Alibaba

Qwen3 Next 80B A3B Instruct

Sep 11, 2025Open weightsModels.devHugging Face

Compare

Intelligence

9.6

#437 of 744Rank 437 of 744 measured models

Output speed

150 t/s

#86 of 403Rank 86 of 403 measured models

Price/1M

$0.388

#233 of 659Rank 233 of 659 measured models

Context window

262K

#458 of 1199Rank 458 of 1199 measured models

Qwen3 Next 80B A3B Instruct scores 9.6 on the Artificial Analysis Intelligence Index, ranking 437th of 744 measured models. The closest models on this index are GPT-4.5 (Preview) (9.6), Qwen3 Coder 30B A3B Instruct (9.6), and Tri-21B-think Preview (9.6). At $0.388 per million tokens (3:1 input/output blended price), it is more expensive than Qwen3 Coder 30B A3B Instruct ($0.30). With an output speed of 150 t/s, it is about as fast as Qwen3 Coder 30B A3B Instruct (156 t/s).