{"id":"deepseek-v3-2-exp-thinking","slug":"deepseek-v3-2-exp-thinking","name":"DeepSeek V3.2 Exp Thinking","orgId":"deepseek","family":"deepseek-v3-2-exp-thinking","releaseDate":"2025-09-29","availability":"ga","openWeights":true,"license":"MIT","paramsTotal":null,"contextWindow":null,"knowledgeCutoff":null,"modelCardUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","hfRepo":null,"modalities":["text"],"aliases":["deepseek-v3.2-exp-thinking","DeepSeek V3.2 Exp Thinking","DeepSeek-V3.2-Exp_thinking"],"aliasNote":null,"organization":{"id":"deepseek","name":"DeepSeek","slug":"deepseek","country":null,"url":null,"color":"#4D6BFE","mark":"DS"},"price":null,"answer":{"word":"No.","scope":"Best current rank is #56 in Factuality.","lead":"As of Oct 14, 2026, DeepSeek V3.2 Exp Thinking from DeepSeek. Best current rank is #56 in Factuality. Ranked #56 in Factuality.","confidence":"medium"},"verdicts":[{"id":"v_overall_general-llm_deepseek-v3-2-exp-thinking_2026-10-14_open_RANKED","model":"deepseek-v3-2-exp-thinking","model_name":"DeepSeek V3.2 Exp Thinking","category":"general-llm","category_name":"General LLM","slice":"overall","state":"RANKED","rank":83,"present_evidence":[],"missing_evidence":[],"margin":56.55172413793103,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #83 in General LLM.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#83 in General LLM"},{"id":"v_overall_reasoning_deepseek-v3-2-exp-thinking_2026-10-14_open_RANKED","model":"deepseek-v3-2-exp-thinking","model_name":"DeepSeek V3.2 Exp Thinking","category":"reasoning","category_name":"Reasoning","slice":"overall","state":"RANKED","rank":83,"present_evidence":[],"missing_evidence":[],"margin":57.638888888888886,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #83 in Reasoning.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#83 in Reasoning"},{"id":"v_overall_math_deepseek-v3-2-exp-thinking_2026-10-14_open_INSUFFICIENT_DATA","model":"deepseek-v3-2-exp-thinking","model_name":"DeepSeek V3.2 Exp Thinking","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":85}],"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":"#85 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_deepseek-v3-2-exp-thinking_2026-10-14_open_INSUFFICIENT_DATA","model":"deepseek-v3-2-exp-thinking","model_name":"DeepSeek V3.2 Exp Thinking","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":82}],"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":"#82 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_long-context_deepseek-v3-2-exp-thinking_2026-10-14_open_RANKED","model":"deepseek-v3-2-exp-thinking","model_name":"DeepSeek V3.2 Exp Thinking","category":"long-context","category_name":"Long context","slice":"overall","state":"RANKED","rank":84,"present_evidence":[],"missing_evidence":[],"margin":57.93103448275862,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #84 in Long context.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#84 in Long context"},{"id":"v_overall_factuality_deepseek-v3-2-exp-thinking_2026-10-14_open_RANKED","model":"deepseek-v3-2-exp-thinking","model_name":"DeepSeek V3.2 Exp Thinking","category":"factuality","category_name":"Factuality","slice":"overall","state":"RANKED","rank":56,"present_evidence":[],"missing_evidence":[],"margin":42.42424242424242,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #56 in Factuality.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#56 in Factuality"}]}