Qwen4 Max lands +9 on AA Intelligence Index, still 3 points behind Kimi K3.1 Pro

rickasaurus · x · 2026-11-16

Alibaba launched Qwen4 Max, scoring 43 on the Artificial Analysis Intelligence Index (xhigh reasoning effort) — up 9 points from Qwen3.8 Max (34) but 3 points behind Kimi K3.1 Pro (max, 46) at 11% lower cost per task.

Gains vs Qwen3.8 Max across every eval in the Index: HLE-Diamond +21 (24%→45%), AA-Omniscience +18, AutomationBench-AA +17, CritPt v2 +13, Terminal-Bench-Science +11, Terminal-Bench 4.0 +9, GDP.pdf +3, FrontierCode 2.0 +3, AA-Briefcase +82 Elo.

A quoted commentator argues Qwen4 isn't a strong release: despite paper parity with Opus on key benchmarks, the AA Index tells a different story, and Qwen reportedly being cut off from distillation underscores the shortfall.

Related event: Alibaba Releases Qwen4-Max, Setting New Benchmarks for Chinese Models(55 posts)→

Original post →

More from Models

Models channel →