{"id":"grok-3-mini-beta","slug":"grok-3-mini-beta","name":"Grok 3 Mini Beta","orgId":"xai","family":"grok-3-mini-beta","releaseDate":"2025-04-09","availability":"ga","openWeights":false,"license":"Proprietary","paramsTotal":null,"contextWindow":null,"knowledgeCutoff":null,"modelCardUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","hfRepo":null,"modalities":["text"],"aliases":["grok-3-mini-beta","Grok 3 Mini Beta","grok-3-mini-beta_high","grok-3-mini-beta_low","grok-3-mini-beta_medium"],"aliasNote":null,"organization":{"id":"xai","name":"xAI","slug":"xai","country":null,"url":null,"color":"#111111","mark":"x"},"price":null,"answer":{"word":"No.","scope":"Best recorded rank is #75 in Abstraction (ARC).","lead":"As of Oct 14, 2026, Grok 3 Mini Beta from xAI. Best recorded rank is #75 in Abstraction (ARC). Last listed at #75 in Abstraction (ARC) on 2025-04-09. That board does not award a crown.","confidence":"low"},"verdicts":[{"id":"v_overall_reasoning_grok-3-mini-beta_2026-10-14_open_INSUFFICIENT_DATA","model":"grok-3-mini-beta","model_name":"Grok 3 Mini Beta","category":"reasoning","category_name":"Reasoning","slice":"overall","state":"INSUFFICIENT_DATA","rank":null,"present_evidence":[{"benchmark":"gpqa-diamond","name":"GPQA Diamond","rank":79}],"missing_evidence":[{"benchmark":"hle","name":"Humanity's Last Exam"},{"benchmark":"lmarena-text-hard","name":"LMArena Text (style-controlled, hard prompts)"}],"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":"low","rationale":"#79 on GPQA Diamond; missing Humanity's Last Exam 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_grok-3-mini-beta_2026-10-14_open_INSUFFICIENT_DATA","model":"grok-3-mini-beta","model_name":"Grok 3 Mini Beta","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":137}],"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":"#137 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_grok-3-mini-beta_2026-10-14_open_RANKED","model":"grok-3-mini-beta","model_name":"Grok 3 Mini Beta","category":"science","category_name":"Science","slice":"overall","state":"RANKED","rank":79,"present_evidence":[],"missing_evidence":[],"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":"low","rationale":"Last listed at #79 in Science on 2025-04-09. That board does not award a crown.","safeguard_flags":["off_board"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#79 in Science"},{"id":"v_overall_arc_grok-3-mini-beta_2026-10-14_open_RANKED","model":"grok-3-mini-beta","model_name":"Grok 3 Mini Beta","category":"arc","category_name":"Abstraction (ARC)","slice":"overall","state":"RANKED","rank":75,"present_evidence":[],"missing_evidence":[],"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":"low","rationale":"Last listed at #75 in Abstraction (ARC) on 2025-04-09. That board does not award a crown.","safeguard_flags":["off_board"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#75 in Abstraction (ARC)"}]}