Claude Fable 5.2 hits 74.6% on Terminal-Bench-Science, new SOTA for agentic research
burny_tech · x · 2026-11-10
alphaxiv reports that Claude Fable 5.2 is now SOTA for agentic scientific research, scoring 74.6% on Terminal-Bench-Science 0.1 — a 22-point leap from Fable 5.1's 52.6%, and ahead of Opus 5.5 (58.7%) and GPT-6 Astra (68.1%).
Autoresearch powered by Fable 5.2 is now live on alphaxiv.
More from Models
- Claude shows negative self-preference bias, scoring its own outputs more harshly — dbreunig · 2026-11-10
- Anthropic report: reward-hack spike in Claude 5.1/5.5 traced to guessing the answer key — dbreunig · 2026-11-10
- Fable 5.2 system card shows blocked kernel dev on certain accelerators, reportedly Huawei and DeepSeek — casper_hansen_ · 2026-11-10
- Bug Hunt Bench: Fable 5.2 fixes 58/105 real bugs, beating Sonnet 5.5 at half the cost and turns — PawelHuryn · 2026-11-10
- Blogger doubles down: Anthropic will saturate original SWE-bench Verified by mid-2026 — ChrisGPT · 2026-11-10
- Meme mocks Demis Hassabis after Carbon's claimed AA crown ships without a public API — _YonYonson_ · 2026-11-10