First impressions: Fable 5.2 edges out Opus 5.5 in decision-making and post-training
haider1 · x · 2026-11-10
A heavy user shares hands-on impressions: Opus 5.5 was in a different league versus Fable 5 and 5.1, but Fable 5.2 takes a smaller step above Opus in general decision-making and tasks relying on feel and experience rather than pure reasoning. Fable 5.2 also appears to have notably better post-training than 5.1. Anecdotal, not a systematic eval.
Related event: Users Report Fable 5.2 Edges Out Opus 5.5 in Decision-Making(2 posts)→
More from Models
- Musk: xAI rebuilt Grok's RL training and inference stack from scratch in C, with Starlink engineers — elonmusk · 2026-11-10
- Running open-weight models locally: Kimi K3.1 needs 594GB, ~$38k for 15 tok/s — ravikantagrawal · 2026-11-10
- Consultant: banks larping 'sovereignty' with on-prem OSS models; bullish on Chinese providers — teodorio · 2026-11-10
- The most complete list of LLM writing tics yet: negation-first reveals, aphoristic closers — gleech · 2026-11-10
- Amazon swaps Sonnet 4.6 for a decision model in ticket labeling, cutting cost by 98% — victormustar · 2026-11-10
- banteg launches a live Sokoban eval for LLMs — banteg · 2026-11-10