{"id":"qwen3-235b-a22b-thinking","slug":"qwen3-235b-a22b-thinking","name":"Qwen3 235B A22B Thinking","orgId":"alibaba","family":"qwen3-235b-a22b-thinking","releaseDate":"2025-07-25","availability":"ga","openWeights":true,"license":"Apache 2.0","paramsTotal":235000000000,"paramsSource":"epoch","contextWindow":null,"knowledgeCutoff":null,"modelCardUrl":null,"hfRepo":null,"modalities":["text"],"aliases":["Qwen3-235B-A22B-Thinking (2507)","Qwen3 235B A22b Thinking","Qwen3-235B-A22B-Thinking (Jul 2025)"],"aliasNote":null,"listedSince":"2026-10-20","organization":{"id":"alibaba","name":"Alibaba / Qwen","slug":"alibaba","country":null,"url":null,"color":"#FF7A00","mark":"Q"},"price":null,"answer":{"word":"#146","scope":"Best current rank: #146 in General LLM, as of Nov 22, 2026.","lead":"As of Nov 22, 2026, Qwen3 235B A22B Thinking is ranked #146 in General LLM (since Nov 22, 2026; sources LMArena Text (style-controlled, overall); methodology v1.0). Ranked #146 in General LLM.","confidence":"medium"},"status":"BENCHMARKED","verdicts":[{"id":"v_overall_general-llm_qwen3-235b-a22b-thinking_2026-11-22_open_RANKED","model":"qwen3-235b-a22b-thinking","model_name":"Qwen3 235B A22B Thinking","category":"general-llm","category_name":"General LLM","slice":"overall","state":"RANKED","rank":146,"present_evidence":[],"missing_evidence":[],"coverage":null,"segments":[],"confirm":[],"margin":85.96491228070175,"confidence":"medium","valid_from":"2026-11-22","valid_to":null,"configuration":null,"rationale":"Ranked #146 in General LLM.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#146 in General LLM"},{"id":"v_overall_reasoning_qwen3-235b-a22b-thinking_2026-11-22_open_RANKED","model":"qwen3-235b-a22b-thinking","model_name":"Qwen3 235B A22B Thinking","category":"reasoning","category_name":"Reasoning","slice":"overall","state":"RANKED","rank":150,"present_evidence":[],"missing_evidence":[],"coverage":null,"segments":[],"confirm":[],"margin":88.82352941176471,"confidence":"medium","valid_from":"2026-11-22","valid_to":null,"configuration":null,"rationale":"Ranked #150 in Reasoning.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#150 in Reasoning"},{"id":"v_overall_math_qwen3-235b-a22b-thinking_2026-11-22_open_INSUFFICIENT_DATA","model":"qwen3-235b-a22b-thinking","model_name":"Qwen3 235B A22B 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":140}],"missing_evidence":[{"benchmark":"hle","name":"Humanity's Last Exam"},{"benchmark":"frontiermath","name":"FrontierMath"}],"coverage":null,"segments":[],"confirm":[],"margin":null,"confidence":"low","valid_from":"2026-11-22","valid_to":null,"configuration":null,"rationale":"#140 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_qwen3-235b-a22b-thinking_2026-11-22_open_INSUFFICIENT_DATA","model":"qwen3-235b-a22b-thinking","model_name":"Qwen3 235B A22B 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":154}],"missing_evidence":[{"benchmark":"terminal-bench-4","name":"Terminal-Bench 4.0"},{"benchmark":"swe-bench-pro-hard","name":"SWE-bench Pro V2 HARD"}],"coverage":null,"segments":[],"confirm":[],"margin":null,"confidence":"low","valid_from":"2026-11-22","valid_to":null,"configuration":null,"rationale":"#154 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_2026-11-22_open_RANKED","model":"qwen3-235b-a22b-thinking","model_name":"Qwen3 235B A22B Thinking","category":"long-context","category_name":"Long context","slice":"overall","state":"RANKED","rank":152,"present_evidence":[],"missing_evidence":[],"coverage":null,"segments":[],"confirm":[],"margin":90,"confidence":"medium","valid_from":"2026-11-22","valid_to":null,"configuration":null,"rationale":"Ranked #152 in Long context.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#152 in Long context"}]}