Qwen3.8 Max scores 1739 Elo on GDPval-AA, ahead of Kimi K3 (1685), effectively t
Source
ArtificialAnlys
Author
ArtificialAnlys
Published
Terms in this piece · Glossary
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
benchmark — A standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.
Why it matters
A gain driven by taking 4x more turns per task is a different purchase than a gain in per-turn capability: it lands as latency and tokenThe chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.Full definition → spend in production. This is the kind of read a benchmarkA standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.Full definition → headline alone would hide.
Transcript
Qwen3.8 Max scores 1739 Elo on GDPval-AA, ahead of Kimi K3 (1685), effectively tied with Claude Fable 5 (1743) and GPT-5.6 Sol (max, 1730), and behind only Claude Opus 5 (max, 1852). The 468 Elo gain is in part driven by the new model taking more turns per task (64 vs. 14 for https://t.co/23aQXrTnqS
postQwen3.8 Max costs $1.14 per Intelligence Index task, more than double Qwen3.7 Ma
postAlibaba's Qwen3.8 Max scores 56 on the Artificial Analysis Intelligence Index at
postAA-Omniscience regresses 10 points from Qwen3.7 Max (+14 to +4), reversing its p
postOnly two labs occupy the Time per Task Pareto frontier: all frontier models unde