{"id":"claude-haiku-4-5","slug":"claude-haiku-4-5","name":"Claude Haiku 4.5","orgId":"anthropic","family":"claude-haiku-4-5","releaseDate":"2025-10-15","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-haiku-4-5-20251001","Claude Haiku 4.5","claude-haiku-4-5-20251001_unknown","Haiku 4.5 (Claude Code) xhigh","anthropic/claude-haiku-4.5","Anthropic: Claude Haiku 4.5"],"aliasNote":null,"organization":{"id":"anthropic","name":"Anthropic","slug":"anthropic","country":null,"url":null,"color":"#D97757","mark":"A"},"price":{"modelId":"claude-haiku-4-5","provider":"anthropic","inputPerM":null,"outputPerM":null,"blendedPerM":2.0000000000000004,"tokensPerS":null,"observedAt":"2026-10-14","sourceId":"openrouter"},"answer":{"word":"No.","scope":"Best recorded rank is #78 in Abstraction (ARC).","lead":"As of Oct 14, 2026, Claude Haiku 4.5 from Anthropic. Best recorded rank is #78 in Abstraction (ARC). Last listed at #78 in Abstraction (ARC) on 2025-10-15. That board does not award a crown.","confidence":"low"},"verdicts":[{"id":"v_overall_general-llm_claude-haiku-4-5_2026-10-14_open_RANKED","model":"claude-haiku-4-5","model_name":"Claude Haiku 4.5","category":"general-llm","category_name":"General LLM","slice":"overall","state":"RANKED","rank":103,"present_evidence":[],"missing_evidence":[],"margin":70.34482758620689,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #103 in General LLM.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#103 in General LLM"},{"id":"v_pareto_general-llm_claude-haiku-4-5_2026-10-14_open_RANKED","model":"claude-haiku-4-5","model_name":"Claude Haiku 4.5","category":"general-llm","category_name":"General LLM","slice":"pareto","state":"RANKED","rank":133,"present_evidence":[],"missing_evidence":[],"margin":70.74468085106383,"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":"#133 in General LLM"},{"id":"v_overall_reasoning_claude-haiku-4-5_2026-10-14_open_RANKED","model":"claude-haiku-4-5","model_name":"Claude Haiku 4.5","category":"reasoning","category_name":"Reasoning","slice":"overall","state":"RANKED","rank":90,"present_evidence":[],"missing_evidence":[],"margin":62.5,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #90 in Reasoning.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#90 in Reasoning"},{"id":"v_pareto_reasoning_claude-haiku-4-5_2026-10-14_open_RANKED","model":"claude-haiku-4-5","model_name":"Claude Haiku 4.5","category":"reasoning","category_name":"Reasoning","slice":"pareto","state":"RANKED","rank":119,"present_evidence":[],"missing_evidence":[],"margin":63.829787234042556,"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":"#119 in Reasoning"},{"id":"v_overall_math_claude-haiku-4-5_2026-10-14_open_INSUFFICIENT_DATA","model":"claude-haiku-4-5","model_name":"Claude Haiku 4.5","category":"math","category_name":"Math","slice":"overall","state":"INSUFFICIENT_DATA","rank":null,"present_evidence":[{"benchmark":"lmarena-text-math","name":"LMArena Text (style-controlled, math)","rank":112}],"missing_evidence":[{"benchmark":"hle","name":"Humanity's Last Exam"},{"benchmark":"frontiermath","name":"FrontierMath"}],"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"#112 on LMArena Text (style-controlled, math); missing Humanity's Last Exam and FrontierMath","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Not enough data"},{"id":"v_overall_science_claude-haiku-4-5_2026-10-14_open_RANKED","model":"claude-haiku-4-5","model_name":"Claude Haiku 4.5","category":"science","category_name":"Science","slice":"overall","state":"RANKED","rank":109,"present_evidence":[],"missing_evidence":[],"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Last listed at #109 in Science on 2025-10-15. That board does not award a crown.","safeguard_flags":["off_board"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#109 in Science"},{"id":"v_overall_coding_claude-haiku-4-5_2026-10-14_open_INSUFFICIENT_DATA","model":"claude-haiku-4-5","model_name":"Claude Haiku 4.5","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":11}],"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":"xhigh","rationale":"#11 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-4-5_2026-10-14_open_RANKED","model":"claude-haiku-4-5","model_name":"Claude Haiku 4.5","category":"coding-web-dev","category_name":"Coding › Web dev","slice":"overall","state":"RANKED","rank":90,"present_evidence":[],"missing_evidence":[],"margin":84.76190476190476,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #90 in Coding › Web dev.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#90 in Coding › Web dev"},{"id":"v_pareto_coding-web-dev_claude-haiku-4-5_2026-10-14_open_RANKED","model":"claude-haiku-4-5","model_name":"Claude Haiku 4.5","category":"coding-web-dev","category_name":"Coding › Web dev","slice":"pareto","state":"RANKED","rank":103,"present_evidence":[],"missing_evidence":[],"margin":81.6,"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":"#103 in Coding › Web dev"},{"id":"v_overall_long-context_claude-haiku-4-5_2026-10-14_open_RANKED","model":"claude-haiku-4-5","model_name":"Claude Haiku 4.5","category":"long-context","category_name":"Long context","slice":"overall","state":"RANKED","rank":83,"present_evidence":[],"missing_evidence":[],"margin":57.241379310344826,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #83 in Long context.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#83 in Long context"},{"id":"v_pareto_long-context_claude-haiku-4-5_2026-10-14_open_RANKED","model":"claude-haiku-4-5","model_name":"Claude Haiku 4.5","category":"long-context","category_name":"Long context","slice":"pareto","state":"RANKED","rank":107,"present_evidence":[],"missing_evidence":[],"margin":56.91489361702128,"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":"#107 in Long context"},{"id":"v_overall_factuality_claude-haiku-4-5_2026-10-14_open_RANKED","model":"claude-haiku-4-5","model_name":"Claude Haiku 4.5","category":"factuality","category_name":"Factuality","slice":"overall","state":"RANKED","rank":96,"present_evidence":[],"missing_evidence":[],"margin":72.72727272727272,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #96 in Factuality.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#96 in Factuality"},{"id":"v_pareto_factuality_claude-haiku-4-5_2026-10-14_open_RANKED","model":"claude-haiku-4-5","model_name":"Claude Haiku 4.5","category":"factuality","category_name":"Factuality","slice":"pareto","state":"RANKED","rank":125,"present_evidence":[],"missing_evidence":[],"margin":73.25581395348837,"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":"#125 in Factuality"},{"id":"v_overall_arc_claude-haiku-4-5_2026-10-14_open_RANKED","model":"claude-haiku-4-5","model_name":"Claude Haiku 4.5","category":"arc","category_name":"Abstraction (ARC)","slice":"overall","state":"RANKED","rank":78,"present_evidence":[],"missing_evidence":[],"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Last listed at #78 in Abstraction (ARC) on 2025-10-15. That board does not award a crown.","safeguard_flags":["off_board"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#78 in Abstraction (ARC)"}]}