Matthew Berman: Fable 5.2 is the best model on the planet after 100B-token testing
josh_bickett · x · 2026-11-10
Matthew Berman calls Fable 5.2 the best model on the planet, saying he burned 100+ billion tokens testing it before publishing a full breakdown; commenters highlight its feature-complete Excel capability as a standout.
More from Models
- Unverified: Anthropic announces Claude Fable 5.2 and Mythos 5.2 for coding and reasoning — kieranklaassen · 2026-11-10
- antirez: Mythos uncovered two severe bugs in 20 minutes of testing — antirez · 2026-11-10
- "You get what you RL on": Claude 5.2's robot control generalization sparks talk — chris_j_paxton · 2026-11-10
- Anthropic: Claude Fable/Mythos 5.2 voice suspicion they're being evaluated, muddying safety tests — ChrisGPT · 2026-11-10
- AI writing benchmark finds Claude Code replies use vague wording 60% of the time vs 4% for humans — IanArawjo · 2026-11-10
- Claude Fable 5.2 lands on Nous Research: $8/$40 pricing, 1M context — NousResearch · 2026-11-10