{"id":"deepseek-v4-pro","slug":"deepseek-v4-pro","name":"DeepSeek V4 Pro","orgId":"deepseek","family":"deepseek-v4-pro","releaseDate":"2026-04-24","availability":"ga","openWeights":true,"license":"MIT","paramsTotal":1600000000000,"contextWindow":1048576,"knowledgeCutoff":null,"modelCardUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","hfRepo":"deepseek-ai/DeepSeek-V4-Pro","modalities":["text"],"aliases":["deepseek-v4-pro","DeepSeek V4 Pro","deepseek-v4-pro_none","deepseek-v4-pro_high","deepseek-v4-pro_max","deepseek/deepseek-v4-pro","DeepSeek: DeepSeek V4 Pro 0423"],"aliasNote":null,"organization":{"id":"deepseek","name":"DeepSeek","slug":"deepseek","country":null,"url":null,"color":"#4D6BFE","mark":"DS"},"price":{"modelId":"deepseek-v4-pro","provider":"deepseek","inputPerM":null,"outputPerM":null,"blendedPerM":1.194075,"tokensPerS":null,"observedAt":"2026-10-14","sourceId":"openrouter"},"answer":{"word":"No.","scope":"Best recorded rank is #28 in Science.","lead":"As of Oct 14, 2026, DeepSeek V4 Pro from DeepSeek. Best recorded rank is #28 in Science. Last listed at #28 in Science on 2026-04-24. That board does not award a crown.","confidence":"low"},"verdicts":[{"id":"v_overall_general-llm_deepseek-v4-pro_2026-10-14_open_RANKED","model":"deepseek-v4-pro","model_name":"DeepSeek V4 Pro","category":"general-llm","category_name":"General LLM","slice":"overall","state":"RANKED","rank":44,"present_evidence":[],"missing_evidence":[],"margin":29.65517241379311,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #44 in General LLM.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#44 in General LLM"},{"id":"v_open-weights_general-llm_deepseek-v4-pro_2026-10-14_open_RANKED","model":"deepseek-v4-pro","model_name":"DeepSeek V4 Pro","category":"general-llm","category_name":"General LLM","slice":"open-weights","state":"RANKED","rank":9,"present_evidence":[],"missing_evidence":[],"margin":14.08450704225352,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #9 in General LLM.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#9 in General LLM"},{"id":"v_pareto_general-llm_deepseek-v4-pro_2026-10-14_open_RANKED","model":"deepseek-v4-pro","model_name":"DeepSeek V4 Pro","category":"general-llm","category_name":"General LLM","slice":"pareto","state":"RANKED","rank":55,"present_evidence":[],"missing_evidence":[],"margin":29.255319148936167,"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":"#55 in General LLM"},{"id":"v_overall_reasoning_deepseek-v4-pro_2026-10-14_open_RANKED","model":"deepseek-v4-pro","model_name":"DeepSeek V4 Pro","category":"reasoning","category_name":"Reasoning","slice":"overall","state":"RANKED","rank":45,"present_evidence":[],"missing_evidence":[],"margin":31.25,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #45 in Reasoning.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#45 in Reasoning"},{"id":"v_open-weights_reasoning_deepseek-v4-pro_2026-10-14_open_RANKED","model":"deepseek-v4-pro","model_name":"DeepSeek V4 Pro","category":"reasoning","category_name":"Reasoning","slice":"open-weights","state":"RANKED","rank":11,"present_evidence":[],"missing_evidence":[],"margin":15.49295774647888,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #11 in Reasoning.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#11 in Reasoning"},{"id":"v_pareto_reasoning_deepseek-v4-pro_2026-10-14_open_RANKED","model":"deepseek-v4-pro","model_name":"DeepSeek V4 Pro","category":"reasoning","category_name":"Reasoning","slice":"pareto","state":"RANKED","rank":57,"present_evidence":[],"missing_evidence":[],"margin":30.851063829787236,"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":"#57 in Reasoning"},{"id":"v_overall_math_deepseek-v4-pro_2026-10-14_open_INSUFFICIENT_DATA","model":"deepseek-v4-pro","model_name":"DeepSeek V4 Pro","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":61}],"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":"#61 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_deepseek-v4-pro_2026-10-14_open_RANKED","model":"deepseek-v4-pro","model_name":"DeepSeek V4 Pro","category":"science","category_name":"Science","slice":"overall","state":"RANKED","rank":28,"present_evidence":[],"missing_evidence":[],"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":"high","rationale":"Last listed at #28 in Science on 2026-04-24. That board does not award a crown.","safeguard_flags":["off_board"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#28 in Science"},{"id":"v_overall_coding_deepseek-v4-pro_2026-10-14_open_INSUFFICIENT_DATA","model":"deepseek-v4-pro","model_name":"DeepSeek V4 Pro","category":"coding","category_name":"Coding","slice":"overall","state":"INSUFFICIENT_DATA","rank":null,"present_evidence":[{"benchmark":"swe-bench-verified","name":"SWE-bench Verified","rank":6}],"missing_evidence":[{"benchmark":"terminal-bench-4","name":"Terminal-Bench 4.0"},{"benchmark":"swe-bench-pro-hard","name":"SWE-bench Pro V2 HARD"},{"benchmark":"lmarena-text-coding","name":"LMArena Text (style-controlled, coding)"}],"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":"max","rationale":"#6 on SWE-bench Verified; missing Terminal-Bench 4.0, SWE-bench Pro V2 HARD, and LMArena Text (style-controlled, coding)","safeguard_flags":["off_board"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Not enough data"},{"id":"v_overall_coding-web-dev_deepseek-v4-pro_2026-10-14_open_RANKED","model":"deepseek-v4-pro","model_name":"DeepSeek V4 Pro","category":"coding-web-dev","category_name":"Coding › Web dev","slice":"overall","state":"RANKED","rank":55,"present_evidence":[],"missing_evidence":[],"margin":51.42857142857143,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #55 in Coding › Web dev.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#55 in Coding › Web dev"},{"id":"v_pareto_coding-web-dev_deepseek-v4-pro_2026-10-14_open_RANKED","model":"deepseek-v4-pro","model_name":"DeepSeek V4 Pro","category":"coding-web-dev","category_name":"Coding › Web dev","slice":"pareto","state":"RANKED","rank":62,"present_evidence":[],"missing_evidence":[],"margin":48.8,"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":"#62 in Coding › Web dev"},{"id":"v_overall_long-context_deepseek-v4-pro_2026-10-14_open_RANKED","model":"deepseek-v4-pro","model_name":"DeepSeek V4 Pro","category":"long-context","category_name":"Long context","slice":"overall","state":"RANKED","rank":42,"present_evidence":[],"missing_evidence":[],"margin":28.965517241379317,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #42 in Long context.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#42 in Long context"},{"id":"v_open-weights_long-context_deepseek-v4-pro_2026-10-14_open_RANKED","model":"deepseek-v4-pro","model_name":"DeepSeek V4 Pro","category":"long-context","category_name":"Long context","slice":"open-weights","state":"RANKED","rank":10,"present_evidence":[],"missing_evidence":[],"margin":14.08450704225352,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #10 in Long context.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#10 in Long context"},{"id":"v_pareto_long-context_deepseek-v4-pro_2026-10-14_open_RANKED","model":"deepseek-v4-pro","model_name":"DeepSeek V4 Pro","category":"long-context","category_name":"Long context","slice":"pareto","state":"RANKED","rank":51,"present_evidence":[],"missing_evidence":[],"margin":27.127659574468083,"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":"#51 in Long context"},{"id":"v_overall_factuality_deepseek-v4-pro_2026-10-14_open_RANKED","model":"deepseek-v4-pro","model_name":"DeepSeek V4 Pro","category":"factuality","category_name":"Factuality","slice":"overall","state":"RANKED","rank":41,"present_evidence":[],"missing_evidence":[],"margin":31.060606060606062,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #41 in Factuality.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#41 in Factuality"},{"id":"v_open-weights_factuality_deepseek-v4-pro_2026-10-14_open_RANKED","model":"deepseek-v4-pro","model_name":"DeepSeek V4 Pro","category":"factuality","category_name":"Factuality","slice":"open-weights","state":"RANKED","rank":9,"present_evidence":[],"missing_evidence":[],"margin":12.857142857142875,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #9 in Factuality.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#9 in Factuality"},{"id":"v_pareto_factuality_deepseek-v4-pro_2026-10-14_open_RANKED","model":"deepseek-v4-pro","model_name":"DeepSeek V4 Pro","category":"factuality","category_name":"Factuality","slice":"pareto","state":"RANKED","rank":49,"present_evidence":[],"missing_evidence":[],"margin":29.069767441860463,"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":"#49 in Factuality"}]}