Fable 5.2 Tops Experiment-Prediction Benchmark at 0.36, Best Model Tested
SamuelAlbanie · x · 2026-11-10
Pzero Research announced that Claude Fable 5.2 is the best model they have tested at predicting experiment results, scoring 0.36 — in line with steady improvement since GPT-4 Turbo.
They note that predicting results before running an experiment is a core part of research taste: a model that does it well can skip bad experiments and get more progress from the same compute.
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