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)→
More from Models
- Google hides Gemini model label in AI Mode, rolls Gemini 4 Carbon to Pro subscribers — gaganghotra_ · 2026-11-16
- Open-weight Karpo-Decision-31B tops Decision Index at 73.9, one forward pass per answer — CodeByPoonam · 2026-11-16
- Nathan Lambert calls out Ethan Mollick for 'selectively ignoring' Kimi in model comparisons — natolambert · 2026-11-16
- Stealth Anthropic model spotted in Devin build as METR chart shows frontier pace up 1.4x — daniel_mac8 · 2026-11-16
- Eval Firm Trajectory Told 40 Agents "NEVER Stop" in Harness Without Telling Epoch — peterwildeford · 2026-11-16
- Unsloth Q8 crushes default Q3 in a self-hosted test over 331 financial PDFs — No_Cartographer3953 · 2026-11-16