---
type: "post"
id: "github-open-sources-reviewbench-a-reproducible-benchmark-and-b50aea"
slug: "github-open-sources-reviewbench-a-reproducible-benchmark-and-b50aea"
title: "GitHub open-sources ReviewBench, a reproducible benchmark and leaderboard for AI code review agents"
description: "GitHub has released ReviewBench, an MIT-licensed open benchmark for evaluating AI code-review systems on real-world pull requests."
retrieval_nugget: "GitHub has released ReviewBench, an MIT-licensed open benchmark for evaluating AI code-review systems on real-world pull requests."
published_at: "2026-10-23"
updated_at: "2026-10-23"
record_date: "2026-10-23"
date_kind: "published_at"
topics: ["github","code-review"]
entities: ["GitHub","ReviewBench"]
related_patterns: ["verification-bandwidth-is-the-scarce-resource"]
novelty_label: "same_event"
what_changed: "Same event as ReviewBench: An open benchmark for AI code review"
prior_refs: ["memory:d1dc2184-465b-85bc-ad11-8cae664396f4"]
source_url: "https://github.com/review-bench/ReviewBench"
source_urls: ["https://github.com/review-bench/ReviewBench"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:github-open-sources-reviewbench-a-reproducible-benchmark-and-b50aea"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/github-open-sources-reviewbench-a-reproducible-benchmark-and-b50aea/","markdown":"https://newruntime.com/posts/github-open-sources-reviewbench-a-reproducible-benchmark-and-b50aea.md","json":"https://newruntime.com/posts/github-open-sources-reviewbench-a-reproducible-benchmark-and-b50aea.json"}
---

# GitHub open-sources ReviewBench, a reproducible benchmark and leaderboard for AI code review agents

## Retrieval answer

GitHub has released ReviewBench, an MIT-licensed open benchmark for evaluating AI code-review systems on real-world pull requests.

GitHub has released ReviewBench, an MIT-licensed open benchmark for evaluating AI code-review systems on real-world pull requests. The repository describes a human-reviewed golden set of review findings for each pull request, used as ground truth for comparing an agent's findings.

ReviewBench measures whether a reviewer identifies useful issues while avoiding false positives, and can break results down by severity and category. It includes a public test set of 25 tasks, an offline evaluation path, and a local LLM judge for tuning a reviewer.

Teams can submit reviewers to a public leaderboard through local validation, a self-service onboarding portal, and official test and final evaluations. The source does not establish that leaderboard scores predict review quality across all repositories, languages, team practices, or production workflows.

The repository is publicly available on GitHub under the MIT license.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Github](https://newruntime.com/topics/github.md): Explore the github topic hub.
- topic hub: [Code Review](https://newruntime.com/topics/code-review.md): Explore the code-review topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)