{"id":"hy3","slug":"hy3","name":"Hy3","orgId":"tencent","family":"hy3","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":"tencent/Hy3","modalities":["text"],"aliases":["hy3","tencent/hy3","Tencent: Hy3"],"aliasNote":null,"organization":{"id":"tencent","name":"tencent","slug":"tencent","country":null,"url":null,"color":"#A39E8F","mark":"TE"},"price":{"modelId":"hy3","provider":"tencent","inputPerM":null,"outputPerM":null,"blendedPerM":0.23099999999999998,"tokensPerS":null,"observedAt":"2026-10-14","sourceId":"openrouter"},"answer":{"word":"No.","scope":"Best current rank is #45 in Coding › Web dev.","lead":"As of Oct 14, 2026, Hy3 from tencent. Best current rank is #45 in Coding › Web dev. Ranked #45 in Coding › Web dev.","confidence":"medium"},"verdicts":[{"id":"v_overall_general-llm_hy3_2026-10-14_open_RANKED","model":"hy3","model_name":"Hy3","category":"general-llm","category_name":"General LLM","slice":"overall","state":"RANKED","rank":52,"present_evidence":[],"missing_evidence":[],"margin":35.172413793103445,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #52 in General LLM.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#52 in General LLM"},{"id":"v_open-weights_general-llm_hy3_2026-10-14_open_RANKED","model":"hy3","model_name":"Hy3","category":"general-llm","category_name":"General LLM","slice":"open-weights","state":"RANKED","rank":12,"present_evidence":[],"missing_evidence":[],"margin":18.309859154929583,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #12 in General LLM.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#12 in General LLM"},{"id":"v_pareto_general-llm_hy3_2026-10-14_open_RANKED","model":"hy3","model_name":"Hy3","category":"general-llm","category_name":"General LLM","slice":"pareto","state":"RANKED","rank":65,"present_evidence":[],"missing_evidence":[],"margin":34.57446808510639,"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":"#65 in General LLM"},{"id":"v_overall_reasoning_hy3_2026-10-14_open_RANKED","model":"hy3","model_name":"Hy3","category":"reasoning","category_name":"Reasoning","slice":"overall","state":"RANKED","rank":52,"present_evidence":[],"missing_evidence":[],"margin":36.111111111111114,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #52 in Reasoning.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#52 in Reasoning"},{"id":"v_open-weights_reasoning_hy3_2026-10-14_open_RANKED","model":"hy3","model_name":"Hy3","category":"reasoning","category_name":"Reasoning","slice":"open-weights","state":"RANKED","rank":14,"present_evidence":[],"missing_evidence":[],"margin":19.718309859154928,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #14 in Reasoning.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#14 in Reasoning"},{"id":"v_pareto_reasoning_hy3_2026-10-14_open_RANKED","model":"hy3","model_name":"Hy3","category":"reasoning","category_name":"Reasoning","slice":"pareto","state":"RANKED","rank":66,"present_evidence":[],"missing_evidence":[],"margin":35.63829787234043,"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":"#66 in Reasoning"},{"id":"v_overall_math_hy3_2026-10-14_open_INSUFFICIENT_DATA","model":"hy3","model_name":"Hy3","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":31}],"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":"#31 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_hy3_2026-10-14_open_INSUFFICIENT_DATA","model":"hy3","model_name":"Hy3","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":54}],"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":"#54 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_hy3_2026-10-14_open_RANKED","model":"hy3","model_name":"Hy3","category":"coding-web-dev","category_name":"Coding › Web dev","slice":"overall","state":"RANKED","rank":45,"present_evidence":[],"missing_evidence":[],"margin":41.904761904761905,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #45 in Coding › Web dev.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#45 in Coding › Web dev"},{"id":"v_open-weights_coding-web-dev_hy3_2026-10-14_open_RANKED","model":"hy3","model_name":"Hy3","category":"coding-web-dev","category_name":"Coding › Web dev","slice":"open-weights","state":"RANKED","rank":14,"present_evidence":[],"missing_evidence":[],"margin":25.490196078431367,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #14 in Coding › Web dev.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#14 in Coding › Web dev"},{"id":"v_pareto_coding-web-dev_hy3_2026-10-14_open_RANKED","model":"hy3","model_name":"Hy3","category":"coding-web-dev","category_name":"Coding › Web dev","slice":"pareto","state":"RANKED","rank":51,"present_evidence":[],"missing_evidence":[],"margin":40,"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":"#51 in Coding › Web dev"},{"id":"v_overall_long-context_hy3_2026-10-14_open_RANKED","model":"hy3","model_name":"Hy3","category":"long-context","category_name":"Long context","slice":"overall","state":"RANKED","rank":51,"present_evidence":[],"missing_evidence":[],"margin":35.172413793103445,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #51 in Long context.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#51 in Long context"},{"id":"v_open-weights_long-context_hy3_2026-10-14_open_RANKED","model":"hy3","model_name":"Hy3","category":"long-context","category_name":"Long context","slice":"open-weights","state":"RANKED","rank":14,"present_evidence":[],"missing_evidence":[],"margin":19.718309859154928,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #14 in Long context.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#14 in Long context"},{"id":"v_pareto_long-context_hy3_2026-10-14_open_RANKED","model":"hy3","model_name":"Hy3","category":"long-context","category_name":"Long context","slice":"pareto","state":"RANKED","rank":64,"present_evidence":[],"missing_evidence":[],"margin":34.04255319148936,"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":"#64 in Long context"},{"id":"v_overall_factuality_hy3_2026-10-14_open_RANKED","model":"hy3","model_name":"Hy3","category":"factuality","category_name":"Factuality","slice":"overall","state":"RANKED","rank":61,"present_evidence":[],"missing_evidence":[],"margin":46.21212121212121,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #61 in Factuality.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#61 in Factuality"},{"id":"v_pareto_factuality_hy3_2026-10-14_open_RANKED","model":"hy3","model_name":"Hy3","category":"factuality","category_name":"Factuality","slice":"pareto","state":"RANKED","rank":74,"present_evidence":[],"missing_evidence":[],"margin":43.604651162790695,"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":"#74 in Factuality"}]}