{"id":"mistral-large-3","slug":"mistral-large-3","name":"Mistral Large 3","orgId":"mistral","family":"mistral-large-3","releaseDate":null,"availability":"ga","openWeights":true,"license":"Apache 2.0","paramsTotal":null,"contextWindow":null,"knowledgeCutoff":null,"modelCardUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","hfRepo":null,"modalities":["text"],"aliases":["mistral-large-3","Mistral Large 3"],"aliasNote":null,"organization":{"id":"mistral","name":"Mistral","slug":"mistral","country":null,"url":null,"color":"#F2A73B","mark":"Mi"},"price":null,"answer":{"word":"No.","scope":"Best current rank is #76 in Factuality.","lead":"As of Oct 14, 2026, Mistral Large 3 from Mistral. Best current rank is #76 in Factuality. Ranked #76 in Factuality.","confidence":"medium"},"verdicts":[{"id":"v_overall_general-llm_mistral-large-3_2026-10-14_open_RANKED","model":"mistral-large-3","model_name":"Mistral Large 3","category":"general-llm","category_name":"General LLM","slice":"overall","state":"RANKED","rank":102,"present_evidence":[],"missing_evidence":[],"margin":69.65517241379311,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #102 in General LLM.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#102 in General LLM"},{"id":"v_overall_reasoning_mistral-large-3_2026-10-14_open_RANKED","model":"mistral-large-3","model_name":"Mistral Large 3","category":"reasoning","category_name":"Reasoning","slice":"overall","state":"RANKED","rank":103,"present_evidence":[],"missing_evidence":[],"margin":71.52777777777777,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #103 in Reasoning.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#103 in Reasoning"},{"id":"v_overall_math_mistral-large-3_2026-10-14_open_INSUFFICIENT_DATA","model":"mistral-large-3","model_name":"Mistral Large 3","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":113}],"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":"#113 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_coding_mistral-large-3_2026-10-14_open_INSUFFICIENT_DATA","model":"mistral-large-3","model_name":"Mistral Large 3","category":"coding","category_name":"Coding","slice":"overall","state":"INSUFFICIENT_DATA","rank":null,"present_evidence":[{"benchmark":"lmarena-text-coding","name":"LMArena Text (style-controlled, coding)","rank":88}],"missing_evidence":[{"benchmark":"terminal-bench-4","name":"Terminal-Bench 4.0"},{"benchmark":"swe-bench-pro-hard","name":"SWE-bench Pro V2 HARD"}],"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"#88 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Not enough data"},{"id":"v_overall_coding-web-dev_mistral-large-3_2026-10-14_open_RANKED","model":"mistral-large-3","model_name":"Mistral Large 3","category":"coding-web-dev","category_name":"Coding › Web dev","slice":"overall","state":"RANKED","rank":102,"present_evidence":[],"missing_evidence":[],"margin":96.19047619047619,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #102 in Coding › Web dev.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#102 in Coding › Web dev"},{"id":"v_overall_long-context_mistral-large-3_2026-10-14_open_RANKED","model":"mistral-large-3","model_name":"Mistral Large 3","category":"long-context","category_name":"Long context","slice":"overall","state":"RANKED","rank":100,"present_evidence":[],"missing_evidence":[],"margin":68.96551724137932,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #100 in Long context.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#100 in Long context"},{"id":"v_overall_vision_mistral-large-3_2026-10-14_open_INSUFFICIENT_DATA","model":"mistral-large-3","model_name":"Mistral Large 3","category":"vision","category_name":"Vision","slice":"overall","state":"INSUFFICIENT_DATA","rank":null,"present_evidence":[{"benchmark":"lmarena-vision","name":"LMArena Vision (style-controlled)","rank":68}],"missing_evidence":[{"benchmark":"gdp-pdf","name":"GDP.pdf"}],"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"#68 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_mistral-large-3_2026-10-14_open_RANKED","model":"mistral-large-3","model_name":"Mistral Large 3","category":"factuality","category_name":"Factuality","slice":"overall","state":"RANKED","rank":76,"present_evidence":[],"missing_evidence":[],"margin":57.57575757575758,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #76 in Factuality.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#76 in Factuality"}]}