{"id":"gemini-2-5-flash-preview-05-20","slug":"gemini-2-5-flash-preview-05-20","name":"Gemini 2.5 Flash Preview 05.20","orgId":"google","family":"gemini-2-5-flash-preview-05-20","releaseDate":"2025-05-20","availability":"ga","openWeights":false,"license":null,"paramsTotal":null,"contextWindow":null,"knowledgeCutoff":null,"modelCardUrl":"https://aider.chat/docs/leaderboards/#polyglot-leaderboard","hfRepo":null,"modalities":["text"],"aliases":["gemini-2.5-flash-preview-05-20_23K","Gemini 2.5 Flash Preview 05.20","gemini-2.5-flash-preview-05-20","gemini-2.5-flash-preview-05-20_16K"],"aliasNote":null,"organization":{"id":"google","name":"Google DeepMind","slug":"google","country":null,"url":null,"color":"#4285F4","mark":"G"},"price":null,"answer":{"word":"No.","scope":"Best current rank is #28 in Math.","lead":"As of Oct 14, 2026, Gemini 2.5 Flash Preview 05.20 from Google DeepMind. Best current rank is #28 in Math. Ranked #28 in Math.","confidence":"medium"},"verdicts":[{"id":"v_overall_reasoning_gemini-2-5-flash-preview-05-20_2026-10-14_open_INSUFFICIENT_DATA","model":"gemini-2-5-flash-preview-05-20","model_name":"Gemini 2.5 Flash Preview 05.20","category":"reasoning","category_name":"Reasoning","slice":"overall","state":"INSUFFICIENT_DATA","rank":null,"present_evidence":[{"benchmark":"hle","name":"Humanity's Last Exam","rank":28}],"missing_evidence":[{"benchmark":"gpqa-diamond","name":"GPQA Diamond"},{"benchmark":"lmarena-text-hard","name":"LMArena Text (style-controlled, hard prompts)"}],"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"#28 on Humanity's Last Exam; missing GPQA Diamond and LMArena Text (style-controlled, hard prompts)","safeguard_flags":["off_board"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Not enough data"},{"id":"v_overall_math_gemini-2-5-flash-preview-05-20_2026-10-14_open_RANKED","model":"gemini-2-5-flash-preview-05-20","model_name":"Gemini 2.5 Flash Preview 05.20","category":"math","category_name":"Math","slice":"overall","state":"RANKED","rank":28,"present_evidence":[],"missing_evidence":[],"margin":60,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #28 in Math.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#28 in Math"},{"id":"v_overall_arc_gemini-2-5-flash-preview-05-20_2026-10-14_open_RANKED","model":"gemini-2-5-flash-preview-05-20","model_name":"Gemini 2.5 Flash Preview 05.20","category":"arc","category_name":"Abstraction (ARC)","slice":"overall","state":"RANKED","rank":52,"present_evidence":[],"missing_evidence":[],"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Last listed at #52 in Abstraction (ARC) on 2025-05-20. That board does not award a crown.","safeguard_flags":["off_board"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#52 in Abstraction (ARC)"}]}