Qwen4 Max uses 39% fewer output tokens while scoring 9 points higher

ArtificialAnlys · x · 2026-11-16

Artificial Analysis charts show Qwen4 Max averages 105k output tokens per Intelligence Index task (56k reasoning), 39% fewer than Qwen3.8 Max's 171k, while scoring 9 points higher on the index. For comparison, Kimi K3.1 Pro uses 72k and Tencent Hy4 78k. With most models' output dominated by reasoning tokens, Qwen4 Max improving scores while thinking less marks a notable gain in reasoning efficiency.

Original post →

More from Models

Models channel →