Alibaba

Qwen3 235B A22B 2507 (Reasoning)

Jul 25, 2025ReasoningOpen weights

Compare

Intelligence

12.7

#354 of 744Rank 354 of 744 measured models

Coding

22.1

#216 of 298Rank 216 of 298 measured models

Output speed

85.4 t/s

#210 of 403Rank 210 of 403 measured models

Price/1M

$0.747

#334 of 659Rank 334 of 659 measured models

Context window

256K

#518 of 1199Rank 518 of 1199 measured models

Cost per task

$0.0806

#47 of 193Rank 47 of 193 measured models

Qwen3 235B A22B 2507 (Reasoning) scores 12.7 on the Artificial Analysis Intelligence Index, ranking 354th of 744 measured models. The closest models on this index are GPT-4.1 (12.7), Granite 4.2 30B (12.7), and Kimi K2 (12.7). At $0.747 per million tokens (3:1 input/output blended price), it is cheaper than GPT-4.1 ($3.50) and Kimi K2 ($1.00), more expensive than Granite 4.2 30B ($0.282). With an output speed of 85.4 t/s, it is faster than Granite 4.2 30B (75.5 t/s) and Kimi K2 (55.1 t/s), slower than GPT-4.1 (152 t/s).