Research Open source Safety & ethics

ReviewBench: An open benchmark for AI code review

GitHub Michelle Zhou

Publication summary. The terms of GitHub do not allow reproduction of the full article: read the complete text on the original website.

Source summary (English)

We’re launching ReviewBench, a benchmark for code review agents built on representative GitHub pull requests, multi-source ground truth, calibrated evaluation, and production-aligned metrics. The post ReviewBench: An open benchmark for AI code review appeared first on The GitHub Blog.

Read the full article

github.blog

View on GitHub (new tab)

Topics

Share

X (new tab) LinkedIn (new tab) Facebook (new tab) Email

Related articles