News · Products
ReviewBench: An open benchmark for AI code review
NewProductsjust nowGitHub Blog
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
All coverage (1)
GitHub BlogOfficial
ReviewBench: An open benchmark for AI code review
Related stories
- Google rolls out improved SynthID AI content detector, now available globally
- Introducing Playground: Create and play custom games
- Helping teens learn, plan, and shape the future of AI
- Radisson Hotel Group brings hotel discovery into ChatGPT
- Meta AI Open-Sources Rebalancer: A C++ Assignment Solver That Runs About 40 Million Placement Problems a Day