↓Skip to main content
Zeitgeist — a spike by Chris Gathercole
  1. Creators/
  2. Simon Willison — Creator of Datasette; co-creator of Django/

Qwen 3.8 27B scores 52 on the Artificial Analysis Intelligence Index

Blog · Watch/Read

  • Simon Willison highlights the “truly astonishing” performance of the Qwen 3.8 27B model on the Artificial Analysis Intelligence Index.
  • Qwen 3.8 27B scored 52, matching GPT-5.6 Luna (max) and coming within one point of significantly larger models like GLM-5.2 (753B) and DeepSeek V4 Pro 0813 (1.7T).
  • The key takeaway is that a relatively small 27B parameter model is achieving performance comparable to much larger, state-of-the-art models, indicating a significant advancement in AI efficiency and capability.