Alibaba

Qwen3 30B A3B 2507 (Reasoning)

Jul 30, 2025ReasoningOpen weights

Compare

Intelligence

9.8

#432 of 744Rank 432 of 744 measured models

Coding

12.1

#259 of 298Rank 259 of 298 measured models

Output speed

135 t/s

#112 of 403Rank 112 of 403 measured models

Price/1M

$0.595

#306 of 659Rank 306 of 659 measured models

Context window

262K

#458 of 1199Rank 458 of 1199 measured models

Cost per task

$0.0659

#41 of 193Rank 41 of 193 measured models

Qwen3 30B A3B 2507 (Reasoning) scores 9.8 on the Artificial Analysis Intelligence Index, ranking 432nd of 744 measured models. The closest models on this index are Gemini 2.5 Flash (9.9), o1-mini (9.8), and Qwen3 30B A3B Thinking 2507 (9.8). At $0.595 per million tokens (3:1 input/output blended price), it is cheaper than Gemini 2.5 Flash ($0.85) and Qwen3 30B A3B Thinking 2507 ($0.75). With an output speed of 135 t/s, it is slower than Gemini 2.5 Flash (203 t/s).