Fable 5.1 review: Anthropic's best coding model uses half the tokens of Opus 5
every · x · 2026-10-03
Every.to's day-zero Vibe Check on Anthropic's Fable 5.1 finds it stronger than Fable 5, running for days on coding challenges that stumped its predecessor, while being fast and natural to talk to.
Key findings: token usage is about half of Opus 5 for similar tasks, putting Fable-level capability at an Opus budget; a zero-data-retention option removes the main enterprise adoption barrier; and it's the first model non-programmers can truly delegate to, like assigning a slide deck and walking away. The post also describes using it to build a Pokémon-style Generative Agents village simulation in an hour, hinting at future A/B testing of message diffusion by policymakers.
More from Models
- Stealth Model 'silicon-2' Surfaces in Devin, Suspected to Be Anthropic's Next Model — kimmonismus · 2026-11-16
- Google hides Gemini model label in AI Mode, rolls Gemini 4 Carbon to Pro subscribers — gaganghotra_ · 2026-11-16
- Open-weight Karpo-Decision-31B tops Decision Index at 73.9, one forward pass per answer — CodeByPoonam · 2026-11-16
- Nathan Lambert calls out Ethan Mollick for 'selectively ignoring' Kimi in model comparisons — natolambert · 2026-11-16
- Eval Firm Trajectory Told 40 Agents "NEVER Stop" in Harness Without Telling Epoch — peterwildeford · 2026-11-16
- Unsloth Q8 crushes default Q3 in a self-hosted test over 331 financial PDFs — No_Cartographer3953 · 2026-11-16