{"id":"qwen3-235b-a22b-thinking-2507","slug":"qwen3-235b-a22b-thinking-2507","name":"Qwen3 235B A22b Thinking 2507","orgId":"alibaba","family":"qwen3-235b-a22b-thinking-2507","releaseDate":"2025-07-25","availability":"ga","openWeights":true,"license":"Apache 2.0","paramsTotal":235000000000,"contextWindow":128000,"knowledgeCutoff":null,"modelCardUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","hfRepo":"Qwen/Qwen3-235B-A22B-Thinking-2507","modalities":["text"],"aliases":["qwen3-235b-a22b-thinking-2507","Qwen3 235B A22b Thinking 2507","Qwen3-235B-A22B-Thinking (Jul 2025)","Qwen3 235B A22b Thinking","qwen/qwen3-235b-a22b-thinking-2507","Qwen: Qwen3 235B A22B Thinking 2507"],"aliasNote":null,"organization":{"id":"alibaba","name":"Alibaba / Qwen","slug":"alibaba","country":null,"url":null,"color":"#FF7A00","mark":"Q"},"price":{"modelId":"qwen3-235b-a22b-thinking-2507","provider":"qwen","inputPerM":null,"outputPerM":null,"blendedPerM":1.2125000000000001,"tokensPerS":null,"observedAt":"2026-10-14","sourceId":"openrouter"},"answer":{"word":"No.","scope":"Best recorded rank is #69 in Science.","lead":"As of Oct 14, 2026, Qwen3 235B A22b Thinking 2507 from Alibaba / Qwen. Best recorded rank is #69 in Science. Last listed at #69 in Science on 2025-07-25. That board does not award a crown.","confidence":"low"},"verdicts":[{"id":"v_overall_general-llm_qwen3-235b-a22b-thinking-2507_2026-10-14_open_RANKED","model":"qwen3-235b-a22b-thinking-2507","model_name":"Qwen3 235B A22b Thinking 2507","category":"general-llm","category_name":"General LLM","slice":"overall","state":"RANKED","rank":115,"present_evidence":[],"missing_evidence":[],"margin":78.62068965517241,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #115 in General LLM.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#115 in General LLM"},{"id":"v_pareto_general-llm_qwen3-235b-a22b-thinking-2507_2026-10-14_open_RANKED","model":"qwen3-235b-a22b-thinking-2507","model_name":"Qwen3 235B A22b Thinking 2507","category":"general-llm","category_name":"General LLM","slice":"pareto","state":"RANKED","rank":151,"present_evidence":[],"missing_evidence":[],"margin":80.31914893617021,"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":"#151 in General LLM"},{"id":"v_overall_reasoning_qwen3-235b-a22b-thinking-2507_2026-10-14_open_RANKED","model":"qwen3-235b-a22b-thinking-2507","model_name":"Qwen3 235B A22b Thinking 2507","category":"reasoning","category_name":"Reasoning","slice":"overall","state":"RANKED","rank":119,"present_evidence":[],"missing_evidence":[],"margin":82.63888888888889,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #119 in Reasoning.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#119 in Reasoning"},{"id":"v_pareto_reasoning_qwen3-235b-a22b-thinking-2507_2026-10-14_open_RANKED","model":"qwen3-235b-a22b-thinking-2507","model_name":"Qwen3 235B A22b Thinking 2507","category":"reasoning","category_name":"Reasoning","slice":"pareto","state":"RANKED","rank":156,"present_evidence":[],"missing_evidence":[],"margin":83.51063829787233,"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":"#156 in Reasoning"},{"id":"v_overall_math_qwen3-235b-a22b-thinking-2507_2026-10-14_open_INSUFFICIENT_DATA","model":"qwen3-235b-a22b-thinking-2507","model_name":"Qwen3 235B A22b Thinking 2507","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":116}],"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":"#116 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_qwen3-235b-a22b-thinking-2507_2026-10-14_open_RANKED","model":"qwen3-235b-a22b-thinking-2507","model_name":"Qwen3 235B A22b Thinking 2507","category":"science","category_name":"Science","slice":"overall","state":"RANKED","rank":69,"present_evidence":[],"missing_evidence":[],"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Last listed at #69 in Science on 2025-07-25. That board does not award a crown.","safeguard_flags":["off_board"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#69 in Science"},{"id":"v_overall_coding_qwen3-235b-a22b-thinking-2507_2026-10-14_open_INSUFFICIENT_DATA","model":"qwen3-235b-a22b-thinking-2507","model_name":"Qwen3 235B A22b Thinking 2507","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":119}],"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":"#119 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_qwen3-235b-a22b-thinking-2507_2026-10-14_open_RANKED","model":"qwen3-235b-a22b-thinking-2507","model_name":"Qwen3 235B A22b Thinking 2507","category":"long-context","category_name":"Long context","slice":"overall","state":"RANKED","rank":119,"present_evidence":[],"missing_evidence":[],"margin":82.06896551724138,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #119 in Long context.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#119 in Long context"},{"id":"v_pareto_long-context_qwen3-235b-a22b-thinking-2507_2026-10-14_open_RANKED","model":"qwen3-235b-a22b-thinking-2507","model_name":"Qwen3 235B A22b Thinking 2507","category":"long-context","category_name":"Long context","slice":"pareto","state":"RANKED","rank":158,"present_evidence":[],"missing_evidence":[],"margin":84.04255319148936,"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":"#158 in Long context"},{"id":"v_overall_factuality_qwen3-235b-a22b-thinking-2507_2026-10-14_open_INSUFFICIENT_DATA","model":"qwen3-235b-a22b-thinking-2507","model_name":"Qwen3 235B A22b Thinking 2507","category":"factuality","category_name":"Factuality","slice":"overall","state":"INSUFFICIENT_DATA","rank":null,"present_evidence":[{"benchmark":"simpleqa","name":"SimpleQA Verified","rank":44}],"missing_evidence":[{"benchmark":"lmarena-factuality","name":"LMArena Text factuality"}],"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"#44 on SimpleQA Verified; missing LMArena Text factuality","safeguard_flags":["off_board"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Not enough data"}]}