{"board":"overall","computedAt":"2026-10-09T01:18:00.892Z","method":"2026.10-irt-1","scale":{"mean":50,"sd":15,"note":"Reference-group mean is 50 and one standard deviation is 15. Not a percentage."},"weights":{"coding":0.4,"research":0.2,"professional":0.2,"knowledge":0.15,"preference":0.05},"models":[{"rank":1,"slug":"claude-opus-5-5","name":"Claude Opus 5.5","lab":"Anthropic","released":"2026-09-22","openWeights":false,"score":78.63,"scores":{"coding":84.55,"overall":78.63,"research":85.59,"knowledge":67.75,"preference":63.5,"professional":71.76},"evaluations":32,"coverage":0.909,"pricesUsdPerMillionTokens":{"input":4,"output":20,"cachedInput":0.2},"url":"https://badinfluence.news/leaderboard/models/claude-opus-5-5"},{"rank":2,"slug":"claude-fable-5-1","name":"Claude Fable 5.1","lab":"Anthropic","released":"2026-09-01","openWeights":false,"score":77.52,"scores":{"coding":78.38,"overall":77.52,"research":80.8,"knowledge":82.86,"preference":62.88,"professional":72.17},"evaluations":34,"coverage":0.97,"pricesUsdPerMillionTokens":{"input":10,"output":50,"cachedInput":0.25},"url":"https://badinfluence.news/leaderboard/models/claude-fable-5-1"},{"rank":3,"slug":"gpt-6-astra","name":"GPT-6 Astra","lab":"OpenAI","released":"2026-09-03","openWeights":false,"score":74.12,"scores":{"coding":71.2,"overall":74.12,"research":91.46,"knowledge":79.06,"preference":57.23,"professional":63.15},"evaluations":34,"coverage":0.97,"pricesUsdPerMillionTokens":{"input":10,"output":50,"cachedInput":1},"url":"https://badinfluence.news/leaderboard/models/gpt-6-astra"},{"rank":4,"slug":"claude-fable-5","name":"Claude Fable 5","lab":"Anthropic","released":"2026-06-09","openWeights":false,"score":73.56,"scores":{"coding":74.93,"overall":73.56,"research":74.89,"knowledge":71.92,"preference":62.19,"professional":73.56},"evaluations":32,"coverage":0.879,"pricesUsdPerMillionTokens":{"input":10,"output":50,"cachedInput":1},"url":"https://badinfluence.news/leaderboard/models/claude-fable-5"},{"rank":5,"slug":"claude-opus-5","name":"Claude Opus 5","lab":"Anthropic","released":"2026-07-24","openWeights":false,"score":72.86,"scores":{"coding":74.12,"overall":72.86,"research":75.57,"knowledge":69.5,"preference":59.18,"professional":73.61},"evaluations":34,"coverage":0.97,"pricesUsdPerMillionTokens":{"input":5,"output":25,"cachedInput":0.5},"url":"https://badinfluence.news/leaderboard/models/claude-opus-5"},{"rank":6,"slug":"claude-sonnet-5-5","name":"Claude Sonnet 5.5","lab":"Anthropic","released":"2026-09-28","openWeights":false,"score":71.37,"scores":{"coding":74.26,"overall":71.37,"research":79.47,"knowledge":58.71,"preference":54.96,"professional":71.1},"evaluations":30,"coverage":0.848,"pricesUsdPerMillionTokens":{"input":2,"output":10,"cachedInput":0.1},"url":"https://badinfluence.news/leaderboard/models/claude-sonnet-5-5"},{"rank":7,"slug":"gpt-6-1-sol","name":"GPT-6.1 Sol","lab":"OpenAI","released":"2026-09-29","openWeights":false,"score":70.66,"scores":{"coding":67.55,"overall":70.66,"research":86.59,"knowledge":74.8,"preference":57.41,"professional":61.16},"evaluations":31,"coverage":0.879,"pricesUsdPerMillionTokens":{"input":2,"output":10,"cachedInput":0.1},"url":"https://badinfluence.news/leaderboard/models/gpt-6-1-sol"},{"rank":8,"slug":"gpt-5-6-sol","name":"GPT-5.6 Sol","lab":"OpenAI","released":"2026-07-09","openWeights":false,"score":65.46,"scores":{"coding":67.97,"overall":65.46,"research":73.95,"knowledge":60.1,"preference":55.41,"professional":58.51},"evaluations":35,"coverage":0.97,"pricesUsdPerMillionTokens":{"input":2,"output":10,"cachedInput":0.2},"url":"https://badinfluence.news/leaderboard/models/gpt-5-6-sol"},{"rank":9,"slug":"gpt-6-sol","name":"GPT-6 Sol","lab":"OpenAI","released":"2026-09-22","openWeights":false,"score":64.67,"scores":{"coding":67.92,"overall":64.67,"research":72.86,"knowledge":63.62,"preference":49.71,"professional":54.52},"evaluations":31,"coverage":0.879,"pricesUsdPerMillionTokens":{"input":2,"output":10,"cachedInput":0.2},"url":"https://badinfluence.news/leaderboard/models/gpt-6-sol"},{"rank":10,"slug":"gemini-3-8-flash","name":"Gemini 3.8 Flash","lab":"Google","released":"2026-09-02","openWeights":false,"score":64.64,"scores":{"coding":60.67,"overall":64.64,"research":65.02,"knowledge":79.16,"preference":57.45,"professional":63.09},"evaluations":33,"coverage":0.939,"pricesUsdPerMillionTokens":{"input":0.75,"output":3.75,"cachedInput":0.075},"url":"https://badinfluence.news/leaderboard/models/gemini-3-8-flash"},{"rank":11,"slug":"muse-spark-1-3","name":"Muse Spark 1.3","lab":"Meta","released":"2026-09-02","openWeights":false,"score":64.4,"scores":{"coding":61.65,"overall":64.4,"research":57.89,"knowledge":71.96,"preference":57.26,"professional":72.51},"evaluations":31,"coverage":0.879,"pricesUsdPerMillionTokens":{"input":1.25,"output":4.25,"cachedInput":0.15},"url":"https://badinfluence.news/leaderboard/models/muse-spark-1-3"},{"rank":12,"slug":"grok-4-6","name":"Grok 4.6","lab":"xAI","released":"2026-08-12","openWeights":false,"score":62.66,"scores":{"coding":61.27,"overall":62.66,"research":60.24,"knowledge":68.3,"preference":48.82,"professional":67.07},"evaluations":34,"coverage":0.97,"pricesUsdPerMillionTokens":{"input":2,"output":6,"cachedInput":0.5},"url":"https://badinfluence.news/leaderboard/models/grok-4-6"},{"rank":13,"slug":"kimi-k3","name":"Kimi K3","lab":"Moonshot AI","released":"2026-07-16","openWeights":true,"score":61.86,"scores":{"coding":61.52,"overall":61.86,"research":56.18,"knowledge":66.05,"preference":55.34,"professional":66.73},"evaluations":33,"coverage":0.939,"pricesUsdPerMillionTokens":{"input":0.76,"output":13,"cachedInput":0.31},"url":"https://badinfluence.news/leaderboard/models/kimi-k3"},{"rank":14,"slug":"grok-4-7","name":"Grok 4.7","lab":"xAI","released":"2026-09-21","openWeights":false,"score":61.7,"scores":{"coding":64.83,"overall":61.7,"research":54.39,"knowledge":62.63,"preference":45.88,"professional":65.99},"evaluations":31,"coverage":0.879,"pricesUsdPerMillionTokens":{"input":2,"output":6,"cachedInput":0.5},"url":"https://badinfluence.news/leaderboard/models/grok-4-7"},{"rank":15,"slug":"gemini-3-7-flash","name":"Gemini 3.7 Flash","lab":"Google","released":"2026-08-13","openWeights":false,"score":61.45,"scores":{"coding":60.77,"overall":61.45,"research":61.42,"knowledge":65.3,"preference":55,"professional":61.56},"evaluations":32,"coverage":0.909,"pricesUsdPerMillionTokens":{"input":0.75,"output":3.75,"cachedInput":0.075},"url":"https://badinfluence.news/leaderboard/models/gemini-3-7-flash"},{"rank":16,"slug":"glm-5-3","name":"GLM 5.3","lab":"Z.ai","released":"2026-08-14","openWeights":true,"score":60.72,"scores":{"coding":66.78,"overall":60.72,"research":52.39,"knowledge":58.46,"preference":52.51,"professional":60.68},"evaluations":34,"coverage":0.97,"pricesUsdPerMillionTokens":{"input":0.039,"output":3.39,"cachedInput":0.038},"url":"https://badinfluence.news/leaderboard/models/glm-5-3"},{"rank":17,"slug":"claude-opus-4-8","name":"Claude Opus 4.8","lab":"Anthropic","released":"2026-05-28","openWeights":false,"score":60.1,"scores":{"coding":61.29,"overall":60.1,"research":59.54,"knowledge":59.79,"preference":53.2,"professional":60.24},"evaluations":32,"coverage":0.879,"pricesUsdPerMillionTokens":{"input":5,"output":25,"cachedInput":0.5},"url":"https://badinfluence.news/leaderboard/models/claude-opus-4-8"},{"rank":18,"slug":"deepseek-v4-1-flash","name":"DeepSeek V4.1 Flash","lab":"DeepSeek","released":"2026-09-09","openWeights":true,"score":60.1,"scores":{"coding":66.13,"overall":60.1,"research":56.1,"knowledge":60.17,"preference":51.55,"professional":54.1},"evaluations":28,"coverage":0.818,"pricesUsdPerMillionTokens":{"input":0.3,"output":1.2,"cachedInput":0.006},"url":"https://badinfluence.news/leaderboard/models/deepseek-v4-1-flash"},{"rank":19,"slug":"muse-spark-1-2","name":"Muse Spark 1.2","lab":"Meta","released":"2026-08-05","openWeights":false,"score":60.08,"scores":{"coding":58.61,"overall":60.08,"research":60.69,"knowledge":57.84,"preference":55.85,"professional":65.14},"evaluations":27,"coverage":0.788,"pricesUsdPerMillionTokens":{"input":1.25,"output":4.25,"cachedInput":0.15},"url":"https://badinfluence.news/leaderboard/models/muse-spark-1-2"},{"rank":20,"slug":"claude-haiku-5-5","name":"Claude Haiku 5.5","lab":"Anthropic","released":"2026-10-07","openWeights":false,"score":59.2,"scores":{"coding":64.96,"overall":59.2,"research":62.21,"knowledge":41.74,"preference":59.14,"professional":57.8},"evaluations":26,"coverage":0.758,"pricesUsdPerMillionTokens":{"input":0.1,"output":0.5,"cachedInput":0.01},"url":"https://badinfluence.news/leaderboard/models/claude-haiku-5-5"},{"rank":21,"slug":"gpt-5-5","name":"GPT-5.5","lab":"OpenAI","released":"2026-04-23","openWeights":false,"score":58.96,"scores":{"coding":57.9,"overall":58.96,"research":64.63,"knowledge":57.66,"preference":52.82,"professional":57.9},"evaluations":30,"coverage":0.848,"pricesUsdPerMillionTokens":{"input":5,"output":30,"cachedInput":0.5},"url":"https://badinfluence.news/leaderboard/models/gpt-5-5"},{"rank":22,"slug":"qwen3-8-flash","name":"Qwen3.8 Flash","lab":"Alibaba","released":"2026-08-26","openWeights":true,"score":58.86,"scores":{"coding":58.37,"overall":58.86,"research":54.49,"knowledge":61.85,"preference":59.3,"professional":61.85},"evaluations":10,"coverage":0.303,"pricesUsdPerMillionTokens":{"input":0.15,"output":0.47,"cachedInput":0.016},"url":"https://badinfluence.news/leaderboard/models/qwen3-8-flash"},{"rank":23,"slug":"deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","lab":"DeepSeek","released":"2026-08-13","openWeights":true,"score":57.42,"scores":{"coding":59.39,"overall":57.42,"research":58.7,"knowledge":52.71,"preference":57.02,"professional":55.82},"evaluations":32,"coverage":0.909,"pricesUsdPerMillionTokens":{"input":1.32,"output":3.96,"cachedInput":0.044},"url":"https://badinfluence.news/leaderboard/models/deepseek-v4-pro-0813"},{"rank":24,"slug":"claude-opus-4-7","name":"Claude Opus 4.7","lab":"Anthropic","released":"2026-04-16","openWeights":false,"score":57.37,"scores":{"coding":59.52,"overall":57.37,"research":54.71,"knowledge":53.81,"preference":56.09,"professional":58.73},"evaluations":28,"coverage":0.788,"pricesUsdPerMillionTokens":{"input":5,"output":25,"cachedInput":0.5},"url":"https://badinfluence.news/leaderboard/models/claude-opus-4-7"},{"rank":25,"slug":"grok-4-5","name":"Grok 4.5","lab":"xAI","released":"2026-07-08","openWeights":false,"score":57.11,"scores":{"coding":56.18,"overall":57.11,"research":54.09,"knowledge":65.45,"preference":49.32,"professional":57.67},"evaluations":30,"coverage":0.848,"pricesUsdPerMillionTokens":{"input":2,"output":6,"cachedInput":0.3},"url":"https://badinfluence.news/leaderboard/models/grok-4-5"},{"rank":26,"slug":"muse-spark-1-1","name":"Muse Spark 1.1","lab":"Meta","released":"2026-07-09","openWeights":false,"score":56.63,"scores":{"coding":55.67,"overall":56.63,"research":59.25,"knowledge":54.1,"preference":54.02,"professional":58.49},"evaluations":21,"coverage":0.636,"pricesUsdPerMillionTokens":{"input":1.25,"output":4.25,"cachedInput":0.15},"url":"https://badinfluence.news/leaderboard/models/muse-spark-1-1"},{"rank":27,"slug":"gpt-5-6-terra","name":"GPT-5.6 Terra","lab":"OpenAI","released":"2026-07-09","openWeights":false,"score":56.32,"scores":{"coding":57.08,"overall":56.32,"research":65.45,"knowledge":45.68,"preference":48.72,"professional":55.56},"evaluations":35,"coverage":0.97,"pricesUsdPerMillionTokens":{"input":2,"output":12,"cachedInput":0.2},"url":"https://badinfluence.news/leaderboard/models/gpt-5-6-terra"},{"rank":28,"slug":"claude-sonnet-5","name":"Claude Sonnet 5","lab":"Anthropic","released":"2026-06-30","openWeights":false,"score":56.05,"scores":{"coding":58.3,"overall":56.05,"research":56.93,"knowledge":51.42,"preference":47.94,"professional":56.18},"evaluations":33,"coverage":0.939,"pricesUsdPerMillionTokens":{"input":2,"output":10,"cachedInput":0.2},"url":"https://badinfluence.news/leaderboard/models/claude-sonnet-5"},{"rank":29,"slug":"qwen3-8-max","name":"Qwen3.8 Max","lab":"Alibaba","released":"2026-08-02","openWeights":false,"score":56.05,"scores":{"coding":53.85,"overall":56.05,"research":58.42,"knowledge":50.88,"preference":52.23,"professional":62.89},"evaluations":34,"coverage":0.97,"pricesUsdPerMillionTokens":{"input":null,"output":null,"cachedInput":null},"url":"https://badinfluence.news/leaderboard/models/qwen3-8-max"},{"rank":30,"slug":"deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","lab":"DeepSeek","released":"2026-07-31","openWeights":true,"score":53.86,"scores":{"coding":56.13,"overall":53.86,"research":52.74,"knowledge":47.65,"preference":53.37,"professional":55.2},"evaluations":29,"coverage":0.818,"pricesUsdPerMillionTokens":{"input":0.0079,"output":1.28,"cachedInput":0.0079},"url":"https://badinfluence.news/leaderboard/models/deepseek-v4-flash-0731"}],"notRanked":[{"slug":"gemini-4-argon","name":"Gemini 4 Argon","lab":"Google","score":76.78,"evaluations":21,"reason":"Fewer than 2 kinds of knowledge evaluation","url":"https://badinfluence.news/leaderboard/models/gemini-4-argon"},{"slug":"mimo-v2-6-pro","name":"MiMo-V2.6-Pro","lab":"Xiaomi","score":64.12,"evaluations":21,"reason":"Fewer than 2 kinds of knowledge evaluation","url":"https://badinfluence.news/leaderboard/models/mimo-v2-6-pro"},{"slug":"qwen3-8-max-0902","name":"Qwen3.8 Max (0902)","lab":"Alibaba","score":61.57,"evaluations":9,"reason":"Fewer than 3 kinds of coding evaluation","url":"https://badinfluence.news/leaderboard/models/qwen3-8-max-0902"},{"slug":"deepseek-v4-flash-vision-exp","name":"DeepSeek V4 Flash Vision Exp","lab":"DeepSeek","score":61.18,"evaluations":5,"reason":"Results from only one evaluator so far","url":"https://badinfluence.news/leaderboard/models/deepseek-v4-flash-vision-exp"},{"slug":"ember-1","name":"Ember-1","lab":"Fireworks","score":60.18,"evaluations":12,"reason":"Results from only one evaluator so far","url":"https://badinfluence.news/leaderboard/models/ember-1"},{"slug":"step-5-preview","name":"Step 5 Preview","lab":"StepFun","score":59.97,"evaluations":16,"reason":"Fewer than 2 kinds of knowledge evaluation","url":"https://badinfluence.news/leaderboard/models/step-5-preview"},{"slug":"hy4-preview","name":"Hy4 preview","lab":"Tencent","score":59.63,"evaluations":13,"reason":"Results from only one evaluator so far","url":"https://badinfluence.news/leaderboard/models/hy4-preview"},{"slug":"qwen3-8-2-4t-a95b","name":"Qwen3.8 2.4T A95B","lab":"Alibaba","score":58.66,"evaluations":5,"reason":"Results from only one evaluator so far","url":"https://badinfluence.news/leaderboard/models/qwen3-8-2-4t-a95b"},{"slug":"mimo-v2-6-flash","name":"MiMo-V2.6-Flash","lab":"Xiaomi","score":56.51,"evaluations":20,"reason":"Fewer than 2 kinds of knowledge evaluation","url":"https://badinfluence.news/leaderboard/models/mimo-v2-6-flash"},{"slug":"deepseek-v4-flash-vision","name":"Deepseek V4 Flash Vision","lab":"DeepSeek","score":52.51,"evaluations":5,"reason":"Results from only one evaluator so far","url":"https://badinfluence.news/leaderboard/models/deepseek-v4-flash-vision"},{"slug":"gpt-5-2-codex","name":"GPT-5.2-Codex","lab":"OpenAI","score":50.05,"evaluations":11,"reason":"Fewer than 3 kinds of coding evaluation","url":"https://badinfluence.news/leaderboard/models/gpt-5-2-codex"},{"slug":"deepseek-v4-pro-0424","name":"Deepseek V4 Pro 0424","lab":"DeepSeek","score":48.77,"evaluations":7,"reason":"Results from only one evaluator so far","url":"https://badinfluence.news/leaderboard/models/deepseek-v4-pro-0424"},{"slug":"gpt-5-2","name":"GPT-5.2","lab":"OpenAI","score":48.44,"evaluations":19,"reason":"Fewer than 3 kinds of coding evaluation","url":"https://badinfluence.news/leaderboard/models/gpt-5-2"},{"slug":"qwen3-6-max-preview","name":"Qwen3.6 Max Preview","lab":"Alibaba","score":47.98,"evaluations":8,"reason":"No coding evaluations yet","url":"https://badinfluence.news/leaderboard/models/qwen3-6-max-preview"},{"slug":"muse-spark","name":"Muse Spark","lab":"Meta","score":47.81,"evaluations":7,"reason":"Fewer than 3 kinds of coding evaluation","url":"https://badinfluence.news/leaderboard/models/muse-spark"},{"slug":"gpt-5-3-codex","name":"GPT-5.3-Codex","lab":"OpenAI","score":47.67,"evaluations":6,"reason":"Fewer than 3 kinds of coding evaluation","url":"https://badinfluence.news/leaderboard/models/gpt-5-3-codex"},{"slug":"mimo-v2-pro","name":"Mimo V2 Pro","lab":"Xiaomi","score":44.14,"evaluations":5,"reason":"No coding evaluations yet","url":"https://badinfluence.news/leaderboard/models/mimo-v2-pro"},{"slug":"qwen3-5-27b","name":"Qwen3.5-27B","lab":"Alibaba","score":43.6,"evaluations":5,"reason":"No coding evaluations yet","url":"https://badinfluence.news/leaderboard/models/qwen3-5-27b"},{"slug":"hy3","name":"Hy3","lab":"Tencent","score":42.32,"evaluations":6,"reason":"Fewer than 3 kinds of coding evaluation","url":"https://badinfluence.news/leaderboard/models/hy3"},{"slug":"k2-horizon-375b-a23b","name":"K2 Horizon 375b A23b","lab":"Institute of Foundation Models","score":42.12,"evaluations":5,"reason":"Results from only one evaluator so far","url":"https://badinfluence.news/leaderboard/models/k2-horizon-375b-a23b"}],"links":{"board":"https://badinfluence.news/leaderboard","rules":"https://badinfluence.news/leaderboard/rules","sources":"https://badinfluence.news/leaderboard/sources"}}