Alibaba open-sources Open Code Review: beats Claude Code on precision with ~1/9 tokens

techNmak · x · 2026-09-15

Alibaba open-sourced Open Code Review, a deterministic-pipeline code reviewer that uses agents only where reasoning helps. Born from an internal tool used by tens of thousands of devs, it identified millions of defects. On 200 real PRs from 50 repos, cross-validated by 80+ senior engineers, it beat Claude Code on precision and F1 with the same underlying model using 1/9 tokens, trading lower recall for fewer false positives.

Original post →

More from coding & agent

coding & agent channel →