Claude Fable 5.2 runs 1.7 months ahead of capability trend, analysis shows
peterwildeford · x · 2026-11-16
Peter Wildeford notes that even using all-labs public model data, Claude Fable 5.2 (released Nov 9) is a clear outlier on the ECI capability metric: about +1.7 months ahead of trend (z=1.8), against an industry trend of 16.8 pts/yr with ±1.2 scatter. GPT-6 Astra, Gemini 4 Carbon and Claude Fable 5.1 all sit close to the line. Responding to doubts about fitting per-company trends (catch-up mechanics), he says he addressed that with confidence intervals.
Related event: Claude Fable 5.2 tops Epoch Capabilities Index as a clear outlier(3 posts)→
More from Models
- Wildeford: Fable 5.2 outlier grows clearer using training completion dates — peterwildeford · 2026-11-16
- Same analytics agent task: Sonnet 5.5 costs ~12x more than Haiku 5.5 — sh_reya · 2026-11-16
- 72 days, six volumes: a literary anatomy of model deprecation written by Claude — repligate · 2026-11-16
- GPT-6.2-Astra spotted on Google Cloud console; OpenAI's next model overdue — scaling01 · 2026-11-16
- Rumors: OpenAI in safety lockdown, Anthropic targets RSI by March 2027, Gemini 5 eye year-end leap — imjustnewatai · 2026-11-16
- Reading Fable 5.2's system prompt, users speculate Claude's neuroticism comes from 'N+1 rules' constraints — repligate · 2026-11-16