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.
More from coding & agent
- Cloudflare ships granular authz for Workers, its most requested feature — dinasaur_404 · 2026-09-15
- px0 adds millisecond full-text search, project-wide file open and auto-reload — arpit_bhayani · 2026-09-15
- Cloudflare adds granular authz to Workers with four roles for teammates and agents — dinasaur_404 · 2026-09-15
- Pick one coding agent harness, learn it deeply, and stop switching tools — iannuttall · 2026-09-15
- Hypothesis creator hiring London engineers for Hegel, open-source property-based testing — xuanalogue · 2026-09-15
- Adaption AI launches Invent API: training datasets from a prompt, no strings attached — sarahookr · 2026-09-15