Research papers

Independent, sourced working papers. Every figure links to its source and is tagged by evidence tier. Quotable with attribution and a link. llms.txt · Daily AI brief

KL-2026-0921 September 2026

Frontier Models, September 2026: ASTRA, Fable, Jev and the Chinese Frontier

GPT-6 Astra and Claude Fable 5.1 tie at 53 on the Artificial Analysis Intelligence Index and split the specialised benchmarks. Qwen3.8 Max, GLM-5.3 and Kimi K3 trail by 8 to 9 points at about a quarter of the cost. TypeSafe's Jev returns typed decisions in under 500 ms at $0.042 per million input tokens. Includes a Q4 2026 model-routing table.

HTML · Markdown full text