Qwen: Qwen3 235B A22B Thinking 2507

qwen/qwen3-235b-a22b-thinking-2507

Context: 262,144In: $0.23/1MOut: $2.30/1MUpdated 2026-08-05

Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...

Intelligence
19.6
Coding
22.1
Agentic
3.8

Metric profile

Trend over time

Intelligence
19.6
Coding
22.1
Agentic
3.8

Only 1 snapshot so far (data refreshes daily) — the trend line appears after the 2nd snapshot.

Classic evals (curated from model cards)

Alibaba Qwen — manually maintained, may lag releases

MMLU-Pro
76%
GPQA Diamond
69%
MATH-500
96%

Design Arena (ELO by category)

CategoryELOWin rateRank
website107642%
#94
codecategories106240.8%
#94
3d105540.7%
#89
gamedev100334.4%
#101
uicomponent97833.9%
#98
dataviz97432.3%
#100