{"id":"claude-opus-4-5","slug":"claude-opus-4-5","name":"Claude Opus 4.5","orgId":"anthropic","family":"claude-opus-4-5","releaseDate":"2025-11-24","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","file","image"],"aliases":["claude-opus-4-5-20251101","Claude Opus 4.5","claude-opus-4-5-20251101_unknown","anthropic/claude-opus-4.5","Anthropic: Claude Opus 4.5"],"aliasNote":null,"organization":{"id":"anthropic","name":"Anthropic","slug":"anthropic","country":null,"url":null,"color":"#D97757","mark":"A"},"price":{"modelId":"claude-opus-4-5","provider":"anthropic","inputPerM":null,"outputPerM":null,"blendedPerM":10,"tokensPerS":null,"observedAt":"2026-10-14","sourceId":"openrouter"},"answer":{"word":"It used to be.","scope":"Was SOTA in Reasoning.","lead":"As of Oct 14, 2026, Claude Opus 4.5 from Anthropic. Was SOTA in Reasoning. Was SOTA in Long context from 2026-01-29 to 2026-02-09. Currently ranked #18.","confidence":"medium"},"verdicts":[{"id":"v_overall_general-llm_claude-opus-4-5_2026-10-14_open_RANKED","model":"claude-opus-4-5","model_name":"Claude Opus 4.5","category":"general-llm","category_name":"General LLM","slice":"overall","state":"RANKED","rank":33,"present_evidence":[],"missing_evidence":[],"margin":22.06896551724138,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #33 in General LLM.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#33 in General LLM"},{"id":"v_pareto_general-llm_claude-opus-4-5_2026-10-14_open_RANKED","model":"claude-opus-4-5","model_name":"Claude Opus 4.5","category":"general-llm","category_name":"General LLM","slice":"pareto","state":"RANKED","rank":41,"present_evidence":[],"missing_evidence":[],"margin":21.808510638297875,"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":"#41 in General LLM"},{"id":"v_overall_reasoning_claude-opus-4-5_2025-12-01_open_WAS_SOTA","model":"claude-opus-4-5","model_name":"Claude Opus 4.5","category":"reasoning","category_name":"Reasoning","slice":"overall","state":"WAS_SOTA","rank":28,"present_evidence":[],"missing_evidence":[],"margin":19.444444444444443,"confidence":"medium","valid_from":"2025-12-01","valid_to":null,"configuration":null,"rationale":"Was SOTA in Reasoning from 2025-12-01 to 2026-02-09. Currently ranked #28.","safeguard_flags":["dethroned"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Was SOTA · Reasoning"},{"id":"v_pareto_reasoning_claude-opus-4-5_2026-10-14_open_RANKED","model":"claude-opus-4-5","model_name":"Claude Opus 4.5","category":"reasoning","category_name":"Reasoning","slice":"pareto","state":"RANKED","rank":30,"present_evidence":[],"missing_evidence":[],"margin":16.489361702127653,"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":"#30 in Reasoning"},{"id":"v_overall_math_claude-opus-4-5_2026-10-14_open_RANKED","model":"claude-opus-4-5","model_name":"Claude Opus 4.5","category":"math","category_name":"Math","slice":"overall","state":"RANKED","rank":16,"present_evidence":[],"missing_evidence":[],"margin":33.33333333333333,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #16 in Math.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#16 in Math"},{"id":"v_pareto_math_claude-opus-4-5_2026-10-14_open_RANKED","model":"claude-opus-4-5","model_name":"Claude Opus 4.5","category":"math","category_name":"Math","slice":"pareto","state":"RANKED","rank":16,"present_evidence":[],"missing_evidence":[],"margin":33.33333333333333,"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":"#16 in Math"},{"id":"v_overall_science_claude-opus-4-5_2026-10-14_open_RANKED","model":"claude-opus-4-5","model_name":"Claude Opus 4.5","category":"science","category_name":"Science","slice":"overall","state":"RANKED","rank":68,"present_evidence":[],"missing_evidence":[],"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Last listed at #68 in Science on 2025-11-24. That board does not award a crown.","safeguard_flags":["off_board"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#68 in Science"},{"id":"v_overall_coding_claude-opus-4-5_2026-10-14_open_INSUFFICIENT_DATA","model":"claude-opus-4-5","model_name":"Claude Opus 4.5","category":"coding","category_name":"Coding","slice":"overall","state":"INSUFFICIENT_DATA","rank":null,"present_evidence":[{"benchmark":"swe-bench-verified","name":"SWE-bench Verified","rank":9}],"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":"#9 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-4-5_2025-12-01_open_WAS_SOTA","model":"claude-opus-4-5","model_name":"Claude Opus 4.5","category":"coding-web-dev","category_name":"Coding › Web dev","slice":"overall","state":"WAS_SOTA","rank":51,"present_evidence":[],"missing_evidence":[],"margin":47.61904761904762,"confidence":"medium","valid_from":"2025-12-01","valid_to":null,"configuration":null,"rationale":"Was SOTA in Coding › Web dev from 2025-12-01 to 2026-02-09. Currently ranked #51.","safeguard_flags":["dethroned"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Was SOTA · Coding › Web dev"},{"id":"v_pareto_coding-web-dev_claude-opus-4-5_2026-10-14_open_RANKED","model":"claude-opus-4-5","model_name":"Claude Opus 4.5","category":"coding-web-dev","category_name":"Coding › Web dev","slice":"pareto","state":"RANKED","rank":58,"present_evidence":[],"missing_evidence":[],"margin":45.6,"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":"#58 in Coding › Web dev"},{"id":"v_overall_long-context_claude-opus-4-5_2026-01-29_open_WAS_SOTA","model":"claude-opus-4-5","model_name":"Claude Opus 4.5","category":"long-context","category_name":"Long context","slice":"overall","state":"WAS_SOTA","rank":18,"present_evidence":[],"missing_evidence":[],"margin":12.41379310344827,"confidence":"medium","valid_from":"2026-01-29","valid_to":null,"configuration":null,"rationale":"Was SOTA in Long context from 2026-01-29 to 2026-02-09. Currently ranked #18.","safeguard_flags":["dethroned"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Was SOTA · Long context"},{"id":"v_pareto_long-context_claude-opus-4-5_2026-10-14_open_RANKED","model":"claude-opus-4-5","model_name":"Claude Opus 4.5","category":"long-context","category_name":"Long context","slice":"pareto","state":"RANKED","rank":20,"present_evidence":[],"missing_evidence":[],"margin":10.63829787234043,"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":"#20 in Long context"},{"id":"v_overall_factuality_claude-opus-4-5_2026-10-14_open_RANKED","model":"claude-opus-4-5","model_name":"Claude Opus 4.5","category":"factuality","category_name":"Factuality","slice":"overall","state":"RANKED","rank":36,"present_evidence":[],"missing_evidence":[],"margin":27.272727272727266,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #36 in Factuality.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#36 in Factuality"},{"id":"v_pareto_factuality_claude-opus-4-5_2026-10-14_open_RANKED","model":"claude-opus-4-5","model_name":"Claude Opus 4.5","category":"factuality","category_name":"Factuality","slice":"pareto","state":"RANKED","rank":40,"present_evidence":[],"missing_evidence":[],"margin":23.837209302325576,"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":"#40 in Factuality"},{"id":"v_overall_arc_claude-opus-4-5_2026-10-14_open_RANKED","model":"claude-opus-4-5","model_name":"Claude Opus 4.5","category":"arc","category_name":"Abstraction (ARC)","slice":"overall","state":"RANKED","rank":49,"present_evidence":[],"missing_evidence":[],"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Last listed at #49 in Abstraction (ARC) on 2025-11-24. That board does not award a crown.","safeguard_flags":["off_board"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#49 in Abstraction (ARC)"}]}