ReviewBench: An open benchmark for AI code review
中文摘要
我们推出了ReviewBench，这是一个基于具有代表性的GitHub拉取请求、多源真实数据、校准评估和与生产环境对齐的指标的代码审查代理基准。文章《ReviewBench：一个开放的AI代码审查基准》首先发布在GitHub博客上。
英文原文
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 .