{"id":"o3","slug":"o3","name":"O3","orgId":"openai","family":"o3","releaseDate":"2024-12-20","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":["o3-2025-04-16","O3","o3-2025-04-16_medium","o3-2025-04-16_low","o3-2025-04-16_high","o3-2025-04-16_unknown","openai/o3","OpenAI: o3"],"aliasNote":null,"organization":{"id":"openai","name":"OpenAI","slug":"openai","country":null,"url":null,"color":"#10A37F","mark":"O"},"price":{"modelId":"o3","provider":"openai","inputPerM":null,"outputPerM":null,"blendedPerM":3.5,"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, O3 from OpenAI. Was SOTA in General LLM. Was SOTA in Math from 2025-09-29 to 2025-11-13. Currently ranked #18.","confidence":"medium"},"verdicts":[{"id":"v_overall_general-llm_o3_2025-07-28_open_WAS_SOTA","model":"o3","model_name":"O3","category":"general-llm","category_name":"General LLM","slice":"overall","state":"WAS_SOTA","rank":78,"margin":53.10344827586207,"confidence":"medium","valid_from":"2025-07-28","valid_to":null,"configuration":null,"rationale":"Was SOTA in General LLM from 2025-07-28 to 2025-08-18. Currently ranked #78.","safeguard_flags":["dethroned"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Was SOTA · General LLM"},{"id":"v_pareto_general-llm_o3_2026-10-14_open_NOT_SOTA","model":"o3","model_name":"O3","category":"general-llm","category_name":"General LLM","slice":"pareto","state":"NOT_SOTA","rank":100,"margin":52.659574468085104,"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":"Not SOTA · #100"},{"id":"v_overall_reasoning_o3_2025-08-04_open_WAS_SOTA","model":"o3","model_name":"O3","category":"reasoning","category_name":"Reasoning","slice":"overall","state":"WAS_SOTA","rank":90,"margin":61.37931034482759,"confidence":"medium","valid_from":"2025-08-04","valid_to":null,"configuration":null,"rationale":"Was SOTA in Reasoning from 2025-08-04 to 2025-08-18. Currently ranked #90.","safeguard_flags":["dethroned"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Was SOTA · Reasoning"},{"id":"v_pareto_reasoning_o3_2026-10-14_open_NOT_SOTA","model":"o3","model_name":"O3","category":"reasoning","category_name":"Reasoning","slice":"pareto","state":"NOT_SOTA","rank":118,"margin":62.234042553191486,"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":"Not SOTA · #118"},{"id":"v_overall_math_o3_2025-09-29_open_WAS_SOTA","model":"o3","model_name":"O3","category":"math","category_name":"Math","slice":"overall","state":"WAS_SOTA","rank":18,"margin":39.53488372093023,"confidence":"medium","valid_from":"2025-09-29","valid_to":null,"configuration":"high","rationale":"Was SOTA in Math from 2025-09-29 to 2025-11-13. Currently ranked #18.","safeguard_flags":["dethroned"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Was SOTA · Math"},{"id":"v_pareto_math_o3_2026-10-14_open_NOT_SOTA","model":"o3","model_name":"O3","category":"math","category_name":"Math","slice":"pareto","state":"NOT_SOTA","rank":18,"margin":39.53488372093023,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":"high","rationale":"Not on the Math cost-quality frontier.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Not SOTA · #18"},{"id":"v_overall_science_o3_2026-10-14_open_NOT_SOTA","model":"o3","model_name":"O3","category":"science","category_name":"Science","slice":"overall","state":"NOT_SOTA","rank":84,"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":"high","rationale":"Last listed at #84 in Science on 2025-04-16. That board does not award a crown.","safeguard_flags":["off_board"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Not SOTA · #84"},{"id":"v_overall_coding_o3_2026-10-14_open_NOT_SOTA","model":"o3","model_name":"O3","category":"coding","category_name":"Coding","slice":"overall","state":"NOT_SOTA","rank":27,"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":"medium","rationale":"Last listed at #27 in Coding on 2025-04-16.","safeguard_flags":["off_board"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Not SOTA · #27"},{"id":"v_overall_long-context_o3_2025-07-28_open_WAS_SOTA","model":"o3","model_name":"O3","category":"long-context","category_name":"Long context","slice":"overall","state":"WAS_SOTA","rank":109,"margin":73.97260273972603,"confidence":"medium","valid_from":"2025-07-28","valid_to":null,"configuration":null,"rationale":"Was SOTA in Long context from 2025-07-28 to 2025-08-18. Currently ranked #109.","safeguard_flags":["dethroned"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Was SOTA · Long context"},{"id":"v_pareto_long-context_o3_2026-10-14_open_NOT_SOTA","model":"o3","model_name":"O3","category":"long-context","category_name":"Long context","slice":"pareto","state":"NOT_SOTA","rank":145,"margin":76.59574468085106,"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":"Not SOTA · #145"},{"id":"v_overall_vision_o3_2026-10-14_open_NOT_SOTA","model":"o3","model_name":"O3","category":"vision","category_name":"Vision","slice":"overall","state":"NOT_SOTA","rank":59,"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #59 in Vision.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Not SOTA · #59"},{"id":"v_overall_factuality_o3_2026-10-14_open_NOT_SOTA","model":"o3","model_name":"O3","category":"factuality","category_name":"Factuality","slice":"overall","state":"NOT_SOTA","rank":105,"margin":78.78787878787878,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #105 in Factuality.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Not SOTA · #105"},{"id":"v_pareto_factuality_o3_2026-10-14_open_NOT_SOTA","model":"o3","model_name":"O3","category":"factuality","category_name":"Factuality","slice":"pareto","state":"NOT_SOTA","rank":140,"margin":81.28654970760235,"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":"Not SOTA · #140"},{"id":"v_overall_arc_o3_2026-10-14_open_NOT_SOTA","model":"o3","model_name":"O3","category":"arc","category_name":"Abstraction (ARC)","slice":"overall","state":"NOT_SOTA","rank":50,"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":"high","rationale":"Last listed at #50 in Abstraction (ARC) on 2025-04-16. That board does not award a crown.","safeguard_flags":["off_board"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Not SOTA · #50"}]}