Alibaba

Qwen3.8 27B

Aug 14, 2026ReasoningOpen weights

Compare

Intelligence

27.6

#146 of 744Rank 146 of 744 measured models

Coding

56.1

#101 of 298Rank 101 of 298 measured models

Output speed

44.3 t/s

#340 of 403Rank 340 of 403 measured models

Price/1M

$1.13

#392 of 659Rank 392 of 659 measured models

Context window

256K

#518 of 1199Rank 518 of 1199 measured models

Cost per task

$1.13

#136 of 193Rank 136 of 193 measured models

Qwen3.8 27B (Medium) scores 27.6 on the Artificial Analysis Intelligence Index, ranking 146th of 744 measured models. The closest models on this index are Gemini 3 Pro Preview (28.0), GLM-5 (27.9), and Grok Build 0.1 0616 (27.2). At $1.13 per million tokens (3:1 input/output blended price), it is cheaper than Gemini 3 Pro Preview ($4.50), GLM-5 ($1.55), and Grok Build 0.1 0616 ($1.25). With an output speed of 44.3 t/s, it is slower than GLM-5 (70.8 t/s) and Grok Build 0.1 0616 (67.4 t/s).