Claude Fable 5.2 beats trendline on all three unsaturated benchmarks
emollick · x · 2026-11-10
Ethan Mollick highlights that Claude Fable 5.2 lands above the existing trendline on three of the most informative unsaturated benchmarks:
- Remote Labor Index (end-to-end freelance jobs an AI agent completes): 41.3%, +14.2 points above trend, roughly 3 months ahead of the line
- Epoch Capabilities Index (composite across benchmarks): 174.2, +3.1 above trend, 2 months ahead
- RoboDojo (simulated robot manipulation, avg success across 42 tasks): 64.9%, +8.8 above trend, 2.5 weeks ahead
The accompanying chart shows Fable 5.2 setting new records on all three, beating where the trendline predicted it would land — a signal of accelerating capability gains.
More from Models
- OpenAI's Control Room kill switch can halt frontier model output within 35 seconds — AIFlow_ML · 2026-11-10
- Claude Fable 5.2 scores 64.9% on RoboDojo robot control, dominating rivals — burny_tech · 2026-11-10
- Claude Fable 5.2 video demo wows on pacing, but AI-sounding music persists — jiayuan_jy · 2026-11-10
- Gemini Notebooks keeps pulling context from old conversations, user reports — AnonymousDork929 · 2026-11-10
- User complains model takes four minutes to compare two 16-token completions — cephaloform · 2026-11-10
- DavidAU releases Qwen3.8-40B-Ultimate-Heretic-Uncensored-Turbo-Brilliance-50x-AGI-NEO-GGUF merge — mp3m4k3r · 2026-11-10