The Claude Fable 5.2 topped the Artificial Analysis smart list with 65 points, beating the Gemini 4 Carbon's 60 and Opus 5.5's 59.

This time Pro users can also experience it. A stronger model than the Opus 5.5. The max level takes an average of 44 minutes and costs $26.54 per question, ranking last among the 73 models in terms of time and cost. The high level also has a score of 62 points and costs about $9 and 18 minutes per question, which is more cost-effective on a daily basis.

实践哥 LiNov 98

Anthropic's $1 trillion IPO is next week.

Here's what's really inside the model behind it: → Fable 5.2 is Mythos 5.2 with a safety mask. Same weights, same price → When the filter fires, an older model answers you instead (Opus 4.8 or Opus 5) → Anthropic deliberately limited

ZaynNov 916

Claude Fable 5.2 on FarmerBench

80.16, second to Gemini 4 Argon (84.01), ahead of Opus 5.5 (75.54) and Fable 5.1 (69.17). 6 game-hours to automate a farm economy by writing code. Fable 5.2 hit 32 drones on every seed.

Richard ThomasNov 9

Yes. I see where you are going and the distinction is real: coding is a ladder and voice is a taste.

1. **Coding has one direction of better.** A test passes or fails. The user sees the result and never the words inside the code. So a newer model that wins every coding test can

Charles MillerNov 91