{"id":"deepseek-v3-2","slug":"deepseek-v3-2","name":"DeepSeek V3.2","orgId":"deepseek","family":"deepseek-v3-2","releaseDate":null,"availability":"ga","openWeights":true,"license":"MIT","paramsTotal":null,"contextWindow":163840,"knowledgeCutoff":null,"modelCardUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","hfRepo":"deepseek-ai/DeepSeek-V3.2","modalities":["text"],"aliases":["deepseek-v3.2","DeepSeek V3.2","deepseek/deepseek-v3.2","DeepSeek: DeepSeek V3.2"],"aliasNote":null,"organization":{"id":"deepseek","name":"DeepSeek","slug":"deepseek","country":null,"url":null,"color":"#4D6BFE","mark":"DS"},"price":{"modelId":"deepseek-v3-2","provider":"deepseek","inputPerM":null,"outputPerM":null,"blendedPerM":0.39425,"tokensPerS":null,"observedAt":"2026-10-14","sourceId":"openrouter"},"answer":{"word":"No.","scope":"Best current rank is #71 in Factuality.","lead":"As of Oct 14, 2026, DeepSeek V3.2 from DeepSeek. Best current rank is #71 in Factuality. Ranked #71 in Factuality.","confidence":"medium"},"verdicts":[{"id":"v_overall_general-llm_deepseek-v3-2_2026-10-14_open_RANKED","model":"deepseek-v3-2","model_name":"DeepSeek V3.2","category":"general-llm","category_name":"General LLM","slice":"overall","state":"RANKED","rank":84,"present_evidence":[],"missing_evidence":[],"margin":57.241379310344826,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #84 in General LLM.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#84 in General LLM"},{"id":"v_pareto_general-llm_deepseek-v3-2_2026-10-14_open_RANKED","model":"deepseek-v3-2","model_name":"DeepSeek V3.2","category":"general-llm","category_name":"General LLM","slice":"pareto","state":"RANKED","rank":112,"present_evidence":[],"missing_evidence":[],"margin":59.57446808510638,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Not on the General LLM cost-quality frontier.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#112 in General LLM"},{"id":"v_overall_reasoning_deepseek-v3-2_2026-10-14_open_RANKED","model":"deepseek-v3-2","model_name":"DeepSeek V3.2","category":"reasoning","category_name":"Reasoning","slice":"overall","state":"RANKED","rank":78,"present_evidence":[],"missing_evidence":[],"margin":54.166666666666664,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #78 in Reasoning.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#78 in Reasoning"},{"id":"v_pareto_reasoning_deepseek-v3-2_2026-10-14_open_RANKED","model":"deepseek-v3-2","model_name":"DeepSeek V3.2","category":"reasoning","category_name":"Reasoning","slice":"pareto","state":"RANKED","rank":104,"present_evidence":[],"missing_evidence":[],"margin":55.851063829787236,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Not on the Reasoning cost-quality frontier.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#104 in Reasoning"},{"id":"v_overall_math_deepseek-v3-2_2026-10-14_open_INSUFFICIENT_DATA","model":"deepseek-v3-2","model_name":"DeepSeek V3.2","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":79}],"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":"#79 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_2026-10-14_open_INSUFFICIENT_DATA","model":"deepseek-v3-2","model_name":"DeepSeek V3.2","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":90}],"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":"#90 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_deepseek-v3-2_2026-10-14_open_RANKED","model":"deepseek-v3-2","model_name":"DeepSeek V3.2","category":"coding-web-dev","category_name":"Coding › Web dev","slice":"overall","state":"RANKED","rank":91,"present_evidence":[],"missing_evidence":[],"margin":85.71428571428571,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #91 in Coding › Web dev.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#91 in Coding › Web dev"},{"id":"v_pareto_coding-web-dev_deepseek-v3-2_2026-10-14_open_RANKED","model":"deepseek-v3-2","model_name":"DeepSeek V3.2","category":"coding-web-dev","category_name":"Coding › Web dev","slice":"pareto","state":"RANKED","rank":104,"present_evidence":[],"missing_evidence":[],"margin":82.4,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Not on the Coding › Web dev cost-quality frontier.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#104 in Coding › Web dev"},{"id":"v_overall_long-context_deepseek-v3-2_2026-10-14_open_RANKED","model":"deepseek-v3-2","model_name":"DeepSeek V3.2","category":"long-context","category_name":"Long context","slice":"overall","state":"RANKED","rank":81,"present_evidence":[],"missing_evidence":[],"margin":55.86206896551724,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #81 in Long context.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#81 in Long context"},{"id":"v_pareto_long-context_deepseek-v3-2_2026-10-14_open_RANKED","model":"deepseek-v3-2","model_name":"DeepSeek V3.2","category":"long-context","category_name":"Long context","slice":"pareto","state":"RANKED","rank":102,"present_evidence":[],"missing_evidence":[],"margin":54.25531914893618,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Not on the Long context cost-quality frontier.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#102 in Long context"},{"id":"v_overall_factuality_deepseek-v3-2_2026-10-14_open_RANKED","model":"deepseek-v3-2","model_name":"DeepSeek V3.2","category":"factuality","category_name":"Factuality","slice":"overall","state":"RANKED","rank":71,"present_evidence":[],"missing_evidence":[],"margin":53.78787878787879,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #71 in Factuality.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#71 in Factuality"},{"id":"v_pareto_factuality_deepseek-v3-2_2026-10-14_open_RANKED","model":"deepseek-v3-2","model_name":"DeepSeek V3.2","category":"factuality","category_name":"Factuality","slice":"pareto","state":"RANKED","rank":89,"present_evidence":[],"missing_evidence":[],"margin":52.325581395348834,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Not on the Factuality cost-quality frontier.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#89 in Factuality"}]}