Claude Opus 5 is now live in Devin Desktop and Devin CLI. It will also be part of Devin Cloud’s mode mix.
On FrontierCode 1.1, our proprietary benchmark that grades models on real-world engineering tasks based on quality and mergeability, Claude Opus 5 approaches Fable-level performance at half the cost. Within Devin, it also shows particular strength on difficult debugging and root-cause analysis tasks.
A few more patterns stand out from our evaluations:
- On bug fixing tasks, it prefers targeted, in-place fixes over large refactors.
- It is great at adhering to existing repo conventions when building new features and writing tests.
- It excels at following specs closely and completely.
FrontierCode 1.1 ExtendedScore
Try Devin Cloud · Download Devin Desktop · Install Devin CLI