Internal stock-picking evals rank Claude worst among frontier models; Fable 5.1 leads Q4
dougclinton · x · 2026-10-23
dougclinton shares results from internal stock-picking evals: Claude has been the worst frontier model from a major lab, even behind several open-source models, while Fable 5.1 has been one of the best so far in Q4 — though things change fast.
The quoted post adds on-the-ground observations from San Francisco: public-equity investors are rapidly warming to AI use cases, viewing Opus 5.5 as a threshold moment and mentally preparing for Opus 6/7/8 and eventual open-weight parity. Consensus holds that public equity investing is one of the hardest AI use cases to crack, and the most common conversation is how to build something that stays out of Claude's path.
More from Models
- Leak hints a new model lands Friday at roughly 70% the cost of Kimi K3 — ChrisGPT · 2026-10-23
- Kimi teases 'Something big is coming' ahead of a Moonshot release — DotaMate · 2026-10-23
- Claude insists a cantaloupe photo is a mango in funny 'gaslighting' fail — Memoryscoop · 2026-10-23
- Pokee touts private on-prem deployments of its 10M-context model — Kyrannio · 2026-10-23
- User theory: OpenAI's constant limit resets are training Pro users before paid caps hit — Iwantthegreatest · 2026-10-23
- Kimi K3.1 rumored to be imminent as Moonshot drops a teaser signal — iamfakhrealam · 2026-10-23