Model Releases
ReviewBench: An open benchmark for AI code review
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
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.
Related
- Coding agent tracing and evaluation: An open source tool to improve AI coding workflows
- AgentLens: Production-Assessed Trajectory Reviews for Coding Agent Evaluation
- Agentic Coding in the Wild: Characterizing GitHub Copilot Traces at Production Scale
- RealSWE: A Compositional Evaluation of Coding Agents under Realistic User Requests
Source: GitHub AI Blog | 2026-10-05