{"id":"qwen3-235b-a22b-instruct-2507","slug":"qwen3-235b-a22b-instruct-2507","name":"Qwen3 235B A22b Instruct 2507","orgId":"alibaba","family":"qwen3-235b-a22b-instruct-2507","releaseDate":"2025-07-25","availability":"ga","openWeights":true,"license":"Apache 2.0","paramsTotal":235000000000,"contextWindow":null,"knowledgeCutoff":null,"modelCardUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","hfRepo":null,"modalities":["text"],"aliases":["qwen3-235b-a22b-instruct-2507","Qwen3 235B A22b Instruct 2507"],"aliasNote":null,"organization":{"id":"alibaba","name":"Alibaba / Qwen","slug":"alibaba","country":null,"url":null,"color":"#FF7A00","mark":"Q"},"price":null,"answer":{"word":"It used to be.","scope":"Was SOTA in General LLM.","lead":"As of Oct 14, 2026, Qwen3 235B A22b Instruct 2507 from Alibaba / Qwen. Was SOTA in General LLM. Was SOTA in Reasoning from 2025-08-18 to 2025-09-08. Currently ranked #79.","confidence":"medium"},"verdicts":[{"id":"v_overall_general-llm_qwen3-235b-a22b-instruct-2507_2026-10-14_open_RANKED","model":"qwen3-235b-a22b-instruct-2507","model_name":"Qwen3 235B A22b Instruct 2507","category":"general-llm","category_name":"General LLM","slice":"overall","state":"RANKED","rank":89,"present_evidence":[],"missing_evidence":[],"margin":60.689655172413794,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #89 in General LLM.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#89 in General LLM"},{"id":"v_open-weights_general-llm_qwen3-235b-a22b-instruct-2507_2025-09-18_open_WAS_SOTA","model":"qwen3-235b-a22b-instruct-2507","model_name":"Qwen3 235B A22b Instruct 2507","category":"general-llm","category_name":"General LLM","slice":"open-weights","state":"WAS_SOTA","rank":34,"present_evidence":[],"missing_evidence":[],"margin":49.29577464788732,"confidence":"medium","valid_from":"2025-09-18","valid_to":null,"configuration":null,"rationale":"Was SOTA in General LLM from 2025-09-18 to 2025-11-05. Currently ranked #34.","safeguard_flags":["dethroned"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Was SOTA · General LLM"},{"id":"v_overall_reasoning_qwen3-235b-a22b-instruct-2507_2025-08-18_open_WAS_SOTA","model":"qwen3-235b-a22b-instruct-2507","model_name":"Qwen3 235B A22b Instruct 2507","category":"reasoning","category_name":"Reasoning","slice":"overall","state":"WAS_SOTA","rank":79,"present_evidence":[],"missing_evidence":[],"margin":54.861111111111114,"confidence":"medium","valid_from":"2025-08-18","valid_to":null,"configuration":null,"rationale":"Was SOTA in Reasoning from 2025-08-18 to 2025-09-08. Currently ranked #79.","safeguard_flags":["dethroned"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Was SOTA · Reasoning"},{"id":"v_open-weights_reasoning_qwen3-235b-a22b-instruct-2507_2025-10-17_open_WAS_SOTA","model":"qwen3-235b-a22b-instruct-2507","model_name":"Qwen3 235B A22b Instruct 2507","category":"reasoning","category_name":"Reasoning","slice":"open-weights","state":"WAS_SOTA","rank":29,"present_evidence":[],"missing_evidence":[],"margin":40.84507042253521,"confidence":"medium","valid_from":"2025-10-17","valid_to":null,"configuration":null,"rationale":"Was SOTA in Reasoning from 2025-10-17 to 2025-11-06. Currently ranked #29.","safeguard_flags":["dethroned"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Was SOTA · Reasoning"},{"id":"v_overall_math_qwen3-235b-a22b-instruct-2507_2026-10-14_open_INSUFFICIENT_DATA","model":"qwen3-235b-a22b-instruct-2507","model_name":"Qwen3 235B A22b Instruct 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":92}],"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":"#92 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-instruct-2507_2026-10-14_open_INSUFFICIENT_DATA","model":"qwen3-235b-a22b-instruct-2507","model_name":"Qwen3 235B A22b Instruct 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":87}],"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":"#87 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-instruct-2507_2026-10-14_open_RANKED","model":"qwen3-235b-a22b-instruct-2507","model_name":"Qwen3 235B A22b Instruct 2507","category":"long-context","category_name":"Long context","slice":"overall","state":"RANKED","rank":86,"present_evidence":[],"missing_evidence":[],"margin":59.310344827586206,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #86 in Long context.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#86 in Long context"},{"id":"v_open-weights_long-context_qwen3-235b-a22b-instruct-2507_2025-09-18_open_WAS_SOTA","model":"qwen3-235b-a22b-instruct-2507","model_name":"Qwen3 235B A22b Instruct 2507","category":"long-context","category_name":"Long context","slice":"open-weights","state":"WAS_SOTA","rank":34,"present_evidence":[],"missing_evidence":[],"margin":47.887323943661976,"confidence":"medium","valid_from":"2025-09-18","valid_to":null,"configuration":null,"rationale":"Was SOTA in Long context from 2025-09-18 to 2025-10-16. Currently ranked #34.","safeguard_flags":["dethroned"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Was SOTA · Long context"},{"id":"v_overall_factuality_qwen3-235b-a22b-instruct-2507_2026-10-14_open_RANKED","model":"qwen3-235b-a22b-instruct-2507","model_name":"Qwen3 235B A22b Instruct 2507","category":"factuality","category_name":"Factuality","slice":"overall","state":"RANKED","rank":81,"present_evidence":[],"missing_evidence":[],"margin":61.36363636363637,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #81 in Factuality.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#81 in Factuality"},{"id":"v_overall_arc_qwen3-235b-a22b-instruct-2507_2026-10-14_open_RANKED","model":"qwen3-235b-a22b-instruct-2507","model_name":"Qwen3 235B A22b Instruct 2507","category":"arc","category_name":"Abstraction (ARC)","slice":"overall","state":"RANKED","rank":81,"present_evidence":[],"missing_evidence":[],"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Last listed at #81 in Abstraction (ARC) on 2025-07-25. That board does not award a crown.","safeguard_flags":["off_board"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#81 in Abstraction (ARC)"}]}