{"id":"deepseek-v3-1-terminus-thinking","slug":"deepseek-v3-1-terminus-thinking","name":"DeepSeek V3.1 Terminus Thinking","orgId":"deepseek","family":"deepseek-v3-1-terminus-thinking","releaseDate":null,"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-v3.1-terminus-thinking","DeepSeek V3.1 Terminus 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 #71 in Long context.","lead":"As of Oct 14, 2026, DeepSeek V3.1 Terminus Thinking from DeepSeek. Best current rank is #71 in Long context. Ranked #71 in Long context.","confidence":"medium"},"verdicts":[{"id":"v_overall_general-llm_deepseek-v3-1-terminus-thinking_2026-10-14_open_RANKED","model":"deepseek-v3-1-terminus-thinking","model_name":"DeepSeek V3.1 Terminus Thinking","category":"general-llm","category_name":"General LLM","slice":"overall","state":"RANKED","rank":96,"present_evidence":[],"missing_evidence":[],"margin":65.51724137931035,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #96 in General LLM.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#96 in General LLM"},{"id":"v_overall_reasoning_deepseek-v3-1-terminus-thinking_2026-10-14_open_RANKED","model":"deepseek-v3-1-terminus-thinking","model_name":"DeepSeek V3.1 Terminus Thinking","category":"reasoning","category_name":"Reasoning","slice":"overall","state":"RANKED","rank":86,"present_evidence":[],"missing_evidence":[],"margin":59.72222222222222,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #86 in Reasoning.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#86 in Reasoning"},{"id":"v_overall_coding_deepseek-v3-1-terminus-thinking_2026-10-14_open_INSUFFICIENT_DATA","model":"deepseek-v3-1-terminus-thinking","model_name":"DeepSeek V3.1 Terminus 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":100}],"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":"#100 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-v3-1-terminus-thinking_2026-10-14_open_RANKED","model":"deepseek-v3-1-terminus-thinking","model_name":"DeepSeek V3.1 Terminus Thinking","category":"long-context","category_name":"Long context","slice":"overall","state":"RANKED","rank":71,"present_evidence":[],"missing_evidence":[],"margin":48.9655172413793,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #71 in Long context.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#71 in Long context"}]}