{"id":"trinity-large-thinking","slug":"trinity-large-thinking","name":"Trinity Large Thinking","orgId":"unknown","family":"trinity-large-thinking","releaseDate":null,"availability":"ga","openWeights":true,"license":"Apache 2.0","paramsTotal":null,"contextWindow":262144,"knowledgeCutoff":null,"modelCardUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","hfRepo":"arcee-ai/Trinity-Large-Thinking","modalities":["text"],"aliases":["trinity-large-thinking","Trinity Large Thinking","arcee-ai/trinity-large-thinking","Arcee AI: Trinity Large Thinking"],"aliasNote":null,"organization":{"id":"unknown","name":"Unknown","slug":"unknown","country":null,"url":null,"color":"#A39E8F","mark":"UN"},"price":{"modelId":"trinity-large-thinking","provider":"arcee-ai","inputPerM":null,"outputPerM":null,"blendedPerM":0.3875,"tokensPerS":null,"observedAt":"2026-10-14","sourceId":"openrouter"},"answer":{"word":"No.","scope":"Best current rank is #101 in Coding › Web dev.","lead":"As of Oct 14, 2026, Trinity Large Thinking from Unknown. Best current rank is #101 in Coding › Web dev. Ranked #101 in Coding › Web dev.","confidence":"medium"},"verdicts":[{"id":"v_overall_general-llm_trinity-large-thinking_2026-10-14_open_RANKED","model":"trinity-large-thinking","model_name":"Trinity Large Thinking","category":"general-llm","category_name":"General LLM","slice":"overall","state":"RANKED","rank":144,"present_evidence":[],"missing_evidence":[],"margin":98.62068965517241,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #144 in General LLM.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#144 in General LLM"},{"id":"v_pareto_general-llm_trinity-large-thinking_2026-10-14_open_RANKED","model":"trinity-large-thinking","model_name":"Trinity Large Thinking","category":"general-llm","category_name":"General LLM","slice":"pareto","state":"RANKED","rank":186,"present_evidence":[],"missing_evidence":[],"margin":98.93617021276596,"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":"#186 in General LLM"},{"id":"v_overall_reasoning_trinity-large-thinking_2026-10-14_open_RANKED","model":"trinity-large-thinking","model_name":"Trinity Large Thinking","category":"reasoning","category_name":"Reasoning","slice":"overall","state":"RANKED","rank":141,"present_evidence":[],"missing_evidence":[],"margin":97.91666666666667,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #141 in Reasoning.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#141 in Reasoning"},{"id":"v_pareto_reasoning_trinity-large-thinking_2026-10-14_open_RANKED","model":"trinity-large-thinking","model_name":"Trinity Large Thinking","category":"reasoning","category_name":"Reasoning","slice":"pareto","state":"RANKED","rank":184,"present_evidence":[],"missing_evidence":[],"margin":98.40425531914893,"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":"#184 in Reasoning"},{"id":"v_overall_math_trinity-large-thinking_2026-10-14_open_INSUFFICIENT_DATA","model":"trinity-large-thinking","model_name":"Trinity Large 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":128}],"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":"#128 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_trinity-large-thinking_2026-10-14_open_INSUFFICIENT_DATA","model":"trinity-large-thinking","model_name":"Trinity Large 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":146}],"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":"#146 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_trinity-large-thinking_2026-10-14_open_RANKED","model":"trinity-large-thinking","model_name":"Trinity Large Thinking","category":"coding-web-dev","category_name":"Coding › Web dev","slice":"overall","state":"RANKED","rank":101,"present_evidence":[],"missing_evidence":[],"margin":95.23809523809524,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #101 in Coding › Web dev.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#101 in Coding › Web dev"},{"id":"v_pareto_coding-web-dev_trinity-large-thinking_2026-10-14_open_RANKED","model":"trinity-large-thinking","model_name":"Trinity Large Thinking","category":"coding-web-dev","category_name":"Coding › Web dev","slice":"pareto","state":"RANKED","rank":117,"present_evidence":[],"missing_evidence":[],"margin":92.8,"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":"#117 in Coding › Web dev"},{"id":"v_overall_factuality_trinity-large-thinking_2026-10-14_open_RANKED","model":"trinity-large-thinking","model_name":"Trinity Large Thinking","category":"factuality","category_name":"Factuality","slice":"overall","state":"RANKED","rank":118,"present_evidence":[],"missing_evidence":[],"margin":89.39393939393939,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #118 in Factuality.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#118 in Factuality"},{"id":"v_pareto_factuality_trinity-large-thinking_2026-10-14_open_RANKED","model":"trinity-large-thinking","model_name":"Trinity Large Thinking","category":"factuality","category_name":"Factuality","slice":"pareto","state":"RANKED","rank":156,"present_evidence":[],"missing_evidence":[],"margin":91.27906976744185,"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":"#156 in Factuality"}]}