Sign in

Is Qwen3 235B A22B Instruct SOTA in Reasoning?#107 in ReasoningRanked #107 in Reasoning.

How it scores here

Qwen3 235B A22B Instruct in Reasoning

Primary benchmarks

  • LMArena Text (style-controlled, hard prompts): 1447 (CI 1444–1450) on Nov 19, 2026 (#135 of 263).

On the category's weighted score it is 63.5 points behind #1 Gemini 4 Carbon and 0.6 behind the next model up, DeepSeek V3.2.

Nearby on the board

#ModelCategory score
104GPT-5 Chat38.2
105GPT-537.6
106DeepSeek V3.237.1
107Qwen3 235B A22B Instruct36.5
108DeepSeek V3.2 Exp35.9
109Muse Glimmer35.3
110Claude Haiku 5.534.7
Standings

Reasoning

#ModelState
1Gemini 4 CarbonCo-SOTA
1Gemini 4 ArgonCo-SOTA
1Gemini 4 NeonCo-SOTA
2Muse WonderNear-SOTA
3Claude Opus 4.6Near-SOTA
4Claude Opus 5.5Near-SOTA
5Claude Fable 5Near-SOTA
6Claude Opus 4.7Was SOTA
7Claude Fable 5.1Was SOTA
8Muse Spark 1.3#8 in this category
9Gemini 3.8 Flash#9 in this category
10Claude Fable 5.2#10 in this category

Category page →