{"id":"deepseek-v2-5","slug":"deepseek-v2-5","name":"DeepSeek V2.5","orgId":"deepseek","family":"deepseek-v2-5","releaseDate":"2024-09-06","availability":"ga","openWeights":true,"license":"DeepSeek","paramsTotal":236000000000,"contextWindow":null,"knowledgeCutoff":null,"modelCardUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","hfRepo":null,"modalities":["text"],"aliases":["deepseek-v2.5","DeepSeek V2.5"],"aliasNote":null,"organization":{"id":"deepseek","name":"DeepSeek","slug":"deepseek","country":null,"url":null,"color":"#4D6BFE","mark":"DS"},"price":null,"answer":{"word":"No.","scope":"#8 on LMArena Text (style-controlled, hard prompts); missing Humanity's Last Exam and GPQA Diamond","lead":"As of Oct 14, 2026, DeepSeek V2.5 from DeepSeek. #8 on LMArena Text (style-controlled, hard prompts); missing Humanity's Last Exam and GPQA Diamond #8 on LMArena Text (style-controlled, hard prompts); missing Humanity's Last Exam and GPQA Diamond","confidence":"low"},"verdicts":[{"id":"v_overall_reasoning_deepseek-v2-5_2026-10-14_open_INSUFFICIENT_DATA","model":"deepseek-v2-5","model_name":"DeepSeek V2.5","category":"reasoning","category_name":"Reasoning","slice":"overall","state":"INSUFFICIENT_DATA","rank":null,"present_evidence":[{"benchmark":"lmarena-text-hard","name":"LMArena Text (style-controlled, hard prompts)","rank":8}],"missing_evidence":[{"benchmark":"hle","name":"Humanity's Last Exam"},{"benchmark":"gpqa-diamond","name":"GPQA Diamond"}],"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"#8 on LMArena Text (style-controlled, hard prompts); missing Humanity's Last Exam and GPQA Diamond","safeguard_flags":["off_board"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Not enough data"},{"id":"v_overall_coding_deepseek-v2-5_2026-10-14_open_INSUFFICIENT_DATA","model":"deepseek-v2-5","model_name":"DeepSeek V2.5","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":9}],"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":"#9 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD","safeguard_flags":["off_board"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Not enough data"}]}