{"id":"qwen3-vl-235b-a22b-thinking","slug":"qwen3-vl-235b-a22b-thinking","name":"Qwen3 VL 235B A22b Thinking","orgId":"alibaba","family":"qwen3-vl-235b-a22b-thinking","releaseDate":null,"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-vl-235b-a22b-thinking","Qwen3 VL 235B A22b Thinking"],"aliasNote":null,"organization":{"id":"alibaba","name":"Alibaba / Qwen","slug":"alibaba","country":null,"url":null,"color":"#FF7A00","mark":"Q"},"price":null,"answer":{"word":"No.","scope":"Best current rank is #115 in Long context.","lead":"As of Oct 14, 2026, Qwen3 VL 235B A22b Thinking from Alibaba / Qwen. Best current rank is #115 in Long context. Ranked #115 in Long context.","confidence":"medium"},"verdicts":[{"id":"v_overall_general-llm_qwen3-vl-235b-a22b-thinking_2026-10-14_open_RANKED","model":"qwen3-vl-235b-a22b-thinking","model_name":"Qwen3 VL 235B A22b Thinking","category":"general-llm","category_name":"General LLM","slice":"overall","state":"RANKED","rank":120,"present_evidence":[],"missing_evidence":[],"margin":82.06896551724138,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #120 in General LLM.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#120 in General LLM"},{"id":"v_overall_reasoning_qwen3-vl-235b-a22b-thinking_2026-10-14_open_RANKED","model":"qwen3-vl-235b-a22b-thinking","model_name":"Qwen3 VL 235B A22b Thinking","category":"reasoning","category_name":"Reasoning","slice":"overall","state":"RANKED","rank":117,"present_evidence":[],"missing_evidence":[],"margin":81.25,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #117 in Reasoning.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#117 in Reasoning"},{"id":"v_overall_math_qwen3-vl-235b-a22b-thinking_2026-10-14_open_INSUFFICIENT_DATA","model":"qwen3-vl-235b-a22b-thinking","model_name":"Qwen3 VL 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":111}],"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":"#111 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-vl-235b-a22b-thinking_2026-10-14_open_INSUFFICIENT_DATA","model":"qwen3-vl-235b-a22b-thinking","model_name":"Qwen3 VL 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":108}],"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":"#108 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-vl-235b-a22b-thinking_2026-10-14_open_RANKED","model":"qwen3-vl-235b-a22b-thinking","model_name":"Qwen3 VL 235B A22b Thinking","category":"long-context","category_name":"Long context","slice":"overall","state":"RANKED","rank":115,"present_evidence":[],"missing_evidence":[],"margin":79.3103448275862,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #115 in Long context.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#115 in Long context"},{"id":"v_overall_vision_qwen3-vl-235b-a22b-thinking_2026-10-14_open_INSUFFICIENT_DATA","model":"qwen3-vl-235b-a22b-thinking","model_name":"Qwen3 VL 235B A22b Thinking","category":"vision","category_name":"Vision","slice":"overall","state":"INSUFFICIENT_DATA","rank":null,"present_evidence":[{"benchmark":"lmarena-vision","name":"LMArena Vision (style-controlled)","rank":71}],"missing_evidence":[{"benchmark":"gdp-pdf","name":"GDP.pdf"}],"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"#71 on LMArena Vision (style-controlled); missing GDP.pdf","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Not enough data"}]}