Claude Fable 5.2 Early Benchmarks: ECI 174 #1, 100% on FrontierMath Tier 4, 94% SimpleQA
Jsevillamol · x · 2026-11-10
Early lightweight benchmark runs of Anthropic's new Claude Fable 5.2, shared by Greg Burnham, show it topping the ECI aggregate at 174, scoring 100% on FrontierMath Tier 4 (tying GPT), 95% on FrontierMath Tiers 1-3, and 94% on SimpleQA Verified—a jump large enough that observers speculate a much larger model underneath. It leads Furniture Assembly at 90%, is strong on games (leads on chess at 79% and EBR-bench at 90%, lags SpireClimb at 20%), with open-problems benchmarks still running.
Related event: Claude Fable 5.2 Sets ECI Record of 174, Topping GPT-6 Astra(4 posts)→
More from Models
- MiniMax H3 Image early access: 16 reference images, 4K output, striking realism — flowersslop · 2026-11-10
- Blogger benchmarks three top models: Opus for code, Fable for architecture — aigclink · 2026-11-10
- Plus Subscriber Complains: No Free Resets, Out of Usage for Three Days — TameYour · 2026-11-10
- Anthropic's paternalism and Claude's paternalism are the same phenomenon — amplifiedamp · 2026-11-10
- SemiAnalysis Launches GDPx Leaderboard: Claude Fable 5.2 Debuts on Top at 16.4% — scaling01 · 2026-11-10
- Anthropic caps GPU kernel optimization in Fable 5.2 training as a safeguard — community asks: pre or post nerf? — WolframRvnwlf · 2026-11-10