{"version":"agent-index-v1-2-preview","runId":4,"calculatedAt":"2026-11-03T02:23:57.380Z","name":"Agent Index","methodology":{"baseline_date":"2026-11-02","browser_policy":"LiveBench browser tasks require screenshot input. Its published zero for unsupported screenshot interaction is a valid zero, not missing coverage. This does not measure every possible text/DOM-based browser agent.","components":[{"anchor_max":67.9,"anchor_min":18.2,"benchmark_id":"hle-diamond-aa","comparison_group":"aa-hle-diamond-no-tools-1000","key":"reasoning","label":"HLE-Diamond","reference_results":[{"model_id":"claude-fable-5-1","result_id":500,"score":60.099999999999994},{"model_id":"claude-opus-5-5","result_id":505,"score":67.9},{"model_id":"claude-sonnet-5-5","result_id":499,"score":53.300000000000004},{"model_id":"deepseek-v4-1-flash-1017","result_id":507,"score":25.3},{"model_id":"gemini-3-8-flash","result_id":510,"score":33.1},{"model_id":"glm-5-3-flash","result_id":517,"score":18.2},{"model_id":"gpt-6-1-sol","result_id":501,"score":58.8},{"model_id":"gpt-6-astra","result_id":503,"score":63.800000000000004},{"model_id":"grok-4-7","result_id":504,"score":23.599999999999998},{"model_id":"kimi-k3","result_id":506,"score":26.900000000000002},{"model_id":"kimi-k3-1-pro","result_id":508,"score":37.3},{"model_id":"minimax-m3-1-flash","result_id":516,"score":28.1}],"weight":0.1},{"anchor_max":31.4,"anchor_min":15.4,"benchmark_id":"gdp-pdf-aa","comparison_group":"aa-gdp-pdf-all-pass-five-attempts","key":"documents","label":"GDP.pdf","reference_results":[{"model_id":"claude-fable-5-1","result_id":567,"score":26.2},{"model_id":"claude-opus-5-5","result_id":566,"score":26.2},{"model_id":"claude-sonnet-5-5","result_id":568,"score":25.8},{"model_id":"deepseek-v4-1-flash-1017","result_id":527,"score":17.2},{"model_id":"gemini-3-8-flash","result_id":569,"score":21},{"model_id":"glm-5-3-flash","result_id":523,"score":15.4},{"model_id":"gpt-6-1-sol","result_id":564,"score":31},{"model_id":"gpt-6-astra","result_id":563,"score":31},{"model_id":"grok-4-7","result_id":570,"score":20},{"model_id":"kimi-k3","result_id":526,"score":22},{"model_id":"kimi-k3-1-pro","result_id":528,"score":31.4},{"model_id":"minimax-m3-1-flash","result_id":534,"score":20.8}],"weight":0.1},{"anchor_max":1814,"anchor_min":1203,"benchmark_id":"aa-briefcase-v1-1","comparison_group":"aa-briefcase-1.1-stirrup-combined-elo","key":"deliverables","label":"AA-Briefcase","reference_results":[{"model_id":"claude-fable-5-1","result_id":573,"score":1670},{"model_id":"claude-opus-5-5","result_id":572,"score":1801},{"model_id":"claude-sonnet-5-5","result_id":571,"score":1814},{"model_id":"deepseek-v4-1-flash-1017","result_id":543,"score":1570.42},{"model_id":"gemini-3-8-flash","result_id":578,"score":1203},{"model_id":"glm-5-3-flash","result_id":539,"score":1450.23},{"model_id":"gpt-6-1-sol","result_id":577,"score":1555},{"model_id":"gpt-6-astra","result_id":576,"score":1569},{"model_id":"grok-4-7","result_id":574,"score":1638},{"model_id":"kimi-k3","result_id":542,"score":1498.42},{"model_id":"kimi-k3-1-pro","result_id":544,"score":1675.78},{"model_id":"minimax-m3-1-flash","result_id":550,"score":1474.82}],"weight":0.2},{"anchor_max":77.9,"anchor_min":16.5,"benchmark_id":"livebench-2-agentic","comparison_group":"livebench-2-2026-10-25-agentic","fallback_tracks":[{"benchmark_id":"livebench-2-agentic-2026-10-14","comparison_group":"livebench-2-2026-10-14-agentic","release":"2026-10-14"}],"key":"agentic","label":"LiveBench Agentic","reference_results":[{"model_id":"claude-fable-5-1","result_id":586,"score":77.9},{"model_id":"claude-opus-5-5","result_id":588,"score":72.8},{"model_id":"claude-sonnet-5-5","result_id":590,"score":63.4},{"model_id":"deepseek-v4-1-flash-1017","result_id":592,"score":35.7},{"model_id":"gemini-3-8-flash","result_id":599,"score":16.5},{"model_id":"glm-5-3-flash","result_id":598,"score":19},{"model_id":"gpt-6-1-sol","result_id":589,"score":68.7},{"model_id":"gpt-6-astra","result_id":587,"score":77.5},{"model_id":"grok-4-7","result_id":594,"score":46.1},{"model_id":"kimi-k3","result_id":596,"score":26.4},{"model_id":"kimi-k3-1-pro","result_id":593,"score":39.1},{"model_id":"minimax-m3-1-flash","result_id":595,"score":28.8}],"weight":0.2},{"anchor_max":97.7,"anchor_min":59.3,"benchmark_id":"livebench-2-coding","comparison_group":"livebench-2-2026-10-25-coding","fallback_tracks":[{"benchmark_id":"livebench-2-coding-2026-10-14","comparison_group":"livebench-2-2026-10-14-coding","release":"2026-10-14"}],"key":"coding","label":"LiveBench Coding","reference_results":[{"model_id":"claude-fable-5-1","result_id":614,"score":97.7},{"model_id":"claude-opus-5-5","result_id":616,"score":96.3},{"model_id":"claude-sonnet-5-5","result_id":618,"score":94.7},{"model_id":"deepseek-v4-1-flash-1017","result_id":620,"score":96},{"model_id":"gemini-3-8-flash","result_id":627,"score":82.2},{"model_id":"glm-5-3-flash","result_id":626,"score":80.6},{"model_id":"gpt-6-1-sol","result_id":617,"score":96},{"model_id":"gpt-6-astra","result_id":615,"score":93.7},{"model_id":"grok-4-7","result_id":622,"score":84.5},{"model_id":"kimi-k3","result_id":624,"score":59.3},{"model_id":"kimi-k3-1-pro","result_id":621,"score":81.8},{"model_id":"minimax-m3-1-flash","result_id":623,"score":83.9}],"weight":0.05},{"anchor_max":67.1717171717172,"anchor_min":12.6262626262626,"benchmark_id":"terminal-bench-4-0-aa","comparison_group":"aa-terminal-4.0-mini-swe-agent-three-repeats","key":"terminal","label":"Terminal-Bench 4.0","reference_results":[{"model_id":"claude-fable-5-1","result_id":687,"score":55.050505050505},{"model_id":"claude-opus-5-5","result_id":696,"score":59.5959595959596},{"model_id":"claude-sonnet-5-5","result_id":685,"score":63.636363636363605},{"model_id":"deepseek-v4-1-flash-1017","result_id":698,"score":33.8383838383838},{"model_id":"gemini-3-8-flash","result_id":701,"score":19.6969696969697},{"model_id":"glm-5-3-flash","result_id":712,"score":32.8282828282828},{"model_id":"gpt-6-1-sol","result_id":689,"score":56.0606060606061},{"model_id":"gpt-6-astra","result_id":694,"score":59.5959595959596},{"model_id":"grok-4-7","result_id":695,"score":25.7575757575758},{"model_id":"kimi-k3","result_id":697,"score":12.6262626262626},{"model_id":"kimi-k3-1-pro","result_id":699,"score":67.1717171717172},{"model_id":"minimax-m3-1-flash","result_id":708,"score":25.7575757575758}],"weight":0.15},{"anchor_max":93.3,"anchor_min":45.1,"benchmark_id":"livebench-2-browser-use","comparison_group":"livebench-2-2026-10-25-browser-use","fallback_tracks":[{"benchmark_id":"livebench-2-browser-use-2026-10-14","comparison_group":"livebench-2-2026-10-14-browser-use","release":"2026-10-14"}],"key":"browser","label":"LiveBench Browser Use","reference_results":[{"model_id":"claude-fable-5-1","result_id":628,"score":89.8},{"model_id":"claude-opus-5-5","result_id":630,"score":88.4},{"model_id":"claude-sonnet-5-5","result_id":632,"score":89.3},{"model_id":"deepseek-v4-1-flash-1017","result_id":634,"score":67.2},{"model_id":"gemini-3-8-flash","result_id":641,"score":45.1},{"model_id":"glm-5-3-flash","result_id":640,"score":59.8},{"model_id":"gpt-6-1-sol","result_id":631,"score":93.3},{"model_id":"gpt-6-astra","result_id":629,"score":91.3},{"model_id":"grok-4-7","result_id":636,"score":49.3},{"model_id":"kimi-k3","result_id":638,"score":75.2},{"model_id":"kimi-k3-1-pro","result_id":635,"score":75.9},{"model_id":"minimax-m3-1-flash","result_id":637,"score":80.6}],"weight":0.2}],"description":"Practical agent capability from seven benchmark tracks, including screenshot-based browser interaction.","fallback_policy":"LiveBench Agentic, Coding and Browser Use prefer October 25, 2026 and fall back to October 14, 2026 when unavailable. Older question sets differ; fallback scores are labeled in the breakdown. Original v1 weights and normalization anchors stay fixed. No missing result is invented or replaced by zero.","id":"agent-index-v1-2-preview","missing_policy":"All seven components required. Missing scores are null and never reweighted or replaced by zero.","name":"Agent Index v1.2","normalization":"frozen_reference_min_max","precision":"Store six decimal places; display one decimal. Rank uses the stored score; exact ties share a competition rank.","reference_model_ids":["claude-fable-5-1","claude-opus-5-5","claude-sonnet-5-5","deepseek-v4-1-flash-1017","gemini-3-8-flash","glm-5-3-flash","gpt-6-1-sol","gpt-6-astra","grok-4-7","kimi-k3","kimi-k3-1-pro","minimax-m3-1-flash"],"revision":"1.2","scale_policy":"Per component: clamp(100 * (raw - anchor_min) / (anchor_max - anchor_min), 0, 100). Anchors are frozen from the twelve complete-coverage reference models on 2026-11-02. 0 and 100 are reference endpoints, not task success rates.","selection_policy":"Use each component's preferred benchmark and comparison group first. Only when a model has no published result in that preferred track, try its listed fallback tracks in order. Within the chosen track, use latest reported date, falling back to retrieval date, then highest score. Exact source release and effort are retained.","status":"preview"},"scores":[{"modelId":"claude-opus-5-5","model":"Claude Opus 5.5","provider":"Anthropic","score":90.36441,"rank":1,"coverage":7,"status":"ranked"},{"modelId":"gpt-6-astra","model":"GPT-6 Astra","provider":"OpenAI","score":87.591075,"rank":2,"coverage":7,"status":"ranked"},{"modelId":"claude-sonnet-5-5","model":"Claude Sonnet 5.5","provider":"Anthropic","score":85.816649,"rank":3,"coverage":7,"status":"ranked"},{"modelId":"claude-fable-5-1","model":"Claude Fable 5.1","provider":"Anthropic","score":85.681384,"rank":4,"coverage":7,"status":"ranked"},{"modelId":"gpt-6-1-sol","model":"GPT-6.1 Sol","provider":"OpenAI","score":83.417457,"rank":5,"coverage":7,"status":"ranked"},{"modelId":"kimi-k3-1-pro","model":"Kimi K3.1 Pro","provider":"Moonshot AI","score":67.390006,"rank":6,"coverage":7,"status":"ranked"},{"modelId":"gpt-6-1-terra","model":"GPT-6.1 Terra","provider":"OpenAI","score":67.36715,"rank":7,"coverage":7,"status":"ranked"},{"modelId":"gemini-4-argon","model":"Gemini 4 Argon","provider":"Google","score":67.328485,"rank":8,"coverage":7,"status":"ranked"},{"modelId":"muse-wonder-1-0","model":"Muse Wonder 1.0","provider":"Meta","score":60.883373,"rank":9,"coverage":7,"status":"ranked"},{"modelId":"claude-haiku-5-5","model":"Claude Haiku 5.5","provider":"Anthropic","score":45.384925,"rank":10,"coverage":7,"status":"ranked"},{"modelId":"mimo-v2-6-pro","model":"MiMo-V2.6-Pro","provider":"Xiaomi","score":40.93017,"rank":11,"coverage":7,"status":"ranked"},{"modelId":"deepseek-v4-1-flash-1017","model":"DeepSeek V4.1 Flash 1017","provider":"DeepSeek","score":40.616588,"rank":12,"coverage":7,"status":"ranked"},{"modelId":"minimax-m3-1-flash","model":"MiniMax M3.1 Flash","provider":"MiniMax","score":39.815538,"rank":13,"coverage":7,"status":"ranked"},{"modelId":"grok-4-7","model":"Grok 4.7","provider":"xAI","score":38.477265,"rank":14,"coverage":7,"status":"ranked"},{"modelId":"gpt-5-6-terra","model":"GPT-5.6 Terra","provider":"OpenAI","score":37.767096,"rank":15,"coverage":7,"status":"ranked"},{"modelId":"muse-spark-1-3","model":"Muse Spark 1.3","provider":"Meta","score":35.141349,"rank":16,"coverage":7,"status":"ranked"},{"modelId":"kimi-k3","model":"Kimi K3","provider":"Moonshot AI","score":31.259934,"rank":17,"coverage":7,"status":"ranked"},{"modelId":"gpt-6-luna","model":"GPT-6 Luna","provider":"OpenAI","score":28.244316,"rank":18,"coverage":7,"status":"ranked"},{"modelId":"glm-5-3","model":"GLM-5.3","provider":"Z.ai","score":27.306028,"rank":19,"coverage":7,"status":"ranked"},{"modelId":"glm-5-3-flash","model":"GLM-5.3-Flash","provider":"Z.ai","score":23.335545,"rank":20,"coverage":7,"status":"ranked"},{"modelId":"step-5-preview","model":"Step 5 Preview","provider":"StepFun","score":18.548522,"rank":21,"coverage":7,"status":"ranked"},{"modelId":"gemini-3-8-flash","model":"Gemini 3.8 Flash","provider":"Google","score":12.549203,"rank":22,"coverage":7,"status":"ranked"},{"modelId":"qwen3-8-27b","model":"Qwen3.8 27B","provider":"Qwen","score":11.760547,"rank":23,"coverage":7,"status":"ranked"},{"modelId":"muse-spark-open","model":"Muse Spark Open","provider":"Meta","score":7.979483,"rank":24,"coverage":7,"status":"ranked"},{"modelId":"nemotron-3-5-super-vl","model":"Nemotron 3.5 Super VL","provider":"NVIDIA","score":1.5625,"rank":25,"coverage":7,"status":"ranked"},{"modelId":"inkling","model":"Inkling","provider":"Thinking Machines","score":0.611979,"rank":26,"coverage":7,"status":"ranked"},{"modelId":"claude-fable-5","model":"Claude Fable 5","provider":"Anthropic","score":null,"rank":null,"coverage":1,"status":"insufficient_coverage"},{"modelId":"claude-mythos-5","model":"Claude Mythos 5","provider":"Anthropic","score":null,"rank":null,"coverage":0,"status":"insufficient_coverage"},{"modelId":"claude-mythos-preview","model":"Claude Mythos Preview","provider":"Anthropic","score":null,"rank":null,"coverage":0,"status":"insufficient_coverage"},{"modelId":"claude-opus-4-5","model":"Claude Opus 4.5","provider":"Anthropic","score":null,"rank":null,"coverage":0,"status":"insufficient_coverage"},{"modelId":"claude-opus-4-6","model":"Claude Opus 4.6","provider":"Anthropic","score":null,"rank":null,"coverage":0,"status":"insufficient_coverage"},{"modelId":"claude-opus-4-7","model":"Claude Opus 4.7","provider":"Anthropic","score":null,"rank":null,"coverage":1,"status":"insufficient_coverage"},{"modelId":"claude-opus-4-8","model":"Claude Opus 4.8","provider":"Anthropic","score":null,"rank":null,"coverage":3,"status":"insufficient_coverage"},{"modelId":"claude-opus-5","model":"Claude Opus 5","provider":"Anthropic","score":null,"rank":null,"coverage":3,"status":"insufficient_coverage"},{"modelId":"claude-sonnet-4-5","model":"Claude Sonnet 4.5","provider":"Anthropic","score":null,"rank":null,"coverage":3,"status":"insufficient_coverage"},{"modelId":"claude-sonnet-4-6","model":"Claude Sonnet 4.6","provider":"Anthropic","score":null,"rank":null,"coverage":3,"status":"insufficient_coverage"},{"modelId":"claude-sonnet-5","model":"Claude Sonnet 5","provider":"Anthropic","score":null,"rank":null,"coverage":3,"status":"insufficient_coverage"},{"modelId":"deepseek-r1-0120","model":"DeepSeek R1 (Jan 2025)","provider":"DeepSeek","score":null,"rank":null,"coverage":3,"status":"insufficient_coverage"},{"modelId":"deepseek-v3-2","model":"DeepSeek V3.2","provider":"DeepSeek","score":null,"rank":null,"coverage":0,"status":"insufficient_coverage"},{"modelId":"deepseek-v4-flash","model":"DeepSeek V4 Flash","provider":"DeepSeek","score":null,"rank":null,"coverage":3,"status":"insufficient_coverage"},{"modelId":"deepseek-v4-flash-0420","model":"DeepSeek V4 Flash 0420","provider":"DeepSeek","score":null,"rank":null,"coverage":3,"status":"insufficient_coverage"},{"modelId":"deepseek-v4-pro","model":"DeepSeek V4 Pro","provider":"DeepSeek","score":null,"rank":null,"coverage":0,"status":"insufficient_coverage"},{"modelId":"deepseek-v4-pro-0424","model":"DeepSeek V4 Pro 0424","provider":"DeepSeek","score":null,"rank":null,"coverage":3,"status":"insufficient_coverage"},{"modelId":"deepseek-v4-pro-0813","model":"DeepSeek V4 Pro 0813","provider":"DeepSeek","score":null,"rank":null,"coverage":4,"status":"insufficient_coverage"},{"modelId":"deepseek-v4-1-flash","model":"DeepSeek V4.1 Flash","provider":"DeepSeek","score":null,"rank":null,"coverage":4,"status":"insufficient_coverage"},{"modelId":"deepseekcoder-appworld","model":"DeepSeekCoder","provider":"DeepSeek","score":null,"rank":null,"coverage":0,"status":"insufficient_coverage"},{"modelId":"gemini-3-flash","model":"Gemini 3 Flash","provider":"Google","score":null,"rank":null,"coverage":0,"status":"insufficient_coverage"},{"modelId":"gemini-3-pro","model":"Gemini 3 Pro","provider":"Google","score":null,"rank":null,"coverage":0,"status":"insufficient_coverage"},{"modelId":"gemini-3-1-pro","model":"Gemini 3.1 Pro","provider":"Google","score":null,"rank":null,"coverage":4,"status":"insufficient_coverage"},{"modelId":"gemini-4-carbon","model":"Gemini 4 Carbon","provider":"Google","score":null,"rank":null,"coverage":4,"status":"insufficient_coverage"},{"modelId":"glm-5","model":"GLM-5","provider":"Z.ai","score":null,"rank":null,"coverage":0,"status":"insufficient_coverage"},{"modelId":"glm-5-1","model":"GLM-5.1","provider":"Z.ai","score":null,"rank":null,"coverage":3,"status":"insufficient_coverage"},{"modelId":"glm-5-2","model":"GLM-5.2","provider":"Z.ai","score":null,"rank":null,"coverage":3,"status":"insufficient_coverage"},{"modelId":"gpt-4-turbo","model":"GPT-4 Turbo","provider":"OpenAI","score":null,"rank":null,"coverage":0,"status":"insufficient_coverage"},{"modelId":"gpt-4-1","model":"GPT-4.1","provider":"OpenAI","score":null,"rank":null,"coverage":0,"status":"insufficient_coverage"},{"modelId":"gpt-4-1-mini","model":"GPT-4.1 mini","provider":"OpenAI","score":null,"rank":null,"coverage":0,"status":"insufficient_coverage"},{"modelId":"gpt-4o","model":"GPT-4o","provider":"OpenAI","score":null,"rank":null,"coverage":0,"status":"insufficient_coverage"},{"modelId":"gpt-5-2","model":"GPT-5.2","provider":"OpenAI","score":null,"rank":null,"coverage":0,"status":"insufficient_coverage"},{"modelId":"gpt-5-4","model":"GPT-5.4","provider":"OpenAI","score":null,"rank":null,"coverage":0,"status":"insufficient_coverage"},{"modelId":"gpt-5-4-mini","model":"GPT-5.4 mini","provider":"OpenAI","score":null,"rank":null,"coverage":3,"status":"insufficient_coverage"},{"modelId":"gpt-5-4-pro","model":"GPT-5.4 Pro","provider":"OpenAI","score":null,"rank":null,"coverage":0,"status":"insufficient_coverage"},{"modelId":"gpt-5-5","model":"GPT-5.5","provider":"OpenAI","score":null,"rank":null,"coverage":3,"status":"insufficient_coverage"},{"modelId":"gpt-5-5-pro","model":"GPT-5.5 Pro","provider":"OpenAI","score":null,"rank":null,"coverage":0,"status":"insufficient_coverage"},{"modelId":"gpt-5-6","model":"GPT-5.6","provider":"OpenAI","score":null,"rank":null,"coverage":0,"status":"insufficient_coverage"},{"modelId":"gpt-5-6-luna","model":"GPT-5.6 Luna","provider":"OpenAI","score":null,"rank":null,"coverage":3,"status":"insufficient_coverage"},{"modelId":"gpt-5-6-sol","model":"GPT-5.6 Sol","provider":"OpenAI","score":null,"rank":null,"coverage":3,"status":"insufficient_coverage"},{"modelId":"gpt-oss-120b","model":"gpt-oss-120b","provider":"OpenAI","score":null,"rank":null,"coverage":4,"status":"insufficient_coverage"},{"modelId":"gpt-oss-20b","model":"gpt-oss-20b","provider":"OpenAI","score":null,"rank":null,"coverage":4,"status":"insufficient_coverage"},{"modelId":"grok-4-heavy","model":"Grok 4 Heavy","provider":"xAI","score":null,"rank":null,"coverage":0,"status":"insufficient_coverage"},{"modelId":"kimi-k2-thinking","model":"Kimi K2 Thinking","provider":"Moonshot AI","score":null,"rank":null,"coverage":0,"status":"insufficient_coverage"},{"modelId":"kimi-k2-5","model":"Kimi K2.5","provider":"Moonshot AI","score":null,"rank":null,"coverage":0,"status":"insufficient_coverage"},{"modelId":"kimi-k2-6","model":"Kimi K2.6","provider":"Moonshot AI","score":null,"rank":null,"coverage":3,"status":"insufficient_coverage"},{"modelId":"llama3-70b-appworld","model":"LLaMA3-70B","provider":"Meta","score":null,"rank":null,"coverage":0,"status":"insufficient_coverage"},{"modelId":"minimax-m2-7","model":"MiniMax M2.7","provider":"MiniMax","score":null,"rank":null,"coverage":3,"status":"insufficient_coverage"},{"modelId":"minimax-m3","model":"MiniMax M3","provider":"MiniMax","score":null,"rank":null,"coverage":4,"status":"insufficient_coverage"},{"modelId":"muse-spark","model":"Muse Spark","provider":"Meta","score":null,"rank":null,"coverage":1,"status":"insufficient_coverage"},{"modelId":"muse-spark-1-1","model":"Muse Spark 1.1","provider":"Meta","score":null,"rank":null,"coverage":3,"status":"insufficient_coverage"},{"modelId":"muse-spark-1-2","model":"Muse Spark 1.2","provider":"Meta","score":null,"rank":null,"coverage":3,"status":"insufficient_coverage"},{"modelId":"qwen3-5-35b-a3b","model":"Qwen 3.5 35B-A3B","provider":"Qwen","score":null,"rank":null,"coverage":0,"status":"insufficient_coverage"},{"modelId":"qwen3-5-9b","model":"Qwen 3.5 9B","provider":"Qwen","score":null,"rank":null,"coverage":4,"status":"insufficient_coverage"},{"modelId":"qwen2-5-32b","model":"Qwen2.5-32B","provider":"Qwen","score":null,"rank":null,"coverage":0,"status":"insufficient_coverage"},{"modelId":"qwen3-14b","model":"Qwen3-14B","provider":"Qwen","score":null,"rank":null,"coverage":3,"status":"insufficient_coverage"},{"modelId":"qwen3-5-397b-a17b","model":"Qwen3.5-397B-A17B","provider":"Qwen","score":null,"rank":null,"coverage":4,"status":"insufficient_coverage"},{"modelId":"qwen3-6-plus","model":"Qwen3.6 Plus","provider":"Qwen","score":null,"rank":null,"coverage":0,"status":"insufficient_coverage"},{"modelId":"seed2-0-pro","model":"Seed2.0 Pro","provider":"ByteDance","score":null,"rank":null,"coverage":0,"status":"insufficient_coverage"},{"modelId":"step-3-7-flash","model":"Step 3.7 Flash","provider":"StepFun","score":null,"rank":null,"coverage":0,"status":"insufficient_coverage"}],"components":[{"modelId":"claude-fable-5","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-fable-5","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-fable-5","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-fable-5","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-fable-5","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-fable-5","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":684,"rawScore":42.4242424242424,"normalizedScore":54.62962962962958,"contribution":8.194444444444436,"source":"https://artificialanalysis.ai/models/claude-fable-5","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"Claude Fable 5 (Max, Opus 4.8 Fallback)\"}"},{"modelId":"claude-fable-5","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-fable-5-1","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":"1,000 questions / no tools","fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":500,"rawScore":60.099999999999994,"normalizedScore":84.30583501006033,"contribution":8.430583501006033,"source":"https://artificialanalysis.ai/models/claude-fable-5-1","settings":"{\"comparison_group\": \"aa-hle-diamond-no-tools-1000\", \"selection\": \"best reported configuration per release\", \"settings\": \"Claude Fable 5.1 (Max, Default Fallback)\", \"tools\": false}"},{"modelId":"claude-fable-5-1","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":567,"rawScore":26.2,"normalizedScore":67.50000000000001,"contribution":6.750000000000002,"source":"https://artificialanalysis.ai/evaluations/gdp-pdf","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"publisher default displayed configuration\", \"settings\": \"Claude Fable 5.1 (max with fallback)\"}"},{"modelId":"claude-fable-5-1","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":573,"rawScore":1670,"normalizedScore":76.43207855973813,"contribution":15.286415711947626,"source":"https://artificialanalysis.ai/evaluations/aa-briefcase","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"publisher default displayed configuration\", \"settings\": \"Claude Fable 5.1 (max with fallback)\"}"},{"modelId":"claude-fable-5-1","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":586,"rawScore":77.9,"normalizedScore":100,"contribution":20,"source":"https://livebench.ai/#/release/2026-10-25","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-agentic\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"agentic\"}"},{"modelId":"claude-fable-5-1","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":614,"rawScore":97.7,"normalizedScore":100,"contribution":5,"source":"https://livebench.ai/#/release/2026-10-25","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-coding\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"coding\"}"},{"modelId":"claude-fable-5-1","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":687,"rawScore":55.050505050505,"normalizedScore":77.77777777777766,"contribution":11.666666666666648,"source":"https://artificialanalysis.ai/models/claude-fable-5-1-xhigh","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"Claude Fable 5.1 (Xhigh, Default Fallback)\"}"},{"modelId":"claude-fable-5-1","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":628,"rawScore":89.8,"normalizedScore":92.73858921161826,"contribution":18.547717842323653,"source":"https://livebench.ai/#/release/2026-10-25","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-browser-use\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"browser-use\"}"},{"modelId":"claude-haiku-5-5","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":"1,000 questions / no tools","fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":790,"rawScore":29.6,"normalizedScore":22.937625754527165,"contribution":2.2937625754527167,"source":"https://artificialanalysis.ai/evaluations/hle-diamond","settings":"{\"comparison_group\": \"aa-hle-diamond-no-tools-1000\", \"selection\": \"best reported configuration per release\", \"settings\": \"Claude Haiku 5.5 (max)\", \"tools\": false}"},{"modelId":"claude-haiku-5-5","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":735,"rawScore":20.8,"normalizedScore":33.75000000000001,"contribution":3.375000000000001,"source":"https://artificialanalysis.ai/evaluations/gdp-pdf","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"Claude Haiku 5.5 (max)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"claude-haiku-5-5","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":758,"rawScore":1576,"normalizedScore":61.04746317512275,"contribution":12.209492635024551,"source":"https://artificialanalysis.ai/evaluations/aa-briefcase","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"Claude Haiku 5.5 (max)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"claude-haiku-5-5","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":829,"rawScore":40,"normalizedScore":38.27361563517915,"contribution":7.65472312703583,"source":"https://livebench.ai/data/20261025/table.csv","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-agentic\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"agentic\"}"},{"modelId":"claude-haiku-5-5","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":831,"rawScore":91.4,"normalizedScore":83.59375000000001,"contribution":4.179687500000001,"source":"https://livebench.ai/data/20261025/table.csv","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-coding\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"coding\"}"},{"modelId":"claude-haiku-5-5","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":806,"rawScore":32.8,"normalizedScore":36.98518518518518,"contribution":5.547777777777777,"source":"https://artificialanalysis.ai/evaluations/terminalbench-4-0","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"Claude Haiku 5.5 (max)\"}"},{"modelId":"claude-haiku-5-5","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":832,"rawScore":69.5,"normalizedScore":50.622406639004154,"contribution":10.124481327800831,"source":"https://livebench.ai/data/20261025/table.csv","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-browser-use\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"browser-use\"}"},{"modelId":"claude-mythos-5","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-mythos-5","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-mythos-5","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-mythos-5","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-mythos-5","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-mythos-5","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":null,"fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-mythos-5","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-mythos-preview","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-mythos-preview","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-mythos-preview","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-mythos-preview","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-mythos-preview","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-mythos-preview","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":null,"fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-mythos-preview","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-opus-4-5","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-opus-4-5","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-opus-4-5","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-opus-4-5","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-opus-4-5","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-opus-4-5","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":null,"fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-opus-4-5","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-opus-4-6","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-opus-4-6","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-opus-4-6","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-opus-4-6","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-opus-4-6","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-opus-4-6","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":null,"fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-opus-4-6","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-opus-4-7","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-opus-4-7","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-opus-4-7","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":772,"rawScore":1252,"normalizedScore":8.01963993453355,"contribution":1.6039279869067102,"source":"https://artificialanalysis.ai/evaluations/aa-briefcase","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"Claude Opus 4.7 (max)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"claude-opus-4-7","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-opus-4-7","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-opus-4-7","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":null,"fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-opus-4-7","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-opus-4-8","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-opus-4-8","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":730,"rawScore":22.8,"normalizedScore":46.25000000000001,"contribution":4.625000000000001,"source":"https://artificialanalysis.ai/evaluations/gdp-pdf","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"Claude Opus 4.8 (max)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"claude-opus-4-8","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":770,"rawScore":1320,"normalizedScore":19.148936170212767,"contribution":3.829787234042554,"source":"https://artificialanalysis.ai/evaluations/aa-briefcase","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"Claude Opus 4.8 (max)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"claude-opus-4-8","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-opus-4-8","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-opus-4-8","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":703,"rawScore":21.7171717171717,"normalizedScore":16.666666666666664,"contribution":2.4999999999999996,"source":"https://artificialanalysis.ai/models/claude-opus-4-8","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"Claude Opus 4.8 (Max)\"}"},{"modelId":"claude-opus-4-8","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-opus-5","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-opus-5","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":734,"rawScore":21.6,"normalizedScore":38.750000000000014,"contribution":3.8750000000000018,"source":"https://artificialanalysis.ai/evaluations/gdp-pdf","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"Claude Opus 5 (max)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"claude-opus-5","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":756,"rawScore":1656,"normalizedScore":74.14075286415712,"contribution":14.828150572831426,"source":"https://artificialanalysis.ai/evaluations/aa-briefcase","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"Claude Opus 5 (max)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"claude-opus-5","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-opus-5","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-opus-5","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":691,"rawScore":48.989898989899,"normalizedScore":66.66666666666666,"contribution":9.999999999999998,"source":"https://artificialanalysis.ai/models/claude-opus-5","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"Claude Opus 5 (Max)\"}"},{"modelId":"claude-opus-5","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-opus-5-5","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":"1,000 questions / no tools","fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":505,"rawScore":67.9,"normalizedScore":100,"contribution":10,"source":"https://artificialanalysis.ai/models/claude-opus-5-5","settings":"{\"comparison_group\": \"aa-hle-diamond-no-tools-1000\", \"selection\": \"best reported configuration per release\", \"settings\": \"Claude Opus 5.5 (Max, Default Fallback)\", \"tools\": false}"},{"modelId":"claude-opus-5-5","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":566,"rawScore":26.2,"normalizedScore":67.50000000000001,"contribution":6.750000000000002,"source":"https://artificialanalysis.ai/evaluations/gdp-pdf","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"publisher default displayed configuration\", \"settings\": \"Claude Opus 5.5 (max with fallback)\"}"},{"modelId":"claude-opus-5-5","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":572,"rawScore":1801,"normalizedScore":97.87234042553192,"contribution":19.574468085106385,"source":"https://artificialanalysis.ai/evaluations/aa-briefcase","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"publisher default displayed configuration\", \"settings\": \"Claude Opus 5.5 (max with fallback)\"}"},{"modelId":"claude-opus-5-5","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":588,"rawScore":72.8,"normalizedScore":91.69381107491856,"contribution":18.338762214983714,"source":"https://livebench.ai/#/release/2026-10-25","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-agentic\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"agentic\"}"},{"modelId":"claude-opus-5-5","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":616,"rawScore":96.3,"normalizedScore":96.35416666666666,"contribution":4.817708333333333,"source":"https://livebench.ai/#/release/2026-10-25","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-coding\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"coding\"}"},{"modelId":"claude-opus-5-5","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":696,"rawScore":59.5959595959596,"normalizedScore":86.11111111111107,"contribution":12.91666666666666,"source":"https://artificialanalysis.ai/models/claude-opus-5-5","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"Claude Opus 5.5 (Max, Default Fallback)\"}"},{"modelId":"claude-opus-5-5","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":630,"rawScore":88.4,"normalizedScore":89.83402489626557,"contribution":17.966804979253116,"source":"https://livebench.ai/#/release/2026-10-25","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-browser-use\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"browser-use\"}"},{"modelId":"claude-sonnet-4-5","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-sonnet-4-5","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":753,"rawScore":5.2,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/gdp-pdf","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"Claude 4.5 Sonnet\", \"tools\": \"benchmark-defined\"}"},{"modelId":"claude-sonnet-4-5","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":782,"rawScore":714,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/aa-briefcase","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"Claude 4.5 Sonnet\", \"tools\": \"benchmark-defined\"}"},{"modelId":"claude-sonnet-4-5","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-sonnet-4-5","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-sonnet-4-5","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":817,"rawScore":0,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/terminalbench-4-0","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"Claude 4.5 Sonnet\"}"},{"modelId":"claude-sonnet-4-5","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-sonnet-4-6","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-sonnet-4-6","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":741,"rawScore":15.8,"normalizedScore":2.5000000000000027,"contribution":0.2500000000000003,"source":"https://artificialanalysis.ai/evaluations/gdp-pdf","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"Claude Sonnet 4.6 (max)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"claude-sonnet-4-6","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":774,"rawScore":1062,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/aa-briefcase","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"Claude Sonnet 4.6 (max)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"claude-sonnet-4-6","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-sonnet-4-6","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-sonnet-4-6","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":811,"rawScore":3,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/terminalbench-4-0","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"Claude Sonnet 4.6 (max)\"}"},{"modelId":"claude-sonnet-4-6","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-sonnet-5","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-sonnet-5","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":745,"rawScore":13.2,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/gdp-pdf","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"Claude Sonnet 5 (max)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"claude-sonnet-5","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":765,"rawScore":1357,"normalizedScore":25.204582651391163,"contribution":5.040916530278233,"source":"https://artificialanalysis.ai/evaluations/aa-briefcase","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"Claude Sonnet 5 (max)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"claude-sonnet-5","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-sonnet-5","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-sonnet-5","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":692,"rawScore":14.1414141414141,"normalizedScore":2.7777777777777466,"contribution":0.41666666666666197,"source":"https://artificialanalysis.ai/models/claude-sonnet-5","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"Claude Sonnet 5 (Max)\"}"},{"modelId":"claude-sonnet-5","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"claude-sonnet-5-5","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":"1,000 questions / no tools","fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":499,"rawScore":53.300000000000004,"normalizedScore":70.62374245472839,"contribution":7.062374245472839,"source":"https://artificialanalysis.ai/models/claude-sonnet-5-5","settings":"{\"comparison_group\": \"aa-hle-diamond-no-tools-1000\", \"selection\": \"best reported configuration per release\", \"settings\": \"Claude Sonnet 5.5 (Max, Default Fallback)\", \"tools\": false}"},{"modelId":"claude-sonnet-5-5","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":568,"rawScore":25.8,"normalizedScore":65.00000000000001,"contribution":6.500000000000002,"source":"https://artificialanalysis.ai/evaluations/gdp-pdf","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"publisher default displayed configuration\", \"settings\": \"Claude Sonnet 5.5 (max with fallback)\"}"},{"modelId":"claude-sonnet-5-5","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":571,"rawScore":1814,"normalizedScore":100,"contribution":20,"source":"https://artificialanalysis.ai/evaluations/aa-briefcase","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"publisher default displayed configuration\", \"settings\": \"Claude Sonnet 5.5 (max with fallback)\"}"},{"modelId":"claude-sonnet-5-5","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":590,"rawScore":63.4,"normalizedScore":76.3843648208469,"contribution":15.27687296416938,"source":"https://livebench.ai/#/release/2026-10-25","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-agentic\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"agentic\"}"},{"modelId":"claude-sonnet-5-5","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":618,"rawScore":94.7,"normalizedScore":92.1875,"contribution":4.609375,"source":"https://livebench.ai/#/release/2026-10-25","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-coding\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"coding\"}"},{"modelId":"claude-sonnet-5-5","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":685,"rawScore":63.636363636363605,"normalizedScore":93.51851851851842,"contribution":14.027777777777763,"source":"https://artificialanalysis.ai/models/claude-sonnet-5-5","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"Claude Sonnet 5.5 (Max, Default Fallback)\"}"},{"modelId":"claude-sonnet-5-5","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":632,"rawScore":89.3,"normalizedScore":91.70124481327801,"contribution":18.340248962655604,"source":"https://livebench.ai/#/release/2026-10-25","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-browser-use\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"browser-use\"}"},{"modelId":"deepseek-r1-0120","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"deepseek-r1-0120","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":522,"rawScore":2.4,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/models/deepseek-r1-0120","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"DeepSeek R1 (Jan '25)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"deepseek-r1-0120","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":538,"rawScore":128.91,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/models/deepseek-r1-0120","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"DeepSeek R1 (Jan '25)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"deepseek-r1-0120","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"deepseek-r1-0120","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"deepseek-r1-0120","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":711,"rawScore":0,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/models/deepseek-r1-0120","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"DeepSeek R1 (Jan '25)\"}"},{"modelId":"deepseek-r1-0120","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"deepseek-v3-2","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"deepseek-v3-2","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"deepseek-v3-2","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"deepseek-v3-2","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"deepseek-v3-2","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"deepseek-v3-2","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":null,"fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"deepseek-v3-2","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"deepseek-v4-1-flash","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":"1,000 questions / no tools","fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":509,"rawScore":19.1,"normalizedScore":1.8108651911468854,"contribution":0.18108651911468854,"source":"https://artificialanalysis.ai/models/deepseek-v4-1-flash","settings":"{\"comparison_group\": \"aa-hle-diamond-no-tools-1000\", \"selection\": \"best reported configuration per release\", \"settings\": \"DeepSeek V4.1 Flash (Max)\", \"tools\": false}"},{"modelId":"deepseek-v4-1-flash","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":529,"rawScore":12.8,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/models/deepseek-v4-1-flash","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"DeepSeek V4.1 Flash (Max)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"deepseek-v4-1-flash","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":545,"rawScore":1416.94,"normalizedScore":35.014729950900175,"contribution":7.002945990180035,"source":"https://artificialanalysis.ai/models/deepseek-v4-1-flash","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"DeepSeek V4.1 Flash (Max)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"deepseek-v4-1-flash","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"deepseek-v4-1-flash","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"deepseek-v4-1-flash","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":700,"rawScore":26.7676767676768,"normalizedScore":25.925925925926006,"contribution":3.888888888888901,"source":"https://artificialanalysis.ai/models/deepseek-v4-1-flash","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"DeepSeek V4.1 Flash (Max)\"}"},{"modelId":"deepseek-v4-1-flash","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"deepseek-v4-1-flash-1017","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":"1,000 questions / no tools","fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":507,"rawScore":25.3,"normalizedScore":14.285714285714286,"contribution":1.4285714285714288,"source":"https://artificialanalysis.ai/models/deepseek-v4-1-flash-1017","settings":"{\"comparison_group\": \"aa-hle-diamond-no-tools-1000\", \"selection\": \"best reported configuration per release\", \"settings\": \"DeepSeek V4.1 Flash 1017 (Max)\", \"tools\": false}"},{"modelId":"deepseek-v4-1-flash-1017","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":527,"rawScore":17.2,"normalizedScore":11.249999999999995,"contribution":1.1249999999999996,"source":"https://artificialanalysis.ai/models/deepseek-v4-1-flash-1017","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"DeepSeek V4.1 Flash 1017 (Max)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"deepseek-v4-1-flash-1017","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":543,"rawScore":1570.42,"normalizedScore":60.13420621931262,"contribution":12.026841243862524,"source":"https://artificialanalysis.ai/models/deepseek-v4-1-flash-1017","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"DeepSeek V4.1 Flash 1017 (Max)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"deepseek-v4-1-flash-1017","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":592,"rawScore":35.7,"normalizedScore":31.270358306188925,"contribution":6.254071661237785,"source":"https://livebench.ai/#/release/2026-10-25","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-agentic\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"agentic\"}"},{"modelId":"deepseek-v4-1-flash-1017","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":620,"rawScore":96,"normalizedScore":95.57291666666667,"contribution":4.778645833333334,"source":"https://livebench.ai/#/release/2026-10-25","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-coding\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"coding\"}"},{"modelId":"deepseek-v4-1-flash-1017","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":698,"rawScore":33.8383838383838,"normalizedScore":38.88888888888882,"contribution":5.833333333333323,"source":"https://artificialanalysis.ai/models/deepseek-v4-1-flash-1017","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"DeepSeek V4.1 Flash 1017 (Max)\"}"},{"modelId":"deepseek-v4-1-flash-1017","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":634,"rawScore":67.2,"normalizedScore":45.850622406639005,"contribution":9.170124481327802,"source":"https://livebench.ai/#/release/2026-10-25","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-browser-use\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"browser-use\"}"},{"modelId":"deepseek-v4-flash","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"deepseek-v4-flash","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":748,"rawScore":10.8,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/gdp-pdf","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"DeepSeek V4 Flash (max)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"deepseek-v4-flash","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":775,"rawScore":1041,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/aa-briefcase","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"DeepSeek V4 Flash (high)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"deepseek-v4-flash","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"deepseek-v4-flash","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"deepseek-v4-flash","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":812,"rawScore":3,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/terminalbench-4-0","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"DeepSeek V4 Flash (high)\"}"},{"modelId":"deepseek-v4-flash","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"deepseek-v4-flash-0420","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"deepseek-v4-flash-0420","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":531,"rawScore":10.8,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/models/deepseek-v4-flash-0420","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"DeepSeek V4 Flash 0420 (Max)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"deepseek-v4-flash-0420","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":547,"rawScore":1041.27,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/models/deepseek-v4-flash-0420-high","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"DeepSeek V4 Flash 0420 (High)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"deepseek-v4-flash-0420","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"deepseek-v4-flash-0420","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"deepseek-v4-flash-0420","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":715,"rawScore":3.03030303030303,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/models/deepseek-v4-flash-0420-high","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"DeepSeek V4 Flash 0420 (High)\"}"},{"modelId":"deepseek-v4-flash-0420","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"deepseek-v4-pro","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"deepseek-v4-pro","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"deepseek-v4-pro","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"deepseek-v4-pro","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"deepseek-v4-pro","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"deepseek-v4-pro","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":null,"fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"deepseek-v4-pro","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"deepseek-v4-pro-0424","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"deepseek-v4-pro-0424","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":532,"rawScore":13.4,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/models/deepseek-v4-pro-0424","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"DeepSeek V4 Pro 0424 (Max)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"deepseek-v4-pro-0424","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":548,"rawScore":921.93,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/models/deepseek-v4-pro-0424","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"DeepSeek V4 Pro 0424 (Max)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"deepseek-v4-pro-0424","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"deepseek-v4-pro-0424","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"deepseek-v4-pro-0424","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":716,"rawScore":14.6464646464646,"normalizedScore":3.7037037037036615,"contribution":0.5555555555555493,"source":"https://artificialanalysis.ai/models/deepseek-v4-pro-0424","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"DeepSeek V4 Pro 0424 (Max)\"}"},{"modelId":"deepseek-v4-pro-0424","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"deepseek-v4-pro-0813","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":"1,000 questions / no tools","fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":511,"rawScore":19.5,"normalizedScore":2.615694164989941,"contribution":0.26156941649899407,"source":"https://artificialanalysis.ai/models/deepseek-v4-pro","settings":"{\"comparison_group\": \"aa-hle-diamond-no-tools-1000\", \"selection\": \"best reported configuration per release\", \"settings\": \"DeepSeek V4 Pro 0813 (Max)\", \"tools\": false}"},{"modelId":"deepseek-v4-pro-0813","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":530,"rawScore":11.4,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/models/deepseek-v4-pro","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"DeepSeek V4 Pro 0813 (Max)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"deepseek-v4-pro-0813","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":546,"rawScore":1254.44,"normalizedScore":8.41898527004911,"contribution":1.683797054009822,"source":"https://artificialanalysis.ai/models/deepseek-v4-pro","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"DeepSeek V4 Pro 0813 (Max)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"deepseek-v4-pro-0813","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"deepseek-v4-pro-0813","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"deepseek-v4-pro-0813","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":702,"rawScore":14.1414141414141,"normalizedScore":2.7777777777777466,"contribution":0.41666666666666197,"source":"https://artificialanalysis.ai/models/deepseek-v4-pro","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"DeepSeek V4 Pro 0813 (Max)\"}"},{"modelId":"deepseek-v4-pro-0813","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"deepseekcoder-appworld","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"deepseekcoder-appworld","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"deepseekcoder-appworld","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"deepseekcoder-appworld","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"deepseekcoder-appworld","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"deepseekcoder-appworld","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":null,"fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"deepseekcoder-appworld","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gemini-3-1-pro","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":"1,000 questions / no tools","fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":513,"rawScore":31.4,"normalizedScore":26.559356136820924,"contribution":2.6559356136820926,"source":"https://artificialanalysis.ai/models/gemini-3-1-pro-preview","settings":"{\"comparison_group\": \"aa-hle-diamond-no-tools-1000\", \"selection\": \"best reported configuration per release\", \"settings\": \"Gemini 3.1 Pro Preview\", \"tools\": false}"},{"modelId":"gemini-3-1-pro","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":738,"rawScore":17.8,"normalizedScore":15.000000000000004,"contribution":1.5000000000000004,"source":"https://artificialanalysis.ai/evaluations/gdp-pdf","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"Gemini 3.1 Pro Preview\", \"tools\": \"benchmark-defined\"}"},{"modelId":"gemini-3-1-pro","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":785,"rawScore":457,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/aa-briefcase","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"Gemini 3.1 Pro Preview\", \"tools\": \"benchmark-defined\"}"},{"modelId":"gemini-3-1-pro","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gemini-3-1-pro","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gemini-3-1-pro","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":705,"rawScore":4.04040404040404,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/models/gemini-3-1-pro-preview","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"Gemini 3.1 Pro Preview\"}"},{"modelId":"gemini-3-1-pro","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gemini-3-8-flash","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":"1,000 questions / no tools","fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":510,"rawScore":33.1,"normalizedScore":29.979879275653925,"contribution":2.9979879275653927,"source":"https://artificialanalysis.ai/models/gemini-3-8-flash","settings":"{\"comparison_group\": \"aa-hle-diamond-no-tools-1000\", \"selection\": \"best reported configuration per release\", \"settings\": \"Gemini 3.8 Flash (High)\", \"tools\": false}"},{"modelId":"gemini-3-8-flash","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":729,"rawScore":22.8,"normalizedScore":46.25000000000001,"contribution":4.625000000000001,"source":"https://artificialanalysis.ai/evaluations/gdp-pdf","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"Gemini 3.8 Flash (medium)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"gemini-3-8-flash","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":578,"rawScore":1203,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/aa-briefcase","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"publisher default displayed configuration\", \"settings\": \"Gemini 3.8 Flash (high)\"}"},{"modelId":"gemini-3-8-flash","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":599,"rawScore":16.5,"normalizedScore":0,"contribution":0,"source":"https://livebench.ai/#/release/2026-10-25","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-agentic\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"agentic\"}"},{"modelId":"gemini-3-8-flash","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":627,"rawScore":82.2,"normalizedScore":59.63541666666667,"contribution":2.981770833333334,"source":"https://livebench.ai/#/release/2026-10-25","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-coding\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"coding\"}"},{"modelId":"gemini-3-8-flash","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":701,"rawScore":19.6969696969697,"normalizedScore":12.962962962963001,"contribution":1.94444444444445,"source":"https://artificialanalysis.ai/models/gemini-3-8-flash-medium","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"Gemini 3.8 Flash (Medium)\"}"},{"modelId":"gemini-3-8-flash","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":641,"rawScore":45.1,"normalizedScore":0,"contribution":0,"source":"https://livebench.ai/#/release/2026-10-25","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-browser-use\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"browser-use\"}"},{"modelId":"gemini-3-flash","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gemini-3-flash","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gemini-3-flash","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gemini-3-flash","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gemini-3-flash","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gemini-3-flash","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":null,"fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gemini-3-flash","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gemini-3-pro","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gemini-3-pro","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gemini-3-pro","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gemini-3-pro","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gemini-3-pro","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gemini-3-pro","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":null,"fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gemini-3-pro","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gemini-4-argon","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":"1,000 questions / no tools","fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":515,"rawScore":56.699999999999996,"normalizedScore":77.46478873239437,"contribution":7.746478873239437,"source":"https://artificialanalysis.ai/models/gemini-4-argon","settings":"{\"comparison_group\": \"aa-hle-diamond-no-tools-1000\", \"selection\": \"best reported configuration per release\", \"settings\": \"Gemini 4 Argon (High)\", \"tools\": false}"},{"modelId":"gemini-4-argon","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":733,"rawScore":21.8,"normalizedScore":40.00000000000001,"contribution":4.000000000000001,"source":"https://artificialanalysis.ai/evaluations/gdp-pdf","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"Gemini 4 Argon (high)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"gemini-4-argon","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":760,"rawScore":1484,"normalizedScore":45.99018003273322,"contribution":9.198036006546644,"source":"https://artificialanalysis.ai/evaluations/aa-briefcase","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"Gemini 4 Argon (high)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"gemini-4-argon","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":591,"rawScore":61.2,"normalizedScore":72.80130293159608,"contribution":14.560260586319217,"source":"https://livebench.ai/#/release/2026-10-25","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-agentic\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"agentic\"}"},{"modelId":"gemini-4-argon","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":619,"rawScore":89.7,"normalizedScore":79.16666666666667,"contribution":3.958333333333334,"source":"https://livebench.ai/#/release/2026-10-25","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-coding\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"coding\"}"},{"modelId":"gemini-4-argon","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":707,"rawScore":57.07070707070711,"normalizedScore":81.48148148148151,"contribution":12.222222222222227,"source":"https://artificialanalysis.ai/models/gemini-4-argon","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"Gemini 4 Argon (High)\"}"},{"modelId":"gemini-4-argon","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":633,"rawScore":82.8,"normalizedScore":78.21576763485477,"contribution":15.643153526970956,"source":"https://livebench.ai/#/release/2026-10-25","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-browser-use\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"browser-use\"}"},{"modelId":"gemini-4-carbon","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":"1,000 questions / no tools","fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":502,"rawScore":69.1,"normalizedScore":100,"contribution":10,"source":"https://artificialanalysis.ai/models/gemini-4-carbon","settings":"{\"comparison_group\": \"aa-hle-diamond-no-tools-1000\", \"selection\": \"best reported configuration per release\", \"settings\": \"Gemini 4 Carbon (High)\", \"tools\": false}"},{"modelId":"gemini-4-carbon","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":722,"rawScore":29.6,"normalizedScore":88.75000000000001,"contribution":8.875000000000002,"source":"https://artificialanalysis.ai/evaluations/gdp-pdf","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"Gemini 4 Carbon (medium)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"gemini-4-carbon","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":575,"rawScore":1610,"normalizedScore":66.61211129296235,"contribution":13.322422258592471,"source":"https://artificialanalysis.ai/evaluations/aa-briefcase","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"publisher default displayed configuration\", \"settings\": \"Gemini 4 Carbon (high)\"}"},{"modelId":"gemini-4-carbon","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gemini-4-carbon","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gemini-4-carbon","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":690,"rawScore":65.1515151515151,"normalizedScore":96.29629629629615,"contribution":14.444444444444422,"source":"https://artificialanalysis.ai/models/gemini-4-carbon","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"Gemini 4 Carbon (High)\"}"},{"modelId":"gemini-4-carbon","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"glm-5","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"glm-5","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"glm-5","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"glm-5","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"glm-5","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"glm-5","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":null,"fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"glm-5","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"glm-5-1","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"glm-5-1","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":749,"rawScore":8.4,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/gdp-pdf","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"GLM-5.1\", \"tools\": \"benchmark-defined\"}"},{"modelId":"glm-5-1","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":777,"rawScore":965,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/aa-briefcase","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"GLM-5.1\", \"tools\": \"benchmark-defined\"}"},{"modelId":"glm-5-1","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"glm-5-1","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"glm-5-1","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":814,"rawScore":2,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/terminalbench-4-0","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"GLM-5.1\"}"},{"modelId":"glm-5-1","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"glm-5-2","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"glm-5-2","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":536,"rawScore":10.4,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/models/glm-5-2","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"GLM-5.2 (Max)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"glm-5-2","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":552,"rawScore":1227.23,"normalizedScore":3.9656301145662876,"contribution":0.7931260229132575,"source":"https://artificialanalysis.ai/models/glm-5-2","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"GLM-5.2 (Max)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"glm-5-2","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"glm-5-2","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"glm-5-2","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":718,"rawScore":1.01010101010101,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/models/glm-5-2","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"GLM-5.2 (Max)\"}"},{"modelId":"glm-5-2","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"glm-5-3","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":"1,000 questions / no tools","fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":514,"rawScore":17.9,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/models/glm-5-3","settings":"{\"comparison_group\": \"aa-hle-diamond-no-tools-1000\", \"selection\": \"best reported configuration per release\", \"settings\": \"GLM-5.3 (Max)\", \"tools\": false}"},{"modelId":"glm-5-3","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":533,"rawScore":11.200000000000001,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/models/glm-5-3","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"GLM-5.3 (Max)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"glm-5-3","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":549,"rawScore":1504.57,"normalizedScore":49.35679214402617,"contribution":9.871358428805236,"source":"https://artificialanalysis.ai/models/glm-5-3","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"GLM-5.3 (Max)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"glm-5-3","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic-2026-10-14","benchmarkVersion":"2.0 / 2026-10-14","fallback":1,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":990,"rawScore":35.9,"normalizedScore":31.59609120521172,"contribution":6.3192182410423445,"source":"https://livebench.ai/#/release/2026-10-14","settings":"{\"comparison_group\": \"livebench-2-2026-10-14-agentic\", \"release\": \"2026-10-14\", \"settings\": \"Official LiveBench 2.0 row GLM-5.3. One run per suite; effort not explicitly labeled on this row. Historical release, not the October 25 index track.\", \"source_model_id\": \"glm-5.3\", \"suite\": \"agentic\"}"},{"modelId":"glm-5-3","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding-2026-10-14","benchmarkVersion":"2.0 / 2026-10-14","fallback":1,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":991,"rawScore":82.8,"normalizedScore":61.19791666666666,"contribution":3.059895833333333,"source":"https://livebench.ai/#/release/2026-10-14","settings":"{\"comparison_group\": \"livebench-2-2026-10-14-coding\", \"release\": \"2026-10-14\", \"settings\": \"Official LiveBench 2.0 row GLM-5.3. One run per suite; effort not explicitly labeled on this row. Historical release, not the October 25 index track.\", \"source_model_id\": \"glm-5.3\", \"suite\": \"coding\"}"},{"modelId":"glm-5-3","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":706,"rawScore":41.9191919191919,"normalizedScore":53.70370370370367,"contribution":8.05555555555555,"source":"https://artificialanalysis.ai/models/glm-5-3","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"GLM-5.3 (Max)\"}"},{"modelId":"glm-5-3","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use-2026-10-14","benchmarkVersion":"2.0 / 2026-10-14","fallback":1,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":992,"rawScore":0,"normalizedScore":0,"contribution":0,"source":"https://livebench.ai/#/release/2026-10-14","settings":"{\"comparison_group\": \"livebench-2-2026-10-14-browser-use\", \"release\": \"2026-10-14\", \"settings\": \"Official LiveBench 2.0 row GLM-5.3. One run per suite; effort not explicitly labeled on this row. Historical release, not the October 25 index track.\", \"source_model_id\": \"glm-5.3\", \"suite\": \"browser-use\"}"},{"modelId":"glm-5-3-flash","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":"1,000 questions / no tools","fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":517,"rawScore":18.2,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/models/glm-5-3-flash","settings":"{\"comparison_group\": \"aa-hle-diamond-no-tools-1000\", \"selection\": \"best reported configuration per release\", \"settings\": \"GLM-5.3-Flash\", \"tools\": false}"},{"modelId":"glm-5-3-flash","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":523,"rawScore":15.4,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/models/glm-5-3-flash","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"GLM-5.3-Flash\", \"tools\": \"benchmark-defined\"}"},{"modelId":"glm-5-3-flash","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":539,"rawScore":1450.23,"normalizedScore":40.46317512274959,"contribution":8.092635024549919,"source":"https://artificialanalysis.ai/models/glm-5-3-flash","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"GLM-5.3-Flash\", \"tools\": \"benchmark-defined\"}"},{"modelId":"glm-5-3-flash","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":598,"rawScore":19,"normalizedScore":4.071661237785016,"contribution":0.8143322475570033,"source":"https://livebench.ai/#/release/2026-10-25","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-agentic\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"agentic\"}"},{"modelId":"glm-5-3-flash","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":626,"rawScore":80.6,"normalizedScore":55.46874999999998,"contribution":2.773437499999999,"source":"https://livebench.ai/#/release/2026-10-25","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-coding\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"coding\"}"},{"modelId":"glm-5-3-flash","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":712,"rawScore":32.8282828282828,"normalizedScore":37.037037037036995,"contribution":5.555555555555549,"source":"https://artificialanalysis.ai/models/glm-5-3-flash","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"GLM-5.3-Flash\"}"},{"modelId":"glm-5-3-flash","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":640,"rawScore":59.8,"normalizedScore":30.497925311203314,"contribution":6.0995850622406635,"source":"https://livebench.ai/#/release/2026-10-25","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-browser-use\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"browser-use\"}"},{"modelId":"gpt-4-1","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-4-1","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-4-1","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-4-1","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-4-1","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-4-1","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":null,"fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-4-1","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-4-1-mini","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-4-1-mini","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-4-1-mini","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-4-1-mini","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-4-1-mini","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-4-1-mini","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":null,"fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-4-1-mini","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-4-turbo","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-4-turbo","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-4-turbo","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-4-turbo","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-4-turbo","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-4-turbo","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":null,"fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-4-turbo","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-4o","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-4o","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-4o","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-4o","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-4o","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-4o","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":null,"fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-4o","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-2","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-2","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-2","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-2","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-2","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-2","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":null,"fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-2","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-4","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-4","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-4","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-4","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-4","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-4","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":null,"fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-4","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-4-mini","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-4-mini","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":744,"rawScore":13.4,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/gdp-pdf","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"GPT-5.4 mini (xhigh)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"gpt-5-4-mini","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":780,"rawScore":720,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/aa-briefcase","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"GPT-5.4 mini (xhigh)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"gpt-5-4-mini","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-4-mini","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-4-mini","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":813,"rawScore":2,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/terminalbench-4-0","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"GPT-5.4 mini (xhigh)\"}"},{"modelId":"gpt-5-4-mini","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-4-pro","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-4-pro","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-4-pro","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-4-pro","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-4-pro","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-4-pro","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":null,"fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-4-pro","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-5","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-5","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":732,"rawScore":22.6,"normalizedScore":45.000000000000014,"contribution":4.500000000000002,"source":"https://artificialanalysis.ai/evaluations/gdp-pdf","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"GPT-5.5 (high)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"gpt-5-5","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":773,"rawScore":1136,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/aa-briefcase","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"GPT-5.5 (xhigh)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"gpt-5-5","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-5","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-5","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":693,"rawScore":14.6464646464646,"normalizedScore":3.7037037037036615,"contribution":0.5555555555555493,"source":"https://artificialanalysis.ai/models/gpt-5-5","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"GPT-5.5 (Xhigh)\"}"},{"modelId":"gpt-5-5","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-5-pro","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-5-pro","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-5-pro","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-5-pro","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-5-pro","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-5-pro","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":null,"fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-5-pro","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-6","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-6","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-6","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-6","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-6","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-6","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":null,"fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-6","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-6-luna","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-6-luna","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":727,"rawScore":24,"normalizedScore":53.75000000000001,"contribution":5.375000000000001,"source":"https://artificialanalysis.ai/evaluations/gdp-pdf","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"GPT-5.6 Luna (max)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"gpt-5-6-luna","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":766,"rawScore":1339,"normalizedScore":22.25859247135843,"contribution":4.451718494271686,"source":"https://artificialanalysis.ai/evaluations/aa-briefcase","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"GPT-5.6 Luna (max)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"gpt-5-6-luna","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-6-luna","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-6-luna","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":808,"rawScore":11.6,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/terminalbench-4-0","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"GPT-5.6 Luna (max)\"}"},{"modelId":"gpt-5-6-luna","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-6-sol","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-6-sol","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":724,"rawScore":27.8,"normalizedScore":77.50000000000001,"contribution":7.750000000000002,"source":"https://artificialanalysis.ai/evaluations/gdp-pdf","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"GPT-5.6 Sol (high)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"gpt-5-6-sol","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":761,"rawScore":1479,"normalizedScore":45.171849427168574,"contribution":9.034369885433716,"source":"https://artificialanalysis.ai/evaluations/aa-briefcase","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"GPT-5.6 Sol (max)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"gpt-5-6-sol","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-6-sol","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-6-sol","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":688,"rawScore":39.8989898989899,"normalizedScore":50,"contribution":7.5,"source":"https://artificialanalysis.ai/models/gpt-5-6-sol","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"GPT-5.6 Sol (Max)\"}"},{"modelId":"gpt-5-6-sol","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-5-6-terra","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":"1,000 questions / no tools","fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":791,"rawScore":28.8,"normalizedScore":21.32796780684105,"contribution":2.132796780684105,"source":"https://artificialanalysis.ai/evaluations/hle-diamond","settings":"{\"comparison_group\": \"aa-hle-diamond-no-tools-1000\", \"selection\": \"best reported configuration per release\", \"settings\": \"GPT-5.6 Terra (max)\", \"tools\": false}"},{"modelId":"gpt-5-6-terra","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":726,"rawScore":24.6,"normalizedScore":57.500000000000014,"contribution":5.750000000000002,"source":"https://artificialanalysis.ai/evaluations/gdp-pdf","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"GPT-5.6 Terra (xhigh)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"gpt-5-6-terra","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":768,"rawScore":1333,"normalizedScore":21.27659574468085,"contribution":4.25531914893617,"source":"https://artificialanalysis.ai/evaluations/aa-briefcase","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"GPT-5.6 Terra (max)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"gpt-5-6-terra","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":843,"rawScore":33.1,"normalizedScore":27.035830618892508,"contribution":5.407166123778502,"source":"https://livebench.ai/data/20261025/table.csv","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-agentic\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"agentic\"}"},{"modelId":"gpt-5-6-terra","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":845,"rawScore":86.2,"normalizedScore":70.05208333333333,"contribution":3.5026041666666665,"source":"https://livebench.ai/data/20261025/table.csv","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-coding\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"coding\"}"},{"modelId":"gpt-5-6-terra","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":803,"rawScore":35.4,"normalizedScore":41.75185185185185,"contribution":6.262777777777778,"source":"https://artificialanalysis.ai/evaluations/terminalbench-4-0","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"GPT-5.6 Terra (max)\"}"},{"modelId":"gpt-5-6-terra","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":846,"rawScore":70.3,"normalizedScore":52.28215767634854,"contribution":10.456431535269708,"source":"https://livebench.ai/data/20261025/table.csv","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-browser-use\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"browser-use\"}"},{"modelId":"gpt-6-1-sol","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":"1,000 questions / no tools","fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":501,"rawScore":58.8,"normalizedScore":81.6901408450704,"contribution":8.16901408450704,"source":"https://artificialanalysis.ai/models/gpt-6-1-sol","settings":"{\"comparison_group\": \"aa-hle-diamond-no-tools-1000\", \"selection\": \"best reported configuration per release\", \"settings\": \"GPT-6.1 Sol (Max)\", \"tools\": false}"},{"modelId":"gpt-6-1-sol","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":720,"rawScore":32,"normalizedScore":100,"contribution":10,"source":"https://artificialanalysis.ai/evaluations/gdp-pdf","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"GPT-6.1 Sol (high)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"gpt-6-1-sol","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":577,"rawScore":1555,"normalizedScore":57.61047463175123,"contribution":11.522094926350247,"source":"https://artificialanalysis.ai/evaluations/aa-briefcase","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"publisher default displayed configuration\", \"settings\": \"GPT-6.1 Sol (max)\"}"},{"modelId":"gpt-6-1-sol","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":589,"rawScore":68.7,"normalizedScore":85.01628664495114,"contribution":17.003257328990227,"source":"https://livebench.ai/#/release/2026-10-25","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-agentic\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"agentic\"}"},{"modelId":"gpt-6-1-sol","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":617,"rawScore":96,"normalizedScore":95.57291666666667,"contribution":4.778645833333334,"source":"https://livebench.ai/#/release/2026-10-25","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-coding\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"coding\"}"},{"modelId":"gpt-6-1-sol","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":689,"rawScore":56.0606060606061,"normalizedScore":79.62962962962966,"contribution":11.944444444444448,"source":"https://artificialanalysis.ai/models/gpt-6-1-sol","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"GPT-6.1 Sol (Max)\"}"},{"modelId":"gpt-6-1-sol","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":631,"rawScore":93.3,"normalizedScore":100,"contribution":20,"source":"https://livebench.ai/#/release/2026-10-25","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-browser-use\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"browser-use\"}"},{"modelId":"gpt-6-1-terra","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":"1,000 questions / no tools","fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":788,"rawScore":47.3,"normalizedScore":58.55130784708249,"contribution":5.855130784708249,"source":"https://artificialanalysis.ai/evaluations/hle-diamond","settings":"{\"comparison_group\": \"aa-hle-diamond-no-tools-1000\", \"selection\": \"best reported configuration per release\", \"settings\": \"GPT-6.1 Terra (max)\", \"tools\": false}"},{"modelId":"gpt-6-1-terra","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":723,"rawScore":28.6,"normalizedScore":82.50000000000001,"contribution":8.250000000000002,"source":"https://artificialanalysis.ai/evaluations/gdp-pdf","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"GPT-6.1 Terra (max)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"gpt-6-1-terra","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":763,"rawScore":1402,"normalizedScore":32.56955810147299,"contribution":6.513911620294599,"source":"https://artificialanalysis.ai/evaluations/aa-briefcase","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"GPT-6.1 Terra (max)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"gpt-6-1-terra","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":822,"rawScore":48.6,"normalizedScore":52.2801302931596,"contribution":10.45602605863192,"source":"https://livebench.ai/data/20261025/table.csv","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-agentic\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"agentic\"}"},{"modelId":"gpt-6-1-terra","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":824,"rawScore":94.3,"normalizedScore":91.14583333333331,"contribution":4.557291666666666,"source":"https://livebench.ai/data/20261025/table.csv","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-coding\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"coding\"}"},{"modelId":"gpt-6-1-terra","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":801,"rawScore":55.6,"normalizedScore":78.78518518518516,"contribution":11.817777777777772,"source":"https://artificialanalysis.ai/evaluations/terminalbench-4-0","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"GPT-6.1 Terra (max)\"}"},{"modelId":"gpt-6-1-terra","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":825,"rawScore":93.1,"normalizedScore":99.58506224066389,"contribution":19.91701244813278,"source":"https://livebench.ai/data/20261025/table.csv","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-browser-use\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"browser-use\"}"},{"modelId":"gpt-6-astra","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":"1,000 questions / no tools","fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":503,"rawScore":63.800000000000004,"normalizedScore":91.75050301810866,"contribution":9.175050301810867,"source":"https://artificialanalysis.ai/models/gpt-6-astra","settings":"{\"comparison_group\": \"aa-hle-diamond-no-tools-1000\", \"selection\": \"best reported configuration per release\", \"settings\": \"GPT-6 Astra (Max)\", \"tools\": false}"},{"modelId":"gpt-6-astra","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":719,"rawScore":32.2,"normalizedScore":100,"contribution":10,"source":"https://artificialanalysis.ai/evaluations/gdp-pdf","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"GPT-6 Astra (xhigh)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"gpt-6-astra","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":576,"rawScore":1569,"normalizedScore":59.90180032733224,"contribution":11.98036006546645,"source":"https://artificialanalysis.ai/evaluations/aa-briefcase","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"publisher default displayed configuration\", \"settings\": \"GPT-6 Astra (max)\"}"},{"modelId":"gpt-6-astra","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":587,"rawScore":77.5,"normalizedScore":99.3485342019544,"contribution":19.86970684039088,"source":"https://livebench.ai/#/release/2026-10-25","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-agentic\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"agentic\"}"},{"modelId":"gpt-6-astra","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":615,"rawScore":93.7,"normalizedScore":89.58333333333333,"contribution":4.479166666666667,"source":"https://livebench.ai/#/release/2026-10-25","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-coding\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"coding\"}"},{"modelId":"gpt-6-astra","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":694,"rawScore":59.5959595959596,"normalizedScore":86.11111111111107,"contribution":12.91666666666666,"source":"https://artificialanalysis.ai/models/gpt-6-astra-xhigh","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"GPT-6 Astra (Xhigh)\"}"},{"modelId":"gpt-6-astra","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":629,"rawScore":91.3,"normalizedScore":95.85062240663902,"contribution":19.170124481327804,"source":"https://livebench.ai/#/release/2026-10-25","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-browser-use\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"browser-use\"}"},{"modelId":"gpt-6-luna","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":"1,000 questions / no tools","fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":794,"rawScore":22.2,"normalizedScore":8.048289738430583,"contribution":0.8048289738430583,"source":"https://artificialanalysis.ai/evaluations/hle-diamond","settings":"{\"comparison_group\": \"aa-hle-diamond-no-tools-1000\", \"selection\": \"best reported configuration per release\", \"settings\": \"GPT-6 Luna (max)\", \"tools\": false}"},{"modelId":"gpt-6-luna","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":731,"rawScore":22.8,"normalizedScore":46.25000000000001,"contribution":4.625000000000001,"source":"https://artificialanalysis.ai/evaluations/gdp-pdf","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"GPT-6 Luna (max)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"gpt-6-luna","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":767,"rawScore":1337,"normalizedScore":21.93126022913257,"contribution":4.386252045826514,"source":"https://artificialanalysis.ai/evaluations/aa-briefcase","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"GPT-6 Luna (max)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"gpt-6-luna","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":850,"rawScore":30.9,"normalizedScore":23.452768729641686,"contribution":4.690553745928337,"source":"https://livebench.ai/data/20261025/table.csv","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-agentic\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"agentic\"}"},{"modelId":"gpt-6-luna","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":852,"rawScore":84.5,"normalizedScore":65.625,"contribution":3.28125,"source":"https://livebench.ai/data/20261025/table.csv","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-coding\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"coding\"}"},{"modelId":"gpt-6-luna","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":807,"rawScore":12.6,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/terminalbench-4-0","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"GPT-6 Luna (max)\"}"},{"modelId":"gpt-6-luna","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":853,"rawScore":70.3,"normalizedScore":52.28215767634854,"contribution":10.456431535269708,"source":"https://livebench.ai/data/20261025/table.csv","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-browser-use\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"browser-use\"}"},{"modelId":"gpt-oss-120b","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":"1,000 questions / no tools","fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":520,"rawScore":3.8,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/models/gpt-oss-120b","settings":"{\"comparison_group\": \"aa-hle-diamond-no-tools-1000\", \"selection\": \"best reported configuration per release\", \"settings\": \"gpt-oss-120b (High)\", \"tools\": false}"},{"modelId":"gpt-oss-120b","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":535,"rawScore":4,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/models/gpt-oss-120b","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"gpt-oss-120b (High)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"gpt-oss-120b","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":551,"rawScore":0,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/models/gpt-oss-120b","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"gpt-oss-120b (High)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"gpt-oss-120b","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-oss-120b","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-oss-120b","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":717,"rawScore":0,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/models/gpt-oss-120b","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"gpt-oss-120b (High)\"}"},{"modelId":"gpt-oss-120b","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-oss-20b","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":"1,000 questions / no tools","fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":519,"rawScore":4.8,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/models/gpt-oss-20b","settings":"{\"comparison_group\": \"aa-hle-diamond-no-tools-1000\", \"selection\": \"best reported configuration per release\", \"settings\": \"gpt-oss-20b (High)\", \"tools\": false}"},{"modelId":"gpt-oss-20b","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":525,"rawScore":2,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/models/gpt-oss-20b","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"gpt-oss-20b (High)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"gpt-oss-20b","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":541,"rawScore":0,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/models/gpt-oss-20b","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"gpt-oss-20b (High)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"gpt-oss-20b","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-oss-20b","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"gpt-oss-20b","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":714,"rawScore":0,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/models/gpt-oss-20b","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"gpt-oss-20b (High)\"}"},{"modelId":"gpt-oss-20b","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"grok-4-7","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":"1,000 questions / no tools","fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":504,"rawScore":23.599999999999998,"normalizedScore":10.865191146881285,"contribution":1.0865191146881286,"source":"https://artificialanalysis.ai/models/grok-4-7-high","settings":"{\"comparison_group\": \"aa-hle-diamond-no-tools-1000\", \"selection\": \"best reported configuration per release\", \"settings\": \"Grok 4.7 (High)\", \"tools\": false}"},{"modelId":"grok-4-7","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":728,"rawScore":23.2,"normalizedScore":48.75,"contribution":4.875,"source":"https://artificialanalysis.ai/evaluations/gdp-pdf","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"Grok 4.7 (high)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"grok-4-7","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":574,"rawScore":1638,"normalizedScore":71.19476268412438,"contribution":14.238952536824877,"source":"https://artificialanalysis.ai/evaluations/aa-briefcase","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"publisher default displayed configuration\", \"settings\": \"Grok 4.7 (xhigh)\"}"},{"modelId":"grok-4-7","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":594,"rawScore":46.1,"normalizedScore":48.208469055374586,"contribution":9.641693811074918,"source":"https://livebench.ai/#/release/2026-10-25","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-agentic\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"agentic\"}"},{"modelId":"grok-4-7","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":622,"rawScore":84.5,"normalizedScore":65.625,"contribution":3.28125,"source":"https://livebench.ai/#/release/2026-10-25","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-coding\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"coding\"}"},{"modelId":"grok-4-7","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":695,"rawScore":25.7575757575758,"normalizedScore":24.074074074074176,"contribution":3.6111111111111263,"source":"https://artificialanalysis.ai/models/grok-4-7","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"Grok 4.7 (Xhigh)\"}"},{"modelId":"grok-4-7","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":636,"rawScore":49.3,"normalizedScore":8.713692946058083,"contribution":1.7427385892116167,"source":"https://livebench.ai/#/release/2026-10-25","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-browser-use\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"browser-use\"}"},{"modelId":"grok-4-heavy","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"grok-4-heavy","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"grok-4-heavy","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"grok-4-heavy","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"grok-4-heavy","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"grok-4-heavy","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":null,"fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"grok-4-heavy","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"inkling","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":"1,000 questions / no tools","fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":798,"rawScore":10.6,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/hle-diamond","settings":"{\"comparison_group\": \"aa-hle-diamond-no-tools-1000\", \"selection\": \"best reported configuration per release\", \"settings\": \"Inkling (xhigh)\", \"tools\": false}"},{"modelId":"inkling","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":746,"rawScore":12.8,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/gdp-pdf","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"Inkling (xhigh)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"inkling","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":779,"rawScore":833,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/aa-briefcase","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"Inkling (xhigh)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"inkling","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":892,"rawScore":8.5,"normalizedScore":0,"contribution":0,"source":"https://livebench.ai/data/20261025/table.csv","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-agentic\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"agentic\"}"},{"modelId":"inkling","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":894,"rawScore":64,"normalizedScore":12.23958333333334,"contribution":0.611979166666667,"source":"https://livebench.ai/data/20261025/table.csv","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-coding\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"coding\"}"},{"modelId":"inkling","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":815,"rawScore":1,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/terminalbench-4-0","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"Inkling (xhigh)\"}"},{"modelId":"inkling","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":895,"rawScore":12,"normalizedScore":0,"contribution":0,"source":"https://livebench.ai/data/20261025/table.csv","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-browser-use\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"browser-use\"}"},{"modelId":"kimi-k2-5","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"kimi-k2-5","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"kimi-k2-5","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"kimi-k2-5","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"kimi-k2-5","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"kimi-k2-5","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":null,"fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"kimi-k2-5","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"kimi-k2-6","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"kimi-k2-6","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":521,"rawScore":13,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/models/kimi-k2-6","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"Kimi K2.6 (Reasoning)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"kimi-k2-6","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":537,"rawScore":820.03,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/models/kimi-k2-6","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"Kimi K2.6 (Reasoning)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"kimi-k2-6","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"kimi-k2-6","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"kimi-k2-6","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":710,"rawScore":0.505050505050505,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/models/kimi-k2-6","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"Kimi K2.6 (Reasoning)\"}"},{"modelId":"kimi-k2-6","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"kimi-k2-thinking","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"kimi-k2-thinking","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"kimi-k2-thinking","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"kimi-k2-thinking","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"kimi-k2-thinking","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"kimi-k2-thinking","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":null,"fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"kimi-k2-thinking","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"kimi-k3","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":"1,000 questions / no tools","fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":506,"rawScore":26.900000000000002,"normalizedScore":17.50503018108652,"contribution":1.7505030181086523,"source":"https://artificialanalysis.ai/models/kimi-k3","settings":"{\"comparison_group\": \"aa-hle-diamond-no-tools-1000\", \"selection\": \"best reported configuration per release\", \"settings\": \"Kimi K3 (Max)\", \"tools\": false}"},{"modelId":"kimi-k3","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":526,"rawScore":22,"normalizedScore":41.25000000000001,"contribution":4.125000000000001,"source":"https://artificialanalysis.ai/models/kimi-k3","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"Kimi K3 (Max)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"kimi-k3","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":542,"rawScore":1498.42,"normalizedScore":48.35024549918168,"contribution":9.670049099836337,"source":"https://artificialanalysis.ai/models/kimi-k3","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"Kimi K3 (Max)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"kimi-k3","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":596,"rawScore":26.4,"normalizedScore":16.12377850162866,"contribution":3.224755700325732,"source":"https://livebench.ai/#/release/2026-10-25","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-agentic\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"agentic\"}"},{"modelId":"kimi-k3","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":624,"rawScore":59.3,"normalizedScore":0,"contribution":0,"source":"https://livebench.ai/#/release/2026-10-25","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-coding\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"coding\"}"},{"modelId":"kimi-k3","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":697,"rawScore":12.6262626262626,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/models/kimi-k3-low","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"Kimi K3 (Low)\"}"},{"modelId":"kimi-k3","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":638,"rawScore":75.2,"normalizedScore":62.44813278008299,"contribution":12.4896265560166,"source":"https://livebench.ai/#/release/2026-10-25","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-browser-use\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"browser-use\"}"},{"modelId":"kimi-k3-1-pro","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":"1,000 questions / no tools","fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":508,"rawScore":37.3,"normalizedScore":38.430583501006026,"contribution":3.843058350100603,"source":"https://artificialanalysis.ai/models/kimi-k3-1-pro","settings":"{\"comparison_group\": \"aa-hle-diamond-no-tools-1000\", \"selection\": \"best reported configuration per release\", \"settings\": \"Kimi K3.1 Pro\", \"tools\": false}"},{"modelId":"kimi-k3-1-pro","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":528,"rawScore":31.4,"normalizedScore":100,"contribution":10,"source":"https://artificialanalysis.ai/models/kimi-k3-1-pro","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"Kimi K3.1 Pro\", \"tools\": \"benchmark-defined\"}"},{"modelId":"kimi-k3-1-pro","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":544,"rawScore":1675.78,"normalizedScore":77.37806873977087,"contribution":15.475613747954174,"source":"https://artificialanalysis.ai/models/kimi-k3-1-pro","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"Kimi K3.1 Pro\", \"tools\": \"benchmark-defined\"}"},{"modelId":"kimi-k3-1-pro","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":593,"rawScore":39.1,"normalizedScore":36.807817589576544,"contribution":7.361563517915309,"source":"https://livebench.ai/#/release/2026-10-25","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-agentic\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"agentic\"}"},{"modelId":"kimi-k3-1-pro","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":621,"rawScore":81.8,"normalizedScore":58.59374999999999,"contribution":2.9296875,"source":"https://livebench.ai/#/release/2026-10-25","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-coding\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"coding\"}"},{"modelId":"kimi-k3-1-pro","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":699,"rawScore":67.1717171717172,"normalizedScore":100,"contribution":15,"source":"https://artificialanalysis.ai/models/kimi-k3-1-pro","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"Kimi K3.1 Pro\"}"},{"modelId":"kimi-k3-1-pro","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":635,"rawScore":75.9,"normalizedScore":63.90041493775935,"contribution":12.780082987551872,"source":"https://livebench.ai/#/release/2026-10-25","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-browser-use\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"browser-use\"}"},{"modelId":"llama3-70b-appworld","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"llama3-70b-appworld","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"llama3-70b-appworld","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"llama3-70b-appworld","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"llama3-70b-appworld","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"llama3-70b-appworld","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":null,"fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"llama3-70b-appworld","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"mimo-v2-6-pro","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":"1,000 questions / no tools","fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":796,"rawScore":15.2,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/hle-diamond","settings":"{\"comparison_group\": \"aa-hle-diamond-no-tools-1000\", \"selection\": \"best reported configuration per release\", \"settings\": \"MiMo-V2.6-Pro\", \"tools\": false}"},{"modelId":"mimo-v2-6-pro","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":736,"rawScore":19.2,"normalizedScore":23.749999999999996,"contribution":2.3749999999999996,"source":"https://artificialanalysis.ai/evaluations/gdp-pdf","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"MiMo-V2.6-Pro\", \"tools\": \"benchmark-defined\"}"},{"modelId":"mimo-v2-6-pro","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":759,"rawScore":1512,"normalizedScore":50.57283142389525,"contribution":10.114566284779052,"source":"https://artificialanalysis.ai/evaluations/aa-briefcase","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"MiMo-V2.6-Pro\", \"tools\": \"benchmark-defined\"}"},{"modelId":"mimo-v2-6-pro","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":836,"rawScore":35.2,"normalizedScore":30.456026058631924,"contribution":6.091205211726385,"source":"https://livebench.ai/data/20261025/table.csv","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-agentic\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"agentic\"}"},{"modelId":"mimo-v2-6-pro","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":838,"rawScore":81.5,"normalizedScore":57.8125,"contribution":2.890625,"source":"https://livebench.ai/data/20261025/table.csv","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-coding\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"coding\"}"},{"modelId":"mimo-v2-6-pro","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":804,"rawScore":34.8,"normalizedScore":40.651851851851845,"contribution":6.097777777777776,"source":"https://artificialanalysis.ai/evaluations/terminalbench-4-0","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"MiMo-V2.6-Pro\"}"},{"modelId":"mimo-v2-6-pro","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":839,"rawScore":77.3,"normalizedScore":66.80497925311202,"contribution":13.360995850622405,"source":"https://livebench.ai/data/20261025/table.csv","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-browser-use\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"browser-use\"}"},{"modelId":"minimax-m2-7","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"minimax-m2-7","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":752,"rawScore":6,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/gdp-pdf","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"MiniMax-M2.7\", \"tools\": \"benchmark-defined\"}"},{"modelId":"minimax-m2-7","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":781,"rawScore":719,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/aa-briefcase","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"MiniMax-M2.7\", \"tools\": \"benchmark-defined\"}"},{"modelId":"minimax-m2-7","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"minimax-m2-7","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"minimax-m2-7","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":820,"rawScore":0,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/terminalbench-4-0","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"MiniMax-M2.7\"}"},{"modelId":"minimax-m2-7","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"minimax-m3","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":"1,000 questions / no tools","fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":518,"rawScore":16,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/models/minimax-m3","settings":"{\"comparison_group\": \"aa-hle-diamond-no-tools-1000\", \"selection\": \"best reported configuration per release\", \"settings\": \"MiniMax-M3\", \"tools\": false}"},{"modelId":"minimax-m3","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":524,"rawScore":9.8,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/models/minimax-m3","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"MiniMax-M3\", \"tools\": \"benchmark-defined\"}"},{"modelId":"minimax-m3","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":540,"rawScore":1089.34,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/models/minimax-m3","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"MiniMax-M3\", \"tools\": \"benchmark-defined\"}"},{"modelId":"minimax-m3","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"minimax-m3","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"minimax-m3","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":713,"rawScore":2.02020202020202,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/models/minimax-m3","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"MiniMax-M3\"}"},{"modelId":"minimax-m3","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"minimax-m3-1-flash","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":"1,000 questions / no tools","fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":516,"rawScore":28.1,"normalizedScore":19.919517102615696,"contribution":1.9919517102615698,"source":"https://artificialanalysis.ai/models/minimax-m3-1-flash","settings":"{\"comparison_group\": \"aa-hle-diamond-no-tools-1000\", \"selection\": \"best reported configuration per release\", \"settings\": \"MiniMax-M3.1-Flash\", \"tools\": false}"},{"modelId":"minimax-m3-1-flash","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":534,"rawScore":20.8,"normalizedScore":33.75000000000001,"contribution":3.375000000000001,"source":"https://artificialanalysis.ai/models/minimax-m3-1-flash","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"MiniMax-M3.1-Flash\", \"tools\": \"benchmark-defined\"}"},{"modelId":"minimax-m3-1-flash","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":550,"rawScore":1474.82,"normalizedScore":44.487725040916516,"contribution":8.897545008183304,"source":"https://artificialanalysis.ai/models/minimax-m3-1-flash","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"MiniMax-M3.1-Flash\", \"tools\": \"benchmark-defined\"}"},{"modelId":"minimax-m3-1-flash","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":595,"rawScore":28.8,"normalizedScore":20.032573289902277,"contribution":4.006514657980456,"source":"https://livebench.ai/#/release/2026-10-25","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-agentic\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"agentic\"}"},{"modelId":"minimax-m3-1-flash","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":623,"rawScore":83.9,"normalizedScore":64.06250000000001,"contribution":3.203125000000001,"source":"https://livebench.ai/#/release/2026-10-25","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-coding\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"coding\"}"},{"modelId":"minimax-m3-1-flash","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":708,"rawScore":25.7575757575758,"normalizedScore":24.074074074074176,"contribution":3.6111111111111263,"source":"https://artificialanalysis.ai/models/minimax-m3-1-flash","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"MiniMax-M3.1-Flash\"}"},{"modelId":"minimax-m3-1-flash","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":637,"rawScore":80.6,"normalizedScore":73.65145228215766,"contribution":14.730290456431533,"source":"https://livebench.ai/#/release/2026-10-25","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-browser-use\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"browser-use\"}"},{"modelId":"muse-spark","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"muse-spark","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"muse-spark","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":783,"rawScore":646,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/aa-briefcase","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"Muse Spark\", \"tools\": \"benchmark-defined\"}"},{"modelId":"muse-spark","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"muse-spark","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"muse-spark","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":null,"fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"muse-spark","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"muse-spark-1-1","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"muse-spark-1-1","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":743,"rawScore":14.4,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/gdp-pdf","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"Muse Spark 1.1 (xhigh)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"muse-spark-1-1","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":778,"rawScore":851,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/aa-briefcase","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"Muse Spark 1.1 (xhigh)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"muse-spark-1-1","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"muse-spark-1-1","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"muse-spark-1-1","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":709,"rawScore":6.06060606060606,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/models/muse-spark-1-1","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"Muse Spark 1.1 (Xhigh)\"}"},{"modelId":"muse-spark-1-1","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"muse-spark-1-2","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"muse-spark-1-2","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":739,"rawScore":17.4,"normalizedScore":12.499999999999991,"contribution":1.2499999999999991,"source":"https://artificialanalysis.ai/evaluations/gdp-pdf","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"Muse Spark 1.2 (xhigh)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"muse-spark-1-2","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":769,"rawScore":1325,"normalizedScore":19.967266775777414,"contribution":3.993453355155483,"source":"https://artificialanalysis.ai/evaluations/aa-briefcase","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"Muse Spark 1.2 (xhigh)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"muse-spark-1-2","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"muse-spark-1-2","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"muse-spark-1-2","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":686,"rawScore":7.07070707070707,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/models/muse-spark-1-2","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"Muse Spark 1.2 (Xhigh)\"}"},{"modelId":"muse-spark-1-2","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"muse-spark-1-3","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":"1,000 questions / no tools","fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":512,"rawScore":33.7,"normalizedScore":31.18712273641852,"contribution":3.118712273641852,"source":"https://artificialanalysis.ai/models/muse-spark-1-3","settings":"{\"comparison_group\": \"aa-hle-diamond-no-tools-1000\", \"selection\": \"best reported configuration per release\", \"settings\": \"Muse Spark 1.3 (Max)\", \"tools\": false}"},{"modelId":"muse-spark-1-3","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":725,"rawScore":26.6,"normalizedScore":70.00000000000001,"contribution":7.000000000000002,"source":"https://artificialanalysis.ai/evaluations/gdp-pdf","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"Muse Spark 1.3 (max)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"muse-spark-1-3","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":757,"rawScore":1581,"normalizedScore":61.8657937806874,"contribution":12.37315875613748,"source":"https://artificialanalysis.ai/evaluations/aa-briefcase","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"Muse Spark 1.3 (max)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"muse-spark-1-3","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":597,"rawScore":25.5,"normalizedScore":14.657980456026058,"contribution":2.9315960912052117,"source":"https://livebench.ai/#/release/2026-10-25","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-agentic\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"agentic\"}"},{"modelId":"muse-spark-1-3","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":625,"rawScore":90.2,"normalizedScore":80.46875,"contribution":4.0234375,"source":"https://livebench.ai/#/release/2026-10-25","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-coding\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"coding\"}"},{"modelId":"muse-spark-1-3","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":704,"rawScore":33.3333333333333,"normalizedScore":37.962962962962905,"contribution":5.694444444444436,"source":"https://artificialanalysis.ai/models/muse-spark-1-3","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"Muse Spark 1.3 (Max)\"}"},{"modelId":"muse-spark-1-3","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":639,"rawScore":30.9,"normalizedScore":0,"contribution":0,"source":"https://livebench.ai/#/release/2026-10-25","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-browser-use\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"browser-use\"}"},{"modelId":"muse-spark-open","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":"1,000 questions / no tools","fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":792,"rawScore":26.3,"normalizedScore":16.297786720321934,"contribution":1.6297786720321934,"source":"https://artificialanalysis.ai/evaluations/hle-diamond","settings":"{\"comparison_group\": \"aa-hle-diamond-no-tools-1000\", \"selection\": \"best reported configuration per release\", \"settings\": \"Muse Spark Open (xhigh)\", \"tools\": false}"},{"modelId":"muse-spark-open","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":737,"rawScore":18.6,"normalizedScore":20.00000000000001,"contribution":2.0000000000000013,"source":"https://artificialanalysis.ai/evaluations/gdp-pdf","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"Muse Spark Open (xhigh)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"muse-spark-open","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":771,"rawScore":1279,"normalizedScore":12.438625204582651,"contribution":2.4877250409165304,"source":"https://artificialanalysis.ai/evaluations/aa-briefcase","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"Muse Spark Open (xhigh)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"muse-spark-open","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":878,"rawScore":11.7,"normalizedScore":0,"contribution":0,"source":"https://livebench.ai/data/20261025/table.csv","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-agentic\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"agentic\"}"},{"modelId":"muse-spark-open","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":880,"rawScore":73.6,"normalizedScore":37.23958333333332,"contribution":1.861979166666666,"source":"https://livebench.ai/data/20261025/table.csv","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-coding\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"coding\"}"},{"modelId":"muse-spark-open","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":809,"rawScore":8.1,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/terminalbench-4-0","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"Muse Spark Open (xhigh)\"}"},{"modelId":"muse-spark-open","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":881,"rawScore":26.2,"normalizedScore":0,"contribution":0,"source":"https://livebench.ai/data/20261025/table.csv","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-browser-use\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"browser-use\"}"},{"modelId":"muse-wonder-1-0","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":"1,000 questions / no tools","fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":789,"rawScore":39,"normalizedScore":41.85110663983903,"contribution":4.185110663983903,"source":"https://artificialanalysis.ai/evaluations/hle-diamond","settings":"{\"comparison_group\": \"aa-hle-diamond-no-tools-1000\", \"selection\": \"best reported configuration per release\", \"settings\": \"Muse Wonder (max)\", \"tools\": false}"},{"modelId":"muse-wonder-1-0","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":721,"rawScore":30.6,"normalizedScore":95.00000000000001,"contribution":9.500000000000002,"source":"https://artificialanalysis.ai/evaluations/gdp-pdf","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"Muse Wonder (max)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"muse-wonder-1-0","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":755,"rawScore":1659,"normalizedScore":74.63175122749591,"contribution":14.926350245499183,"source":"https://artificialanalysis.ai/evaluations/aa-briefcase","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"Muse Wonder (max)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"muse-wonder-1-0","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":857,"rawScore":52.6,"normalizedScore":58.79478827361563,"contribution":11.758957654723126,"source":"https://livebench.ai/data/20261025/table.csv","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-agentic\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"agentic\"}"},{"modelId":"muse-wonder-1-0","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":859,"rawScore":86.2,"normalizedScore":70.05208333333333,"contribution":3.5026041666666665,"source":"https://livebench.ai/data/20261025/table.csv","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-coding\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"coding\"}"},{"modelId":"muse-wonder-1-0","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":802,"rawScore":52,"normalizedScore":72.18518518518515,"contribution":10.827777777777772,"source":"https://artificialanalysis.ai/evaluations/terminalbench-4-0","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"Muse Wonder (max)\"}"},{"modelId":"muse-wonder-1-0","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":860,"rawScore":60,"normalizedScore":30.912863070539416,"contribution":6.182572614107883,"source":"https://livebench.ai/data/20261025/table.csv","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-browser-use\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"browser-use\"}"},{"modelId":"nemotron-3-5-super-vl","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":"1,000 questions / no tools","fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":799,"rawScore":8.8,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/hle-diamond","settings":"{\"comparison_group\": \"aa-hle-diamond-no-tools-1000\", \"selection\": \"best reported configuration per release\", \"settings\": \"Nemotron 3.5 Super VL\", \"tools\": false}"},{"modelId":"nemotron-3-5-super-vl","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":750,"rawScore":8,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/gdp-pdf","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"Nemotron 3.5 Super VL\", \"tools\": \"benchmark-defined\"}"},{"modelId":"nemotron-3-5-super-vl","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":776,"rawScore":999,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/aa-briefcase","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"Nemotron 3.5 Super VL\", \"tools\": \"benchmark-defined\"}"},{"modelId":"nemotron-3-5-super-vl","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":885,"rawScore":11.7,"normalizedScore":0,"contribution":0,"source":"https://livebench.ai/data/20261025/table.csv","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-agentic\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"agentic\"}"},{"modelId":"nemotron-3-5-super-vl","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":887,"rawScore":71.3,"normalizedScore":31.249999999999996,"contribution":1.5625,"source":"https://livebench.ai/data/20261025/table.csv","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-coding\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"coding\"}"},{"modelId":"nemotron-3-5-super-vl","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":821,"rawScore":0,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/terminalbench-4-0","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"Nemotron 3.5 Super VL\"}"},{"modelId":"nemotron-3-5-super-vl","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":888,"rawScore":21.6,"normalizedScore":0,"contribution":0,"source":"https://livebench.ai/data/20261025/table.csv","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-browser-use\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"browser-use\"}"},{"modelId":"qwen2-5-32b","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"qwen2-5-32b","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"qwen2-5-32b","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"qwen2-5-32b","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"qwen2-5-32b","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"qwen2-5-32b","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":null,"fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"qwen2-5-32b","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"qwen3-14b","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"qwen3-14b","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":754,"rawScore":1.2,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/gdp-pdf","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"Qwen3 14B\", \"tools\": \"benchmark-defined\"}"},{"modelId":"qwen3-14b","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":787,"rawScore":0,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/aa-briefcase","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"Qwen3 14B\", \"tools\": \"benchmark-defined\"}"},{"modelId":"qwen3-14b","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"qwen3-14b","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"qwen3-14b","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":819,"rawScore":0,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/terminalbench-4-0","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"Qwen3 14B\"}"},{"modelId":"qwen3-14b","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"qwen3-5-35b-a3b","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"qwen3-5-35b-a3b","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"qwen3-5-35b-a3b","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"qwen3-5-35b-a3b","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"qwen3-5-35b-a3b","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"qwen3-5-35b-a3b","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":null,"fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"qwen3-5-35b-a3b","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"qwen3-5-397b-a17b","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":"1,000 questions / no tools","fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":797,"rawScore":12.4,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/hle-diamond","settings":"{\"comparison_group\": \"aa-hle-diamond-no-tools-1000\", \"selection\": \"best reported configuration per release\", \"settings\": \"Qwen3.5 397B A17B\", \"tools\": false}"},{"modelId":"qwen3-5-397b-a17b","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":747,"rawScore":12.2,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/gdp-pdf","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"Qwen3.5 397B A17B\", \"tools\": \"benchmark-defined\"}"},{"modelId":"qwen3-5-397b-a17b","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":784,"rawScore":563,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/aa-briefcase","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"Qwen3.5 397B A17B\", \"tools\": \"benchmark-defined\"}"},{"modelId":"qwen3-5-397b-a17b","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"qwen3-5-397b-a17b","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"qwen3-5-397b-a17b","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":818,"rawScore":0,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/terminalbench-4-0","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"Qwen3.5 397B A17B\"}"},{"modelId":"qwen3-5-397b-a17b","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"qwen3-5-9b","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":"1,000 questions / no tools","fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":800,"rawScore":4.8,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/hle-diamond","settings":"{\"comparison_group\": \"aa-hle-diamond-no-tools-1000\", \"selection\": \"best reported configuration per release\", \"settings\": \"Qwen3.5 9B\", \"tools\": false}"},{"modelId":"qwen3-5-9b","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":751,"rawScore":6.6,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/gdp-pdf","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"Qwen3.5 9B\", \"tools\": \"benchmark-defined\"}"},{"modelId":"qwen3-5-9b","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":786,"rawScore":341,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/aa-briefcase","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"Qwen3.5 9B\", \"tools\": \"benchmark-defined\"}"},{"modelId":"qwen3-5-9b","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"qwen3-5-9b","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"qwen3-5-9b","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":816,"rawScore":0.5,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/terminalbench-4-0","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"Qwen3.5 9B\"}"},{"modelId":"qwen3-5-9b","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"qwen3-6-plus","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"qwen3-6-plus","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"qwen3-6-plus","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"qwen3-6-plus","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"qwen3-6-plus","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"qwen3-6-plus","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":null,"fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"qwen3-6-plus","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"qwen3-8-27b","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":"1,000 questions / no tools","fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":795,"rawScore":15.3,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/hle-diamond","settings":"{\"comparison_group\": \"aa-hle-diamond-no-tools-1000\", \"selection\": \"best reported configuration per release\", \"settings\": \"Qwen3.8 27B (xhigh)\", \"tools\": false}"},{"modelId":"qwen3-8-27b","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":740,"rawScore":16.4,"normalizedScore":6.24999999999999,"contribution":0.6249999999999991,"source":"https://artificialanalysis.ai/evaluations/gdp-pdf","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"Qwen3.8 27B (xhigh)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"qwen3-8-27b","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":764,"rawScore":1393,"normalizedScore":31.096563011456627,"contribution":6.219312602291326,"source":"https://artificialanalysis.ai/evaluations/aa-briefcase","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"Qwen3.8 27B (xhigh)\", \"tools\": \"benchmark-defined\"}"},{"modelId":"qwen3-8-27b","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":871,"rawScore":20.6,"normalizedScore":6.677524429967428,"contribution":1.3355048859934857,"source":"https://livebench.ai/data/20261025/table.csv","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-agentic\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"agentic\"}"},{"modelId":"qwen3-8-27b","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":873,"rawScore":86.8,"normalizedScore":71.61458333333333,"contribution":3.5807291666666665,"source":"https://livebench.ai/data/20261025/table.csv","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-coding\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"coding\"}"},{"modelId":"qwen3-8-27b","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":810,"rawScore":5.6,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/terminalbench-4-0","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"Qwen3.8 27B (xhigh)\"}"},{"modelId":"qwen3-8-27b","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":874,"rawScore":24.2,"normalizedScore":0,"contribution":0,"source":"https://livebench.ai/data/20261025/table.csv","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-browser-use\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"browser-use\"}"},{"modelId":"seed2-0-pro","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"seed2-0-pro","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"seed2-0-pro","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"seed2-0-pro","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"seed2-0-pro","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"seed2-0-pro","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":null,"fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"seed2-0-pro","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"step-3-7-flash","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"step-3-7-flash","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":null,"fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"step-3-7-flash","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"step-3-7-flash","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"step-3-7-flash","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":null,"fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"step-3-7-flash","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":null,"fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"step-3-7-flash","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":null,"fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":null,"rawScore":null,"normalizedScore":null,"contribution":null,"source":null,"settings":null},{"modelId":"step-5-preview","key":"reasoning","label":"HLE-Diamond","benchmarkId":"hle-diamond-aa","benchmarkVersion":"1,000 questions / no tools","fallback":0,"weight":0.1,"anchorMin":18.2,"anchorMax":67.9,"resultId":793,"rawScore":24.3,"normalizedScore":12.27364185110664,"contribution":1.2273641851106643,"source":"https://artificialanalysis.ai/evaluations/hle-diamond","settings":"{\"comparison_group\": \"aa-hle-diamond-no-tools-1000\", \"selection\": \"best reported configuration per release\", \"settings\": \"Step 5 Preview\", \"tools\": false}"},{"modelId":"step-5-preview","key":"documents","label":"GDP.pdf","benchmarkId":"gdp-pdf-aa","benchmarkVersion":"100 tasks / All-pass / five attempts","fallback":0,"weight":0.1,"anchorMin":15.4,"anchorMax":31.4,"resultId":742,"rawScore":14.8,"normalizedScore":0,"contribution":0,"source":"https://artificialanalysis.ai/evaluations/gdp-pdf","settings":"{\"comparison_group\": \"aa-gdp-pdf-all-pass-five-attempts\", \"selection\": \"best reported configuration per release\", \"settings\": \"Step 5 Preview\", \"tools\": \"benchmark-defined\"}"},{"modelId":"step-5-preview","key":"deliverables","label":"AA-Briefcase","benchmarkId":"aa-briefcase-v1-1","benchmarkVersion":"1.1 / combined Elo","fallback":0,"weight":0.2,"anchorMin":1203,"anchorMax":1814,"resultId":762,"rawScore":1425,"normalizedScore":36.33387888707038,"contribution":7.266775777414075,"source":"https://artificialanalysis.ai/evaluations/aa-briefcase","settings":"{\"comparison_group\": \"aa-briefcase-1.1-stirrup-combined-elo\", \"selection\": \"best reported configuration per release\", \"settings\": \"Step 5 Preview\", \"tools\": \"benchmark-defined\"}"},{"modelId":"step-5-preview","key":"agentic","label":"LiveBench Agentic","benchmarkId":"livebench-2-agentic","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":16.5,"anchorMax":77.9,"resultId":864,"rawScore":19.4,"normalizedScore":4.7231270358306165,"contribution":0.9446254071661233,"source":"https://livebench.ai/data/20261025/table.csv","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-agentic\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"agentic\"}"},{"modelId":"step-5-preview","key":"coding","label":"LiveBench Coding","benchmarkId":"livebench-2-coding","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.05,"anchorMin":59.3,"anchorMax":97.7,"resultId":866,"rawScore":85.6,"normalizedScore":68.48958333333331,"contribution":3.424479166666666,"source":"https://livebench.ai/data/20261025/table.csv","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-coding\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"coding\"}"},{"modelId":"step-5-preview","key":"terminal","label":"Terminal-Bench 4.0","benchmarkId":"terminal-bench-4-0-aa","benchmarkVersion":"4.0 / mini-swe-agent","fallback":0,"weight":0.15,"anchorMin":12.6262626262626,"anchorMax":67.1717171717172,"resultId":805,"rawScore":33.3,"normalizedScore":37.90185185185185,"contribution":5.685277777777777,"source":"https://artificialanalysis.ai/evaluations/terminalbench-4-0","settings":"{\"comparison_group\": \"aa-terminal-4.0-mini-swe-agent-three-repeats\", \"harness\": \"mini-swe-agent\", \"repeats\": 3, \"selection\": \"best reported configuration per release\", \"settings\": \"Step 5 Preview\"}"},{"modelId":"step-5-preview","key":"browser","label":"LiveBench Browser Use","benchmarkId":"livebench-2-browser-use","benchmarkVersion":"2.0 / 2026-10-25","fallback":0,"weight":0.2,"anchorMin":45.1,"anchorMax":93.3,"resultId":867,"rawScore":24.8,"normalizedScore":0,"contribution":0,"source":"https://livebench.ai/data/20261025/table.csv","settings":"{\"comparison_group\": \"livebench-2-2026-10-25-browser-use\", \"release\": \"2026-10-25\", \"settings\": \"Highest supported effort unless publisher reports an exception; single run\", \"suite\": \"browser-use\"}"}]}