{"id":"claude-opus-4-1","slug":"claude-opus-4-1","name":"Claude Opus 4.1","orgId":"anthropic","family":"claude-opus-4-1","releaseDate":"2025-08-05","availability":"ga","openWeights":false,"license":"Proprietary","paramsTotal":null,"contextWindow":200000,"knowledgeCutoff":null,"modelCardUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","hfRepo":null,"modalities":["text","image","file"],"aliases":["claude-opus-4-1-20250805","Claude Opus 4.1","claude-opus-4-1-20250805_unknown","anthropic/claude-opus-4.1","Anthropic: Claude Opus 4.1"],"aliasNote":null,"organization":{"id":"anthropic","name":"Anthropic","slug":"anthropic","country":null,"url":null,"color":"#D97757","mark":"A"},"price":{"modelId":"claude-opus-4-1","provider":"anthropic","inputPerM":null,"outputPerM":null,"blendedPerM":29.999999999999996,"tokensPerS":null,"observedAt":"2026-10-14","sourceId":"openrouter"},"answer":{"word":"It used to be.","scope":"Was SOTA in General LLM.","lead":"As of Oct 14, 2026, Claude Opus 4.1 from Anthropic. Was SOTA in General LLM. Was SOTA in Long context from 2025-08-18 to 2025-08-27. Currently ranked #43.","confidence":"medium"},"verdicts":[{"id":"v_overall_general-llm_claude-opus-4-1_2025-08-18_open_WAS_SOTA","model":"claude-opus-4-1","model_name":"Claude Opus 4.1","category":"general-llm","category_name":"General LLM","slice":"overall","state":"WAS_SOTA","rank":57,"present_evidence":[],"missing_evidence":[],"margin":38.62068965517241,"confidence":"medium","valid_from":"2025-08-18","valid_to":null,"configuration":null,"rationale":"Was SOTA in General LLM from 2025-08-18 to 2025-08-27. Currently ranked #57.","safeguard_flags":["dethroned"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Was SOTA · General LLM"},{"id":"v_pareto_general-llm_claude-opus-4-1_2026-10-14_open_RANKED","model":"claude-opus-4-1","model_name":"Claude Opus 4.1","category":"general-llm","category_name":"General LLM","slice":"pareto","state":"RANKED","rank":73,"present_evidence":[],"missing_evidence":[],"margin":38.829787234042556,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Not on the General LLM cost-quality frontier.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#73 in General LLM"},{"id":"v_overall_reasoning_claude-opus-4-1_2025-10-17_open_WAS_SOTA","model":"claude-opus-4-1","model_name":"Claude Opus 4.1","category":"reasoning","category_name":"Reasoning","slice":"overall","state":"WAS_SOTA","rank":47,"present_evidence":[],"missing_evidence":[],"margin":32.638888888888886,"confidence":"medium","valid_from":"2025-10-17","valid_to":null,"configuration":null,"rationale":"Was SOTA in Reasoning from 2025-10-17 to 2025-11-17. Currently ranked #47.","safeguard_flags":["dethroned"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Was SOTA · Reasoning"},{"id":"v_pareto_reasoning_claude-opus-4-1_2026-10-14_open_RANKED","model":"claude-opus-4-1","model_name":"Claude Opus 4.1","category":"reasoning","category_name":"Reasoning","slice":"pareto","state":"RANKED","rank":60,"present_evidence":[],"missing_evidence":[],"margin":32.44680851063829,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Not on the Reasoning cost-quality frontier.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#60 in Reasoning"},{"id":"v_overall_math_claude-opus-4-1_2026-10-14_open_RANKED","model":"claude-opus-4-1","model_name":"Claude Opus 4.1","category":"math","category_name":"Math","slice":"overall","state":"RANKED","rank":27,"present_evidence":[],"missing_evidence":[],"margin":57.77777777777778,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #27 in Math.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#27 in Math"},{"id":"v_pareto_math_claude-opus-4-1_2026-10-14_open_RANKED","model":"claude-opus-4-1","model_name":"Claude Opus 4.1","category":"math","category_name":"Math","slice":"pareto","state":"RANKED","rank":27,"present_evidence":[],"missing_evidence":[],"margin":57.77777777777778,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Not on the Math cost-quality frontier.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#27 in Math"},{"id":"v_overall_science_claude-opus-4-1_2026-10-14_open_RANKED","model":"claude-opus-4-1","model_name":"Claude Opus 4.1","category":"science","category_name":"Science","slice":"overall","state":"RANKED","rank":83,"present_evidence":[],"missing_evidence":[],"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Last listed at #83 in Science on 2025-08-05. That board does not award a crown.","safeguard_flags":["off_board"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#83 in Science"},{"id":"v_overall_coding_claude-opus-4-1_2026-10-14_open_INSUFFICIENT_DATA","model":"claude-opus-4-1","model_name":"Claude Opus 4.1","category":"coding","category_name":"Coding","slice":"overall","state":"INSUFFICIENT_DATA","rank":null,"present_evidence":[{"benchmark":"swe-bench-verified","name":"SWE-bench Verified","rank":17}],"missing_evidence":[{"benchmark":"terminal-bench-4","name":"Terminal-Bench 4.0"},{"benchmark":"swe-bench-pro-hard","name":"SWE-bench Pro V2 HARD"},{"benchmark":"lmarena-text-coding","name":"LMArena Text (style-controlled, coding)"}],"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"#17 on SWE-bench Verified; missing Terminal-Bench 4.0, SWE-bench Pro V2 HARD, and LMArena Text (style-controlled, coding)","safeguard_flags":["off_board"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Not enough data"},{"id":"v_overall_coding-web-dev_claude-opus-4-1_2025-11-12_open_WAS_SOTA","model":"claude-opus-4-1","model_name":"Claude Opus 4.1","category":"coding-web-dev","category_name":"Coding › Web dev","slice":"overall","state":"WAS_SOTA","rank":74,"present_evidence":[],"missing_evidence":[],"margin":69.52380952380952,"confidence":"medium","valid_from":"2025-11-12","valid_to":null,"configuration":null,"rationale":"Was SOTA in Coding › Web dev from 2025-11-12 to 2025-11-17. Currently ranked #74.","safeguard_flags":["dethroned"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Was SOTA · Coding › Web dev"},{"id":"v_pareto_coding-web-dev_claude-opus-4-1_2026-10-14_open_RANKED","model":"claude-opus-4-1","model_name":"Claude Opus 4.1","category":"coding-web-dev","category_name":"Coding › Web dev","slice":"pareto","state":"RANKED","rank":84,"present_evidence":[],"missing_evidence":[],"margin":66.4,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Not on the Coding › Web dev cost-quality frontier.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#84 in Coding › Web dev"},{"id":"v_overall_long-context_claude-opus-4-1_2025-08-18_open_WAS_SOTA","model":"claude-opus-4-1","model_name":"Claude Opus 4.1","category":"long-context","category_name":"Long context","slice":"overall","state":"WAS_SOTA","rank":43,"present_evidence":[],"missing_evidence":[],"margin":29.65517241379311,"confidence":"medium","valid_from":"2025-08-18","valid_to":null,"configuration":null,"rationale":"Was SOTA in Long context from 2025-08-18 to 2025-08-27. Currently ranked #43.","safeguard_flags":["dethroned"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Was SOTA · Long context"},{"id":"v_pareto_long-context_claude-opus-4-1_2026-10-14_open_RANKED","model":"claude-opus-4-1","model_name":"Claude Opus 4.1","category":"long-context","category_name":"Long context","slice":"pareto","state":"RANKED","rank":52,"present_evidence":[],"missing_evidence":[],"margin":27.65957446808511,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Not on the Long context cost-quality frontier.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#52 in Long context"},{"id":"v_overall_factuality_claude-opus-4-1_2026-10-14_open_RANKED","model":"claude-opus-4-1","model_name":"Claude Opus 4.1","category":"factuality","category_name":"Factuality","slice":"overall","state":"RANKED","rank":74,"present_evidence":[],"missing_evidence":[],"margin":56.06060606060607,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #74 in Factuality.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#74 in Factuality"},{"id":"v_pareto_factuality_claude-opus-4-1_2026-10-14_open_RANKED","model":"claude-opus-4-1","model_name":"Claude Opus 4.1","category":"factuality","category_name":"Factuality","slice":"pareto","state":"RANKED","rank":93,"present_evidence":[],"missing_evidence":[],"margin":54.651162790697676,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Not on the Factuality cost-quality frontier.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#93 in Factuality"}]}