Model Releases
On FrontierCode (Extended), our benchmark for real-world engineering tasks that grades mergeability and quality, Sonnet 5 scores 53.8% and h…
On FrontierCode (Extended), our benchmark for real-world engineering tasks that grades mergeability and quality, Sonnet 5 scores 53.8% and has a 57.6% pass rate (higher than Opus 4.8). Note: These rel
On FrontierCode (Extended), our benchmark for real-world engineering tasks that grades mergeability and quality, Sonnet 5 scores 53.8% and has a 57.6% pass rate (higher than Opus 4.8). Note: These relative rankings may change slightly with coming adjustments to FrontierCode. https://devin.ai/blog/claude-sonnet-5
Source: Cognition AI (X) | 2026-06-30