{"id":"gpt-5-2","slug":"gpt-5-2","name":"GPT-5.2","orgId":"openai","family":"gpt-5-2","releaseDate":"2025-12-11","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","file","image"],"aliases":["gpt-5.2-high","GPT-5.2","gpt-5.2-2025-12-11_none","gpt-5.2-2025-12-11_xhigh","gpt-5.2-2025-12-11_high","gpt-5.2-2025-12-11_medium","gpt-5.2-2025-12-11_low","gpt-5.2-2025-12-11_unknown","openai/gpt-5.2","OpenAI: GPT-5.2"],"aliasNote":null,"organization":{"id":"openai","name":"OpenAI","slug":"openai","country":null,"url":null,"color":"#10A37F","mark":"O"},"price":{"modelId":"gpt-5-2","provider":"openai","inputPerM":null,"outputPerM":null,"blendedPerM":4.8125,"tokensPerS":null,"observedAt":"2026-10-14","sourceId":"openrouter"},"answer":{"word":"No.","scope":"Best current rank is #12 in Math.","lead":"As of Oct 14, 2026, GPT-5.2 from OpenAI. Best current rank is #12 in Math. Ranked #12 in Math.","confidence":"medium"},"verdicts":[{"id":"v_overall_general-llm_gpt-5-2_2026-10-14_open_RANKED","model":"gpt-5-2","model_name":"GPT-5.2","category":"general-llm","category_name":"General LLM","slice":"overall","state":"RANKED","rank":74,"present_evidence":[],"missing_evidence":[],"margin":50.3448275862069,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":"high","rationale":"Ranked #74 in General LLM.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#74 in General LLM"},{"id":"v_pareto_general-llm_gpt-5-2_2026-10-14_open_RANKED","model":"gpt-5-2","model_name":"GPT-5.2","category":"general-llm","category_name":"General LLM","slice":"pareto","state":"RANKED","rank":92,"present_evidence":[],"missing_evidence":[],"margin":48.93617021276596,"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":"#92 in General LLM"},{"id":"v_overall_reasoning_gpt-5-2_2026-10-14_open_RANKED","model":"gpt-5-2","model_name":"GPT-5.2","category":"reasoning","category_name":"Reasoning","slice":"overall","state":"RANKED","rank":70,"present_evidence":[],"missing_evidence":[],"margin":48.611111111111114,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #70 in Reasoning.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#70 in Reasoning"},{"id":"v_pareto_reasoning_gpt-5-2_2026-10-14_open_RANKED","model":"gpt-5-2","model_name":"GPT-5.2","category":"reasoning","category_name":"Reasoning","slice":"pareto","state":"RANKED","rank":88,"present_evidence":[],"missing_evidence":[],"margin":47.340425531914896,"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":"#88 in Reasoning"},{"id":"v_overall_math_gpt-5-2_2026-10-14_open_RANKED","model":"gpt-5-2","model_name":"GPT-5.2","category":"math","category_name":"Math","slice":"overall","state":"RANKED","rank":12,"present_evidence":[],"missing_evidence":[],"margin":25.581395348837205,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #12 in Math.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#12 in Math"},{"id":"v_pareto_math_gpt-5-2_2026-10-14_open_RANKED","model":"gpt-5-2","model_name":"GPT-5.2","category":"math","category_name":"Math","slice":"pareto","state":"RANKED","rank":12,"present_evidence":[],"missing_evidence":[],"margin":25.581395348837205,"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":"#12 in Math"},{"id":"v_overall_science_gpt-5-2_2026-10-14_open_RANKED","model":"gpt-5-2","model_name":"GPT-5.2","category":"science","category_name":"Science","slice":"overall","state":"RANKED","rank":26,"present_evidence":[],"missing_evidence":[],"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":"xhigh","rationale":"Last listed at #26 in Science on 2025-12-11. That board does not award a crown.","safeguard_flags":["off_board"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#26 in Science"},{"id":"v_overall_coding_gpt-5-2_2026-10-14_open_INSUFFICIENT_DATA","model":"gpt-5-2","model_name":"GPT-5.2","category":"coding","category_name":"Coding","slice":"overall","state":"INSUFFICIENT_DATA","rank":null,"present_evidence":[{"benchmark":"swe-bench-verified","name":"SWE-bench Verified","rank":15}],"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":"high","rationale":"#15 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_gpt-5-2_2026-10-14_open_RANKED","model":"gpt-5-2","model_name":"GPT-5.2","category":"coding-web-dev","category_name":"Coding › Web dev","slice":"overall","state":"RANKED","rank":65,"present_evidence":[],"missing_evidence":[],"margin":60.95238095238095,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #65 in Coding › Web dev.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#65 in Coding › Web dev"},{"id":"v_pareto_coding-web-dev_gpt-5-2_2026-10-14_open_RANKED","model":"gpt-5-2","model_name":"GPT-5.2","category":"coding-web-dev","category_name":"Coding › Web dev","slice":"pareto","state":"RANKED","rank":73,"present_evidence":[],"missing_evidence":[],"margin":57.6,"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":"#73 in Coding › Web dev"},{"id":"v_overall_long-context_gpt-5-2_2026-10-14_open_RANKED","model":"gpt-5-2","model_name":"GPT-5.2","category":"long-context","category_name":"Long context","slice":"overall","state":"RANKED","rank":79,"present_evidence":[],"missing_evidence":[],"margin":54.48275862068966,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #79 in Long context.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#79 in Long context"},{"id":"v_pareto_long-context_gpt-5-2_2026-10-14_open_RANKED","model":"gpt-5-2","model_name":"GPT-5.2","category":"long-context","category_name":"Long context","slice":"pareto","state":"RANKED","rank":100,"present_evidence":[],"missing_evidence":[],"margin":53.19148936170212,"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":"#100 in Long context"},{"id":"v_overall_vision_gpt-5-2_2026-10-14_open_INSUFFICIENT_DATA","model":"gpt-5-2","model_name":"GPT-5.2","category":"vision","category_name":"Vision","slice":"overall","state":"INSUFFICIENT_DATA","rank":null,"present_evidence":[{"benchmark":"lmarena-vision","name":"LMArena Vision (style-controlled)","rank":48}],"missing_evidence":[{"benchmark":"gdp-pdf","name":"GDP.pdf"}],"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":"high","rationale":"#48 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-5-2_2026-10-14_open_RANKED","model":"gpt-5-2","model_name":"GPT-5.2","category":"factuality","category_name":"Factuality","slice":"overall","state":"RANKED","rank":65,"present_evidence":[],"missing_evidence":[],"margin":49.24242424242424,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #65 in Factuality.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#65 in Factuality"},{"id":"v_pareto_factuality_gpt-5-2_2026-10-14_open_RANKED","model":"gpt-5-2","model_name":"GPT-5.2","category":"factuality","category_name":"Factuality","slice":"pareto","state":"RANKED","rank":79,"present_evidence":[],"missing_evidence":[],"margin":46.51162790697674,"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":"#79 in Factuality"},{"id":"v_overall_arc_gpt-5-2_2026-10-14_open_RANKED","model":"gpt-5-2","model_name":"GPT-5.2","category":"arc","category_name":"Abstraction (ARC)","slice":"overall","state":"RANKED","rank":23,"present_evidence":[],"missing_evidence":[],"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":"xhigh","rationale":"Last listed at #23 in Abstraction (ARC) on 2025-12-11. That board does not award a crown.","safeguard_flags":["off_board"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#23 in Abstraction (ARC)"}]}