[](https://devin.ai/blog)

# Claude Fable 5.2 is now available in Devin

CognitionNovember 9, 20261 min read

Claude Fable 5.2 is now live in Devin.

On [FrontierCode 2.0](https://cognition.com/blog/frontier-code-2.0), our benchmark that evaluates models on real-world engineering tasks based on quality and mergeability, Fable 5.2 takes the top spot with a score of 49.1%. That’s a substantial step up from Fable 5.1’s 32.4%, and ahead of Opus 5.5’s 45.5%.

The improvement isn’t limited to its highest score. At low reasoning effort, Fable 5.2 already surpasses Fable 5.1’s best result at less than a third of the cost per task.

[FrontierCode LeaderboardBenchmarks for how well models meet the standards of high-quality production codebasesView Now](https://cognition.ai/frontiercode)

#### FrontierCode 2.0

#### FrontierCode 2.0vsCost ($)

Score is a weighted aggregate of the rubric items. Solutions that don’t pass blocking criteria receive 0.

Cost is the mean USD spend per rollout at list API pricing, including public discounts.

[Download Devin Desktop](https://devin.ai/download) · [Install Devin CLI](https://docs.devin.ai/cli)