.7-max","lab":"alibaba","score":78.3,"best_input_per_m":2.5,"best_output_per_m":7.5,"points_per_dollar":20.88},{"model":"anthropic/claude-sonnet-5","lab":"anthropic","score":78.3,"best_input_per_m":2,"best_output_per_m":10,"points_per_dollar":19.58},{"model":"xai/grok-4.5","lab":"xai","score":78,"best_input_per_m":2,"best_output_per_m":6,"points_per_dollar":26},{"model":"meituan/longcat-2.0","lab":"meituan","score":77.3,"best_input_per_m":0.3,"best_output_per_m":1.2,"points_per_dollar":147.24},{"model":"nvidia/nemotron-3-ultra-550b-a55b","lab":"nvidia","score":67.7,"best_input_per_m":0.5,"best_output_per_m":2.2,"points_per_dollar":73.19},{"model":"poolside/laguna-xs-2.1","lab":"poolside","score":63.1,"best_input_per_m":0.06,"best_output_per_m":0.12,"points_per_dollar":841.33}]},{"name":"ARC-AGI-2","slug":"arc-agi-2","metric":"accuracy","entries":[{"model":"anthropic/claude-opus-5","lab":"anthropic","score":90.4,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":9.04},{"model":"openai/gpt-5.5","lab":"openai","score":85,"best_input_per_m":4.5455,"best_output_per_m":27.2727,"points_per_dollar":8.31},{"model":"openai/gpt-5.4-pro","lab":"openai","score":83.3,"best_input_per_m":27,"best_output_per_m":160,"points_per_dollar":1.38},{"model":"google/gemini-3.1-pro-preview","lab":"google","score":77.1,"best_input_per_m":2,"best_output_per_m":12,"points_per_dollar":17.13},{"model":"openai/gpt-5.4","lab":"openai","score":73.3,"best_input_per_m":2.2,"best_output_per_m":14,"points_per_dollar":14.23},{"model":"google/gemini-3.5-flash","lab":"google","score":72.1,"best_input_per_m":1.5,"best_output_per_m":9,"points_per_dollar":21.36}]},{"name":"GDPval","slug":"gdpval","metric":"wins or ties","entries":[{"model":"openai/gpt-5.5","lab":"openai","score":84.9,"best_input_per_m":4.5455,"best_output_per_m":27.2727,"points_per_dollar":8.3},{"model":"openai/gpt-5.4","lab":"openai","score":83,"best_input_per_m":2.2,"best_output_per_m":14,"points_per_dollar":16.12},{"model":"openai/gpt-5.5-pro","lab":"openai","score":82.3,"best_input_per_m":27.2727,"best_output_per_m":163.6364,"points_per_dollar":1.34},{"model":"openai/gpt-5.4-pro","lab":"openai","score":82,"best_input_per_m":27,"best_output_per_m":160,"points_per_dollar":1.36},{"model":"nvidia/nemotron-3-ultra-550b-a55b","lab":"nvidia","score":46.7,"best_input_per_m":0.5,"best_output_per_m":2.2,"points_per_dollar":50.49},{"model":"stepfun/step-3.7-flash","lab":"stepfun","score":45.8,"best_input_per_m":0.185,"best_output_per_m":1.11,"points_per_dollar":110.03}]},{"name":"FrontierCode","slug":"frontiercode","metric":"pass rate","entries":[{"model":"anthropic/claude-opus-5","lab":"anthropic","score":53.4,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":5.34},{"model":"google/gemini-3.7-flash","lab":"google","score":43.6,"best_input_per_m":0.375,"best_output_per_m":1.875,"points_per_dollar":58.13},{"model":"anthropic/claude-sonnet-5","lab":"anthropic","score":38.8,"best_input_per_m":2,"best_output_per_m":10,"points_per_dollar":9.7},{"model":"anthropic/claude-fable-5","lab":"anthropic","score":29.3,"best_input_per_m":10,"best_output_per_m":50,"points_per_dollar":1.47},{"model":"anthropic/claude-opus-4-8","lab":"anthropic","score":13.4,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":1.34}]},{"name":"AutomationBench","slug":"automationbench","metric":"success rate","entries":[{"model":"moonshotai/kimi-k3","lab":"moonshotai","score":30.8,"best_input_per_m":2.5,"best_output_per_m":13.5,"points_per_dollar":5.87},{"model":"google/gemini-3.7-flash","lab":"google","score":30.4,"best_input_per_m":0.375,"best_output_per_m":1.875,"points_per_dollar":40.53},{"model":"anthropic/claude-opus-5","lab":"anthropic","score":26,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":2.6},{"model":"deepseek/deepseek-v4-flash-0731","lab":"deepseek","score":25.1,"best_input_per_m":0.08,"best_output_per_m":0.18,"points_per_dollar":239.05},{"model":"anthropic/claude-fable-5","lab":"anthropic","score":17.4,"best_input_per_m":10,"best_output_per_m":50,"points_per_dollar":0.87}]},{"name":"Artificial Analysis Intelligence Index","slug":"artificial-analysis-intelligence-index","metric":"index score","entries":[{"model":"openai/gpt-5.6-sol","lab":"openai","score":58.9,"best_input_per_m":2.5,"best_output_per_m":15,"points_per_dollar":10.47},{"model":"openai/gpt-5.6-terra","lab":"openai","score":55,"best_input_per_m":1,"best_output_per_m":6,"points_per_dollar":24.44},{"model":"xai/grok-4.3","lab":"xai","score":53,"best_input_per_m":1.25,"best_output_per_m":2.5,"points_per_dollar":33.92},{"model":"openai/gpt-5.6-luna","lab":"openai","score":51.2,"best_input_per_m":0.1,"best_output_per_m":0.6,"points_per_dollar":227.56},{"model":"cohere/north-mini-code-1-0","lab":"cohere","score":27.6,"best_input_per_m":null,"best_output_per_m":null,"points_per_dollar":null}]},{"name":"τ²-Bench Telecom","slug":"bench-telecom","metric":"success rate","entries":[{"model":"openai/gpt-5.5","lab":"openai","score":98,"best_input_per_m":4.5455,"best_output_per_m":27.2727,"points_per_dollar":9.58},{"model":"xai/grok-4.3","lab":"xai","score":98,"best_input_per_m":1.25,"best_output_per_m":2.5,"points_per_dollar":62.72},{"model":"openai/gpt-5.4-mini","lab":"openai","score":93.4,"best_input_per_m":0.68,"best_output_per_m":4,"points_per_dollar":61.85},{"model":"openai/gpt-5.4-nano","lab":"openai","score":92.5,"best_input_per_m":0.18,"best_output_per_m":1.1,"points_per_dollar":225.61},{"model":"cohere/north-mini-code-1-0","lab":"cohere","score":37,"best_input_per_m":null,"best_output_per_m":null,"points_per_dollar":null}]},{"name":"GDM-MRCR","slug":"gdm-mrcr","metric":"accuracy","entries":[{"model":"google/gemini-3.7-flash","lab":"google","score":97,"best_input_per_m":0.375,"best_output_per_m":1.875,"points_per_dollar":129.33},{"model":"google/gemini-3.6-flash","lab":"google","score":91.8,"best_input_per_m":0.75,"best_output_per_m":3.75,"points_per_dollar":61.2},{"model":"google/gemini-3.5-flash-lite","lab":"google","score":72.2,"best_input_per_m":0.3,"best_output_per_m":2.5,"points_per_dollar":84.94},{"model":"google/gemini-3.6-flash","lab":"google","score":54,"best_input_per_m":0.75,"best_output_per_m":3.75,"points_per_dollar":36},{"model":"google/gemini-3.5-flash-lite","lab":"google","score":21.3,"best_input_per_m":0.3,"best_output_per_m":2.5,"points_per_dollar":25.06}]},{"name":"OSWorld","slug":"osworld","metric":"success rate","entries":[{"model":"anthropic/claude-opus-5","lab":"anthropic","score":70.6,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":7.06},{"model":"openai/gpt-5.6-sol","lab":"openai","score":62.6,"best_input_per_m":2.5,"best_output_per_m":15,"points_per_dollar":11.13},{"model":"openai/gpt-5.6-terra","lab":"openai","score":50.2,"best_input_per_m":1,"best_output_per_m":6,"points_per_dollar":22.31},{"model":"openai/gpt-5.6-luna","lab":"openai","score":45.6,"best_input_per_m":0.1,"best_output_per_m":0.6,"points_per_dollar":202.67}]},{"name":"Agents' Last Exam","slug":"agents-last-exam","metric":"score","entries":[{"model":"openai/gpt-5.6-sol","lab":"openai","score":52.7,"best_input_per_m":2.5,"best_output_per_m":15,"points_per_dollar":9.37},{"model":"openai/gpt-5.6-terra","lab":"openai","score":50.4,"best_input_per_m":1,"best_output_per_m":6,"points_per_dollar":22.4},{"model":"openai/gpt-5.6-luna","lab":"openai","score":50.3,"best_input_per_m":0.1,"best_output_per_m":0.6,"points_per_dollar":223.56},{"model":"deepseek/deepseek-v4-flash-0731","lab":"deepseek","score":25.2,"best_input_per_m":0.08,"best_output_per_m":0.18,"points_per_dollar":240}]},{"name":"OpenAI MRCR","slug":"openai-mrcr","metric":"accuracy","entries":[{"model":"openai/gpt-5.4-mini","lab":"openai","score":47.7,"best_input_per_m":0.68,"best_output_per_m":4,"points_per_dollar":31.59},{"model":"openai/gpt-5.4-nano","lab":"openai","score":44.2,"best_input_per_m":0.18,"best_output_per_m":1.1,"points_per_dollar":107.8},{"model":"openai/gpt-5.4-mini","lab":"openai","score":33.6,"best_input_per_m":0.68,"best_output_per_m":4,"points_per_dollar":22.25},{"model":"openai/gpt-5.4-nano","lab":"openai","score":33.1,"best_input_per_m":0.18,"best_output_per_m":1.1,"points_per_dollar":80.73}]},{"name":"Graphwalks","slug":"graphwalks","metric":"accuracy","entries":[{"model":"openai/gpt-5.4-mini","lab":"openai","score":76.3,"best_input_per_m":0.68,"best_output_per_m":4,"points_per_dollar":50.53},{"model":"openai/gpt-5.4-nano","lab":"openai","score":73.4,"best_input_per_m":0.18,"best_output_per_m":1.1,"points_per_dollar":179.02},{"model":"openai/gpt-5.4-mini","lab":"openai","score":71.5,"best_input_per_m":0.68,"best_output_per_m":4,"points_per_dollar":47.35},{"model":"openai/gpt-5.4-nano","lab":"openai","score":50.8,"best_input_per_m":0.18,"best_output_per_m":1.1,"points_per_dollar":123.9}]},{"name":"NL2Repo","slug":"nl2repo","metric":null,"entries":[{"model":"deepseek/deepseek-v4-flash-0731","lab":"deepseek","score":54.2,"best_input_per_m":0.08,"best_output_per_m":0.18,"points_per_dollar":516.19},{"model":"zhipuai/glm-5.2","lab":"zhipuai","score":48.9,"best_input_per_m":1.4,"best_output_per_m":4.4,"points_per_dollar":22.74},{"model":"alibaba/qwen3.7-max","lab":"alibaba","score":47.2,"best_input_per_m":2.5,"best_output_per_m":7.5,"points_per_dollar":12.59}]},{"name":"Program Bench","slug":"program-bench","metric":null,"entries":[{"model":"moonshotai/kimi-k3","lab":"moonshotai","score":77.8,"best_input_per_m":2.5,"best_output_per_m":13.5,"points_per_dollar":14.82},{"model":"zhipuai/glm-5.2","lab":"zhipuai","score":63.7,"best_input_per_m":1.4,"best_output_per_m":4.4,"points_per_dollar":29.63},{"model":"moonshotai/kimi-k2.7-code","lab":"moonshotai","score":53.6,"best_input_per_m":0.67,"best_output_per_m":3.4,"points_per_dollar":39.63}]},{"name":"SWE Marathon","slug":"swe-marathon","metric":"resolve rate","entries":[{"model":"moonshotai/kimi-k3","lab":"moonshotai","score":42,"best_input_per_m":2.5,"best_output_per_m":13.5,"points_per_dollar":8},{"model":"xai/grok-4.5","lab":"xai","score":29,"best_input_per_m":2,"best_output_per_m":6,"points_per_dollar":9.67},{"model":"zhipuai/glm-5.2","lab":"zhipuai","score":13,"best_input_per_m":1.4,"best_output_per_m":4.4,"points_per_dollar":6.05}]},{"name":"LiveCodeBench","slug":"livecodebench","metric":"pass@1","entries":[{"model":"sakana/fugu-ultra","lab":"sakana","score":93.2,"best_input_per_m":5,"best_output_per_m":30,"points_per_dollar":8.28},{"model":"sakana/fugu","lab":"sakana","score":92.9,"best_input_per_m":null,"best_output_per_m":null,"points_per_dollar":null},{"model":"nvidia/nemotron-3-ultra-550b-a55b","lab":"nvidia","score":89,"best_input_per_m":0.5,"best_output_per_m":2.2,"points_per_dollar":96.22}]},{"name":"AA-Briefcase","slug":"aa-briefcase","metric":"Elo","entries":[{"model":"anthropic/claude-opus-5","lab":"anthropic","score":1720,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":172},{"model":"moonshotai/kimi-k3","lab":"moonshotai","score":1548,"best_input_per_m":2.5,"best_output_per_m":13.5,"points_per_dollar":294.86}]},{"name":"ARC-AGI-1","slug":"arc-agi-1","metric":"accuracy","entries":[{"model":"anthropic/claude-opus-5","lab":"anthropic","score":97.5,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":9.75},{"model":"openai/gpt-5.4-pro","lab":"openai","score":94.5,"best_input_per_m":27,"best_output_per_m":160,"points_per_dollar":1.57}]},{"name":"Toolathlon-Verified","slug":"toolathlon-verified","metric":"score","entries":[{"model":"meta/muse-spark-1.1","lab":"meta","score":75.6,"best_input_per_m":1.25,"best_output_per_m":4.25,"points_per_dollar":37.8},{"model":"deepseek/deepseek-v4-flash-0731","lab":"deepseek","score":70.3,"best_input_per_m":0.08,"best_output_per_m":0.18,"points_per_dollar":669.52}]},{"name":"MLE-Bench","slug":"mle-bench","metric":"average position score","entries":[{"model":"google/gemini-3.6-flash","lab":"google","score":63.9,"best_input_per_m":0.75,"best_output_per_m":3.75,"points_per_dollar":42.6},{"model":"google/gemini-3.5-flash-lite","lab":"google","score":39.2,"best_input_per_m":0.3,"best_output_per_m":2.5,"points_per_dollar":46.12}]},{"name":"JobBench","slug":"jobbench","metric":"success rate","entries":[{"model":"meta/muse-spark-1.1","lab":"meta","score":54.7,"best_input_per_m":1.25,"best_output_per_m":4.25,"points_per_dollar":27.35},{"model":"moonshotai/kimi-k3","lab":"moonshotai","score":52.9,"best_input_per_m":2.5,"best_output_per_m":13.5,"points_per_dollar":10.08}]},{"name":"FrontierSWE","slug":"frontierswe","metric":"dominance score","entries":[{"model":"moonshotai/kimi-k3","lab":"moonshotai","score":81.2,"best_input_per_m":2.5,"best_output_per_m":13.5,"points_per_dollar":15.47},{"model":"zhipuai/glm-5.2","lab":"zhipuai","score":74.4,"best_input_per_m":1.4,"best_output_per_m":4.4,"points_per_dollar":34.6}]},{"name":"MMLU-Pro","slug":"mmlu-pro","metric":"accuracy","entries":[{"model":"sakana/sakana-namazu","lab":"sakana","score":90.33,"best_input_per_m":0.95,"best_output_per_m":4,"points_per_dollar":52.75},{"model":"nvidia/nemotron-3-ultra-550b-a55b","lab":"nvidia","score":86.8,"best_input_per_m":0.5,"best_output_per_m":2.2,"points_per_dollar":93.84}]},{"name":"IFBench","slug":"ifbench","metric":"accuracy","entries":[{"model":"nvidia/nemotron-3-ultra-550b-a55b","lab":"nvidia","score":81.7,"best_input_per_m":0.5,"best_output_per_m":2.2,"points_per_dollar":88.32},{"model":"xai/grok-4.3","lab":"xai","score":81,"best_input_per_m":1.25,"best_output_per_m":2.5,"points_per_dollar":51.84}]},{"name":"OmniDocBench","slug":"omnidocbench","metric":"overall edit distance","entries":[{"model":"openai/gpt-5.4-nano","lab":"openai","score":0.2419,"best_input_per_m":0.18,"best_output_per_m":1.1,"points_per_dollar":0.59},{"model":"openai/gpt-5.4-mini","lab":"openai","score":0.1263,"best_input_per_m":0.68,"best_output_per_m":4,"points_per_dollar":0.08}]},{"name":"GeneBench","slug":"genebench","metric":"accuracy","entries":[{"model":"openai/gpt-5.5-pro","lab":"openai","score":33.2,"best_input_per_m":27.2727,"best_output_per_m":163.6364,"points_per_dollar":0.54},{"model":"openai/gpt-5.4-pro","lab":"openai","score":25.6,"best_input_per_m":27,"best_output_per_m":160,"points_per_dollar":0.42}]},{"name":"SWE Bench Pro","slug":"swe-bench-pro","metric":null,"entries":[{"model":"sakana/fugu-ultra","lab":"sakana","score":73.7,"best_input_per_m":5,"best_output_per_m":30,"points_per_dollar":6.55},{"model":"sakana/fugu","lab":"sakana","score":59,"best_input_per_m":null,"best_output_per_m":null,"points_per_dollar":null}]},{"name":"Terminal Bench 2.1","slug":"terminal-bench-2-1","metric":null,"entries":[{"model":"sakana/fugu-ultra","lab":"sakana","score":82.1,"best_input_per_m":5,"best_output_per_m":30,"points_per_dollar":7.3},{"model":"sakana/fugu","lab":"sakana","score":80.2,"best_input_per_m":null,"best_output_per_m":null,"points_per_dollar":null}]},{"name":"LiveCodeBench Pro","slug":"livecodebench-pro","metric":null,"entries":[{"model":"sakana/fugu-ultra","lab":"sakana","score":90.8,"best_input_per_m":5,"best_output_per_m":30,"points_per_dollar":8.07},{"model":"sakana/fugu","lab":"sakana","score":87.8,"best_input_per_m":null,"best_output_per_m":null,"points_per_dollar":null}]},{"name":"Humanity’s Last Exam","slug":"humanity-s-last-exam","metric":null,"entries":[{"model":"sakana/fugu-ultra","lab":"sakana","score":50,"best_input_per_m":5,"best_output_per_m":30,"points_per_dollar":4.44},{"model":"sakana/fugu","lab":"sakana","score":47.2,"best_input_per_m":null,"best_output_per_m":null,"points_per_dollar":null}]},{"name":"τ3 Banking","slug":"3-banking","metric":null,"entries":[{"model":"sakana/fugu","lab":"sakana","score":21.7,"best_input_per_m":null,"best_output_per_m":null,"points_per_dollar":null},{"model":"sakana/fugu-ultra","lab":"sakana","score":20.6,"best_input_per_m":5,"best_output_per_m":30,"points_per_dollar":1.83}]},{"name":"Long Context Reasoning","slug":"long-context-reasoning","metric":null,"entries":[{"model":"sakana/fugu","lab":"sakana","score":74.7,"best_input_per_m":null,"best_output_per_m":null,"points_per_dollar":null},{"model":"sakana/fugu-ultra","lab":"sakana","score":73.3,"best_input_per_m":5,"best_output_per_m":30,"points_per_dollar":6.52}]},{"name":"MRCRv2","slug":"mrcrv2","metric":null,"entries":[{"model":"sakana/fugu-ultra","lab":"sakana","score":93.6,"best_input_per_m":5,"best_output_per_m":30,"points_per_dollar":8.32},{"model":"sakana/fugu","lab":"sakana","score":86.6,"best_input_per_m":null,"best_output_per_m":null,"points_per_dollar":null}]},{"name":"CTI-REALM","slug":"cti-realm","metric":null,"entries":[{"model":"sakana/fugu-ultra","lab":"sakana","score":69.4,"best_input_per_m":5,"best_output_per_m":30,"points_per_dollar":6.17},{"model":"sakana/fugu","lab":"sakana","score":67.5,"best_input_per_m":null,"best_output_per_m":null,"points_per_dollar":null}]},{"name":"HMMT","slug":"hmmt","metric":"accuracy","entries":[{"model":"zhipuai/glm-5.2","lab":"zhipuai","score":94.4,"best_input_per_m":1.4,"best_output_per_m":4.4,"points_per_dollar":43.91},{"model":"zhipuai/glm-5.2","lab":"zhipuai","score":92.5,"best_input_per_m":1.4,"best_output_per_m":4.4,"points_per_dollar":43.02}]},{"name":"SWE-bench Pro","slug":"swe-bench-pro","metric":"resolved","entries":[{"model":"alibaba/qwen3.8-27b","lab":"alibaba","score":61.7,"best_input_per_m":0.55,"best_output_per_m":3.3,"points_per_dollar":49.86}]},{"name":"SWE-Bench Multimodal","slug":"swe-bench-multimodal","metric":"resolve rate","entries":[{"model":"anthropic/claude-opus-5","lab":"anthropic","score":59.4,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":5.94}]},{"name":"Frontier-Bench","slug":"frontier-bench","metric":"mean reward","entries":[{"model":"anthropic/claude-opus-5","lab":"anthropic","score":43.3,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":4.33}]},{"name":"DeepSearchQA","slug":"deepsearchqa","metric":"F1","entries":[{"model":"anthropic/claude-opus-5","lab":"anthropic","score":95,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":9.5}]},{"name":"ARC-AGI-3","slug":"arc-agi-3","metric":"RHAE","entries":[{"model":"anthropic/claude-opus-5","lab":"anthropic","score":30.2,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":3.02}]},{"name":"HealthBench Professional","slug":"healthbench-professional","metric":"score","entries":[{"model":"anthropic/claude-opus-5","lab":"anthropic","score":59.8,"best_input_per_m":5,"best_output_per_m":25,"points_per_dollar":5.98}]},{"name":"CyberGym","slug":"cybergym","metric":"score","entries":[{"model":"deepseek/deepseek-v4-flash-0731","lab":"deepseek","score":76.7,"best_input_per_m":0.08,"best_output_per_m":0.18,"points_per_dollar":730.48}]},{"name":"DSBench-FullStack","slug":"dsbench-fullstack","metric":"score","entries":[{"model":"deepseek/deepseek-v4-flash-0731","lab":"deepseek","score":68.7,"best_input_per_m":0.08,"best_output_per_m":0.18,"points_per_dollar":654.29}]},{"name":"DSBench-Hard","slug":"dsbench-hard","metric":"score","entries":[{"model":"deepseek/deepseek-v4-flash-0731","lab":"deepseek","score":59.6,"best_input_per_m":0.08,"best_output_per_m":0.18,"points_per_dollar":567.62}]},{"name":"GDP.pdf","slug":"gdp-pdf","metric":"accuracy","entries":[{"model":"google/gemini-3.7-flash","lab":"google","score":34,"best_input_per_m":0.375,"best_output_per_m":1.875,"points_per_dollar":45.33}]},{"name":"LMArena Text-to-Video Arena","slug":"lmarena-text-to-video-arena","metric":"Elo","entries":[{"model":"google/gemini-omni-flash-preview","lab":"google","score":1527,"best_input_per_m":1.5,"best_output_per_m":9,"points_per_dollar":452.44}]},{"name":"IFEval","slug":"ifeval","metric":"accuracy","entries":[{"model":"meituan/longcat-2.0","lab":"meituan","score":90,"best_input_per_m":0.3,"best_output_per_m":1.2,"points_per_dollar":171.43}]},{"name":"FORTE","slug":"forte","metric":"success rate","entries":[{"model":"meituan/longcat-2.0","lab":"meituan","score":73.2,"best_input_per_m":0.3,"best_output_per_m":1.2,"points_per_dollar":139.43}]},{"name":"DeepSearch QA","slug":"deepsearch-qa","metric":null,"entries":[{"model":"meta/muse-glimmer-30b","lab":"meta","score":74.6,"best_input_per_m":0.3,"best_output_per_m":1.1,"points_per_dollar":149.2}]},{"name":"AIME 2026","slug":"aime-2026","metric":"accuracy","entries":[{"model":"meta/muse-glimmer-30b","lab":"meta","score":94.7,"best_input_per_m":0.3,"best_output_per_m":1.1,"points_per_dollar":189.4}]},{"name":"Finance Agent","slug":"finance-agent","metric":"accuracy","entries":[{"model":"meta/muse-spark-1.1","lab":"meta","score":57.2,"best_input_per_m":1.25,"best_output_per_m":4.25,"points_per_dollar":28.6}]},{"name":"BabyVision","slug":"babyvision","metric":"accuracy","entries":[{"model":"meta/muse-spark-1.1","lab":"meta","score":76.3,"best_input_per_m":1.25,"best_output_per_m":4.25,"points_per_dollar":38.15}]},{"name":"τ³-Telecom","slug":"telecom","metric":"accuracy","entries":[{"model":"mistral/mistral-medium-2604","lab":"mistral","score":91.4,"best_input_per_m":1.5,"best_output_per_m":7.5,"points_per_dollar":30.47}]},{"name":"Kimi Code Bench","slug":"kimi-code-bench","metric":null,"entries":[{"model":"moonshotai/kimi-k2.7-code","lab":"moonshotai","score":62,"best_input_per_m":0.67,"best_output_per_m":3.4,"points_per_dollar":45.84}]},{"name":"MLS Bench Lite","slug":"mls-bench-lite","metric":null,"entries":[{"model":"moonshotai/kimi-k2.7-code","lab":"moonshotai","score":35.1,"best_input_per_m":0.67,"best_output_per_m":3.4,"points_per_dollar":25.95}]},{"name":"MCP Mark Verified","slug":"mcp-mark-verified","metric":"success rate","entries":[{"model":"moonshotai/kimi-k2.7-code","lab":"moonshotai","score":81.1,"best_input_per_m":0.67,"best_output_per_m":3.4,"points_per_dollar":59.96}]},{"name":"Kimi Claw 24/7 Bench","slug":"kimi-claw-24-7-bench","metric":null,"entries":[{"model":"moonshotai/kimi-k2.7-code","lab":"moonshotai","score":46.9,"best_input_per_m":0.67,"best_output_per_m":3.4,"points_per_dollar":34.68}]},{"name":"SpreadsheetBench","slug":"spreadsheetbench","metric":"score","entries":[{"model":"moonshotai/kimi-k3","lab":"moonshotai","score":34.8,"best_input_per_m":2.5,"best_output_per_m":13.5,"points_per_dollar":6.63}]},{"name":"ZeroBench","slug":"zerobench","metric":"pass@5","entries":[{"model":"moonshotai/kimi-k3","lab":"moonshotai","score":41,"best_input_per_m":2.5,"best_output_per_m":13.5,"points_per_dollar":7.81}]},{"name":"GPQA","slug":"gpqa","metric":"accuracy","entries":[{"model":"nvidia/nemotron-3-ultra-550b-a55b","lab":"nvidia","score":87,"best_input_per_m":0.5,"best_output_per_m":2.2,"points_per_dollar":94.05}]},{"name":"FinanceAgent","slug":"financeagent","metric":"accuracy","entries":[{"model":"openai/gpt-5.4-pro","lab":"openai","score":61.5,"best_input_per_m":27,"best_output_per_m":160,"points_per_dollar":1.02}]},{"name":"AIME26","slug":"aime26","metric":null,"entries":[{"model":"sakana/sakana-namazu","lab":"sakana","score":96.67,"best_input_per_m":0.95,"best_output_per_m":4,"points_per_dollar":56.45}]},{"name":"LiveCodeBench v6","slug":"livecodebench-v6","metric":null,"entries":[{"model":"sakana/sakana-namazu","lab":"sakana","score":90.33,"best_input_per_m":0.95,"best_output_per_m":4,"points_per_dollar":52.75}]},{"name":"JFBench","slug":"jfbench","metric":null,"entries":[{"model":"sakana/sakana-namazu","lab":"sakana","score":37.4,"best_input_per_m":0.95,"best_output_per_m":4,"points_per_dollar":21.84}]},{"name":"Translation","slug":"translation","metric":null,"entries":[{"model":"sakana/sakana-namazu","lab":"sakana","score":52.2,"best_input_per_m":0.95,"best_output_per_m":4,"points_per_dollar":30.48}]},{"name":"FairPoliticsQA","slug":"fairpoliticsqa","metric":null,"entries":[{"model":"sakana/sakana-namazu","lab":"sakana","score":56.3,"best_input_per_m":0.95,"best_output_per_m":4,"points_per_dollar":32.88}]},{"name":"ClawEval","slug":"claweval","metric":"pass^3","entries":[{"model":"stepfun/step-3.7-flash","lab":"stepfun","score":67.1,"best_input_per_m":0.185,"best_output_per_m":1.11,"points_per_dollar":161.2}]},{"name":"Terminal Bench 2.0","slug":"terminal-bench-2-0","metric":"score","entries":[{"model":"zhipuai/glm-4.7","lab":"zhipuai","score":33.4,"best_input_per_m":0.6,"best_output_per_m":2.2,"points_per_dollar":33.4}]},{"name":"CritPt","slug":"critpt","metric":"accuracy","entries":[{"model":"zhipuai/glm-5.2","lab":"zhipuai","score":20.9,"best_input_per_m":1.4,"best_output_per_m":4.4,"points_per_dollar":9.72}]},{"name":"AIME","slug":"aime","metric":"accuracy","entries":[{"model":"zhipuai/glm-5.2","lab":"zhipuai","score":99.2,"best_input_per_m":1.4,"best_output_per_m":4.4,"points_per_dollar":46.14}]},{"name":"IMOAnswerBench","slug":"imoanswerbench","metric":"accuracy","entries":[{"model":"zhipuai/glm-5.2","lab":"zhipuai","score":91,"best_input_per_m":1.4,"best_output_per_m":4.4,"points_per_dollar":42.33}]},{"name":"PostTrainBench","slug":"posttrainbench","metric":"score","entries":[{"model":"zhipuai/glm-5.2","lab":"zhipuai","score":34.3,"best_input_per_m":1.4,"best_output_per_m":4.4,"points_per_dollar":15.95}]},{"name":"Tool-Decathlon","slug":"tool-decathlon","metric":"score","entries":[{"model":"zhipuai/glm-5.2","lab":"zhipuai","score":48.2,"best_input_per_m":1.4,"best_output_per_m":4.4,"points_per_dollar":22.42}]}]}