---
title: "ReviewBench: An open benchmark for AI code review"
source: "GitHub Blog（网页）"
source_tier: "t1"
url: "https://github.blog/ai-and-ml/github-copilot/reviewbench-an-open-benchmark-for-ai-code-review/"
permalink: "https://feed.astralor.com/items/itm_e4f96ea3e7c3ac5d94a4995f"
published: "2026-10-05T15:59:40.000Z"
score: 54
channel: "tech"
tags: ["AI Agent","ReviewBench","GitHub"]
---

# ReviewBench: An open benchmark for AI code review

## 速览

ReviewBench is a benchmark for code review agents built on representative GitHub pull requests, multi-source ground truth, and calibrated evaluation.

## 关键点

- ReviewBench is a benchmark for code review agents built on representative GitHub pull requests, multi-source ground truth, and calibrated evaluation.

## 全文

ReviewBench is a benchmark for code review agents built on representative GitHub pull requests, multi-source ground truth, and calibrated evaluation.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_e4f96ea3e7c3ac5d94a4995f