Alibaba

Qwen3 235B A22B 2507 Instruct

Jul 21, 2025Open weightsModels.devHugging Face

Compare

Intelligence

12.0

#373 of 744Rank 373 of 744 measured models

Output speed

43.3 t/s

#348 of 403Rank 348 of 403 measured models

Price/1M

$0.385

#232 of 659Rank 232 of 659 measured models

Context window

256K

#518 of 1199Rank 518 of 1199 measured models

Qwen3 235B A22B 2507 Instruct scores 12.0 on the Artificial Analysis Intelligence Index, ranking 373rd of 744 measured models. The closest models on this index are Grok 3 (12.1), Seed-OSS-36B-Instruct (12.1), and Qwen3 235B A22B Instruct 2507 (12.0). At $0.385 per million tokens (3:1 input/output blended price), it is cheaper than Grok 3 ($6), more expensive than Seed-OSS-36B-Instruct ($0.30) and Qwen3 235B A22B Instruct 2507 ($0.205). With an output speed of 43.3 t/s, it is faster than Seed-OSS-36B-Instruct (40.9 t/s), slower than Grok 3 (100 t/s).