ModelsNov 16, 2026 · 11:458 sources

Qwen4-Max scores 43 on the Artificial Analysis Intelligence Index, beating Qwen3.8 Max at ~67% lower cost per task but trailing Kimi K3.1 Pro at ~11% lower cost (@artificialanlys)

From techmeme.com

Image: techmeme.com
AI;DR

Qwen4-Max scores 43 on the Artificial Analysis Intelligence Index. Qwen4-Max beats Qwen3.8 Max at ~67% lower cost per task. Qwen4-Max trails Kimi K3.1 Pro at ~11% lower cost.

Read the sourceSign in to suggest

Sources

+ 6 more
  1. SUPPORT@teortaxestex“Kimi tier but cheaper and faster. Ok. But this is a disaster. Even they are not claiming to be near frontier.”x.com
  2. SUPPORT@stablequan“we are now going to see a much wider gap between chinese vs. anthropic models”x.com
  3. SUPPORT@luminabench“It's heavily distilled from Astra, like the UI's it makes are almost identical, not a very good drop imo”x.com
  4. SUPPORT@udiwertheimer“Qwen4-Max by @Alibaba_Qwen is the #1 Chinese model on the leaderboard making Alibaba now the #1 Chinese lab and #5 lab overall”x.com
  5. SUPPORT@hesamation“the 2.4 TRILLION param Qwen4-Max”x.com
  6. SUPPORT@tphuang“Qwen-4 appears to be built w/ more science discovery in mind. It seems like SWE is not its strong suit based on these benchmarks.”x.com
#llmMarkdown

One ranked edition, every morning

The stories that matter today. Free, cancel anytime.

Telegram @aidr_today