{"id":"llama-4-maverick-17b-128e-instruct","slug":"llama-4-maverick-17b-128e-instruct","name":"Llama 4 Maverick 17B 128e Instruct","orgId":"meta","family":"llama-4-maverick-17b-128e-instruct","releaseDate":"2025-04-05","availability":"ga","openWeights":true,"license":"Llama 4","paramsTotal":17000000000,"contextWindow":null,"knowledgeCutoff":null,"modelCardUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","hfRepo":null,"modalities":["text"],"aliases":["llama-4-maverick-17b-128e-instruct","Llama 4 Maverick 17B 128e Instruct"],"aliasNote":null,"organization":{"id":"meta","name":"Meta","slug":"meta","country":null,"url":null,"color":"#7B61FF","mark":"M"},"price":null,"answer":{"word":"It used to be.","scope":"Was SOTA in Math.","lead":"As of Oct 14, 2026, Llama 4 Maverick 17B 128e Instruct from Meta. Was SOTA in Math. Ranked #35 in Math.","confidence":"medium"},"verdicts":[{"id":"v_overall_reasoning_llama-4-maverick-17b-128e-instruct_2026-10-14_open_INSUFFICIENT_DATA","model":"llama-4-maverick-17b-128e-instruct","model_name":"Llama 4 Maverick 17B 128e Instruct","category":"reasoning","category_name":"Reasoning","slice":"overall","state":"INSUFFICIENT_DATA","rank":null,"present_evidence":[{"benchmark":"hle","name":"Humanity's Last Exam","rank":35}],"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":"#35 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_llama-4-maverick-17b-128e-instruct_2026-10-14_open_RANKED","model":"llama-4-maverick-17b-128e-instruct","model_name":"Llama 4 Maverick 17B 128e Instruct","category":"math","category_name":"Math","slice":"overall","state":"RANKED","rank":35,"present_evidence":[],"missing_evidence":[],"margin":81.3953488372093,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #35 in Math.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#35 in Math"},{"id":"v_open-weights_math_llama-4-maverick-17b-128e-instruct_2025-04-05_open_WAS_SOTA","model":"llama-4-maverick-17b-128e-instruct","model_name":"Llama 4 Maverick 17B 128e Instruct","category":"math","category_name":"Math","slice":"open-weights","state":"WAS_SOTA","rank":null,"present_evidence":[],"missing_evidence":[],"margin":null,"confidence":"medium","valid_from":"2025-04-05","valid_to":null,"configuration":null,"rationale":"Was SOTA in Math from 2025-04-05 to 2026-10-14.","safeguard_flags":["dethroned"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Was SOTA · Math"},{"id":"v_le-32b_math_llama-4-maverick-17b-128e-instruct_2025-04-05_open_WAS_SOTA","model":"llama-4-maverick-17b-128e-instruct","model_name":"Llama 4 Maverick 17B 128e Instruct","category":"math","category_name":"Math","slice":"le-32b","state":"WAS_SOTA","rank":null,"present_evidence":[],"missing_evidence":[],"margin":null,"confidence":"medium","valid_from":"2025-04-05","valid_to":null,"configuration":null,"rationale":"Was SOTA in Math from 2025-04-05 to 2026-10-14.","safeguard_flags":["dethroned"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Was SOTA · Math"},{"id":"v_overall_vision_llama-4-maverick-17b-128e-instruct_2026-10-14_open_INSUFFICIENT_DATA","model":"llama-4-maverick-17b-128e-instruct","model_name":"Llama 4 Maverick 17B 128e Instruct","category":"vision","category_name":"Vision","slice":"overall","state":"INSUFFICIENT_DATA","rank":null,"present_evidence":[{"benchmark":"lmarena-vision","name":"LMArena Vision (style-controlled)","rank":87}],"missing_evidence":[{"benchmark":"gdp-pdf","name":"GDP.pdf"}],"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"#87 on LMArena Vision (style-controlled); missing GDP.pdf","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Not enough data"},{"id":"v_overall_arc_llama-4-maverick-17b-128e-instruct_2026-10-14_open_RANKED","model":"llama-4-maverick-17b-128e-instruct","model_name":"Llama 4 Maverick 17B 128e Instruct","category":"arc","category_name":"Abstraction (ARC)","slice":"overall","state":"RANKED","rank":87,"present_evidence":[],"missing_evidence":[],"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Last listed at #87 in Abstraction (ARC) on 2025-04-05. That board does not award a crown.","safeguard_flags":["off_board"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#87 in Abstraction (ARC)"}]}