{"id":"gpt-5-mini","slug":"gpt-5-mini","name":"GPT-5 Mini","orgId":"openai","family":"gpt-5-mini","releaseDate":"2025-08-07","availability":"ga","openWeights":false,"license":"Proprietary","paramsTotal":null,"contextWindow":400000,"knowledgeCutoff":null,"modelCardUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","hfRepo":null,"modalities":["text","image","file"],"aliases":["gpt-5-mini-high","GPT-5 Mini","gpt-5-mini-2025-08-07_minimal","gpt-5-mini-2025-08-07_high","gpt-5-mini-2025-08-07_medium","gpt-5-mini-2025-08-07_unknown","gpt-5-mini-2025-08-07_low","openai/gpt-5-mini","OpenAI: GPT-5 Mini"],"aliasNote":null,"organization":{"id":"openai","name":"OpenAI","slug":"openai","country":null,"url":null,"color":"#10A37F","mark":"O"},"price":{"modelId":"gpt-5-mini","provider":"openai","inputPerM":null,"outputPerM":null,"blendedPerM":0.6875,"tokensPerS":null,"observedAt":"2026-10-14","sourceId":"openrouter"},"answer":{"word":"It used to be.","scope":"Was SOTA in Math.","lead":"As of Oct 14, 2026, GPT-5 Mini from OpenAI. Was SOTA in Math. Was SOTA in Math from 2025-09-29 to 2025-11-13. Currently ranked #21.","confidence":"medium"},"verdicts":[{"id":"v_overall_general-llm_gpt-5-mini_2026-10-14_open_RANKED","model":"gpt-5-mini","model_name":"GPT-5 Mini","category":"general-llm","category_name":"General LLM","slice":"overall","state":"RANKED","rank":127,"present_evidence":[],"missing_evidence":[],"margin":86.89655172413794,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":"high","rationale":"Ranked #127 in General LLM.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#127 in General LLM"},{"id":"v_pareto_general-llm_gpt-5-mini_2026-10-14_open_RANKED","model":"gpt-5-mini","model_name":"GPT-5 Mini","category":"general-llm","category_name":"General LLM","slice":"pareto","state":"RANKED","rank":165,"present_evidence":[],"missing_evidence":[],"margin":87.76595744680851,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":"high","rationale":"Not on the General LLM cost-quality frontier.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#165 in General LLM"},{"id":"v_overall_reasoning_gpt-5-mini_2026-10-14_open_RANKED","model":"gpt-5-mini","model_name":"GPT-5 Mini","category":"reasoning","category_name":"Reasoning","slice":"overall","state":"RANKED","rank":129,"present_evidence":[],"missing_evidence":[],"margin":89.58333333333333,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":"high","rationale":"Ranked #129 in Reasoning.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#129 in Reasoning"},{"id":"v_pareto_reasoning_gpt-5-mini_2026-10-14_open_RANKED","model":"gpt-5-mini","model_name":"GPT-5 Mini","category":"reasoning","category_name":"Reasoning","slice":"pareto","state":"RANKED","rank":169,"present_evidence":[],"missing_evidence":[],"margin":90.42553191489361,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":"high","rationale":"Not on the Reasoning cost-quality frontier.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#169 in Reasoning"},{"id":"v_overall_math_gpt-5-mini_2025-09-29_open_WAS_SOTA","model":"gpt-5-mini","model_name":"GPT-5 Mini","category":"math","category_name":"Math","slice":"overall","state":"WAS_SOTA","rank":21,"present_evidence":[],"missing_evidence":[],"margin":44.44444444444444,"confidence":"medium","valid_from":"2025-09-29","valid_to":null,"configuration":null,"rationale":"Was SOTA in Math from 2025-09-29 to 2025-11-13. Currently ranked #21.","safeguard_flags":["dethroned"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Was SOTA · Math"},{"id":"v_pareto_math_gpt-5-mini_2026-10-14_open_RANKED","model":"gpt-5-mini","model_name":"GPT-5 Mini","category":"math","category_name":"Math","slice":"pareto","state":"RANKED","rank":21,"present_evidence":[],"missing_evidence":[],"margin":44.44444444444444,"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":"#21 in Math"},{"id":"v_overall_science_gpt-5-mini_2026-10-14_open_RANKED","model":"gpt-5-mini","model_name":"GPT-5 Mini","category":"science","category_name":"Science","slice":"overall","state":"RANKED","rank":81,"present_evidence":[],"missing_evidence":[],"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":"high","rationale":"Last listed at #81 in Science on 2025-08-07. That board does not award a crown.","safeguard_flags":["off_board"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#81 in Science"},{"id":"v_overall_coding_gpt-5-mini_2026-10-14_open_INSUFFICIENT_DATA","model":"gpt-5-mini","model_name":"GPT-5 Mini","category":"coding","category_name":"Coding","slice":"overall","state":"INSUFFICIENT_DATA","rank":null,"present_evidence":[{"benchmark":"swe-bench-verified","name":"SWE-bench Verified","rank":23}],"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":"medium","rationale":"#23 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_long-context_gpt-5-mini_2026-10-14_open_RANKED","model":"gpt-5-mini","model_name":"GPT-5 Mini","category":"long-context","category_name":"Long context","slice":"overall","state":"RANKED","rank":144,"present_evidence":[],"missing_evidence":[],"margin":99.3103448275862,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":"high","rationale":"Ranked #144 in Long context.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#144 in Long context"},{"id":"v_pareto_long-context_gpt-5-mini_2026-10-14_open_RANKED","model":"gpt-5-mini","model_name":"GPT-5 Mini","category":"long-context","category_name":"Long context","slice":"pareto","state":"RANKED","rank":187,"present_evidence":[],"missing_evidence":[],"margin":99.46808510638297,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":"high","rationale":"Not on the Long context cost-quality frontier.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#187 in Long context"},{"id":"v_overall_vision_gpt-5-mini_2026-10-14_open_INSUFFICIENT_DATA","model":"gpt-5-mini","model_name":"GPT-5 Mini","category":"vision","category_name":"Vision","slice":"overall","state":"INSUFFICIENT_DATA","rank":null,"present_evidence":[{"benchmark":"lmarena-vision","name":"LMArena Vision (style-controlled)","rank":76}],"missing_evidence":[{"benchmark":"gdp-pdf","name":"GDP.pdf"}],"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":"high","rationale":"#76 on LMArena Vision (style-controlled); missing GDP.pdf","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Not enough data"},{"id":"v_overall_factuality_gpt-5-mini_2026-10-14_open_RANKED","model":"gpt-5-mini","model_name":"GPT-5 Mini","category":"factuality","category_name":"Factuality","slice":"overall","state":"RANKED","rank":109,"present_evidence":[],"missing_evidence":[],"margin":82.57575757575758,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":"high","rationale":"Ranked #109 in Factuality.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#109 in Factuality"},{"id":"v_pareto_factuality_gpt-5-mini_2026-10-14_open_RANKED","model":"gpt-5-mini","model_name":"GPT-5 Mini","category":"factuality","category_name":"Factuality","slice":"pareto","state":"RANKED","rank":146,"present_evidence":[],"missing_evidence":[],"margin":85.46511627906978,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":"high","rationale":"Not on the Factuality cost-quality frontier.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#146 in Factuality"},{"id":"v_overall_arc_gpt-5-mini_2026-10-14_open_RANKED","model":"gpt-5-mini","model_name":"GPT-5 Mini","category":"arc","category_name":"Abstraction (ARC)","slice":"overall","state":"RANKED","rank":41,"present_evidence":[],"missing_evidence":[],"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":"high","rationale":"Last listed at #41 in Abstraction (ARC) on 2025-08-07. That board does not award a crown.","safeguard_flags":["off_board"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#41 in Abstraction (ARC)"}]}