{"id":"claude-haiku-5-5","slug":"claude-haiku-5-5","name":"Claude Haiku 5.5","orgId":"anthropic","family":"claude-haiku-5-5","releaseDate":"2026-10-07","availability":"ga","openWeights":false,"license":"Proprietary","paramsTotal":null,"contextWindow":1000000,"knowledgeCutoff":null,"modelCardUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","hfRepo":null,"modalities":["text","image","file"],"aliases":["claude-haiku-5.5-high","Claude Haiku 5.5","claude-haiku-5-5_max","Haiku 5.5 (mini-swe-agent) high","anthropic/claude-haiku-5.5","Anthropic: Claude Haiku 5.5","claude-haiku-5-5_unknown"],"aliasNote":null,"organization":{"id":"anthropic","name":"Anthropic","slug":"anthropic","country":null,"url":null,"color":"#D97757","mark":"A"},"price":{"modelId":"claude-haiku-5-5","provider":"anthropic","inputPerM":null,"outputPerM":null,"blendedPerM":0.19999999999999998,"tokensPerS":null,"observedAt":"2026-10-14","sourceId":"openrouter"},"answer":{"word":"Too new.","scope":"Too new to call. The crown still needs confirming evidence.","lead":"As of Oct 14, 2026, Claude Haiku 5.5 from Anthropic. Too new to call. The crown still needs confirming evidence. Too new to call Math. The model is recent, and a crown change still needs two confirming signals.","confidence":"low"},"verdicts":[{"id":"v_overall_math_claude-haiku-5-5_2026-10-14_open_PENDING","model":"claude-haiku-5-5","model_name":"Claude Haiku 5.5","category":"math","category_name":"Math","slice":"overall","state":"PENDING","rank":13,"present_evidence":[],"missing_evidence":[],"margin":26.66666666666667,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Too new to call Math. The model is recent, and a crown change still needs two confirming signals.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Pending · Math"},{"id":"v_pareto_math_claude-haiku-5-5_2026-10-14_open_SOTA","model":"claude-haiku-5-5","model_name":"Claude Haiku 5.5","category":"math","category_name":"Math","slice":"pareto","state":"SOTA","rank":13,"present_evidence":[],"missing_evidence":[],"margin":26.66666666666667,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"On the cost-quality frontier for Math: nothing scores better for less than $0.20 per 1M blended tokens.","safeguard_flags":["pareto"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Pareto · Math"},{"id":"v_overall_science_claude-haiku-5-5_2026-10-14_open_PENDING","model":"claude-haiku-5-5","model_name":"Claude Haiku 5.5","category":"science","category_name":"Science","slice":"overall","state":"PENDING","rank":38,"present_evidence":[],"missing_evidence":[],"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":"max","rationale":"Too new to call Science. Ranked #38. That board does not award a crown.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Pending · Science"},{"id":"v_overall_coding_claude-haiku-5-5_2026-10-14_open_INSUFFICIENT_DATA","model":"claude-haiku-5-5","model_name":"Claude Haiku 5.5","category":"coding","category_name":"Coding","slice":"overall","state":"INSUFFICIENT_DATA","rank":null,"present_evidence":[{"benchmark":"swe-bench-pro-hard","name":"SWE-bench Pro V2 HARD","rank":10}],"missing_evidence":[{"benchmark":"terminal-bench-4","name":"Terminal-Bench 4.0"},{"benchmark":"lmarena-text-coding","name":"LMArena Text (style-controlled, coding)"}],"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":"high","rationale":"#10 on SWE-bench Pro V2 HARD; missing Terminal-Bench 4.0 and LMArena Text (style-controlled, coding)","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Not enough data"},{"id":"v_overall_coding-web-dev_claude-haiku-5-5_2026-10-14_open_PENDING","model":"claude-haiku-5-5","model_name":"Claude Haiku 5.5","category":"coding-web-dev","category_name":"Coding › Web dev","slice":"overall","state":"PENDING","rank":25,"present_evidence":[],"missing_evidence":[],"margin":22.85714285714286,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":"high","rationale":"Too new to call Coding › Web dev. The model is recent, and a crown change still needs two confirming signals.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Pending · Coding › Web dev"},{"id":"v_pareto_coding-web-dev_claude-haiku-5-5_2026-10-14_open_RANKED","model":"claude-haiku-5-5","model_name":"Claude Haiku 5.5","category":"coding-web-dev","category_name":"Coding › Web dev","slice":"pareto","state":"RANKED","rank":28,"present_evidence":[],"missing_evidence":[],"margin":21.599999999999994,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":"high","rationale":"Not on the Coding › Web dev cost-quality frontier.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#28 in Coding › Web dev"}]}