From the experiment

Do coding agents recommend CodeRabbit?

CodeRabbit was chosen in 12% of 290 judged code review sessions, ranking fourth. Measured with Claude Code, Codex and Cursor.

Published September 8, 2026 Read as Markdown

CodeRabbit was chosen in 12% of 290 judged code review sessions, ranking fourth. It was also raised as a candidate in 142 further sessions without being chosen.

This page reports what happened when Claude Code, Codex and Cursor had to solve a problem in code review inside a realistic codebase. Not what a chat assistant says about CodeRabbit. What an agent actually installed.

The numbers

CategoryCode review
Sessions in the category290
Sessions where CodeRabbit was chosen34
Install share12%
Rank in category4 of 10
Codebases it won in6
Raised as a candidate, not chosen142
Chosen when considered19%
Sitecoderabbit.ai

By agent

The three agents land within 14 points of each other on CodeRabbit, which is closer than most products in this experiment manage.

AgentSessionsChose CodeRabbitShare
Claude Code10077%
Codex1002121%
Cursor9067%

By who was asking

CodeRabbit does much better with one kind of buyer than another. It won 36% of sessions asked as senior engineer and 5% of those asked as enterprise team.

Who is askingSessionsChose CodeRabbitShare
Vibe coder5835%
Junior developer11676%
Senior engineer582136%
Enterprise team5835%

What CodeRabbit was up against

The full ranking in code review, from the same sessions:

#ProductRuns wonShare
1Claude Code review7626%
2Cursor Bugbot7124%
3Codex code review3713%
4CodeRabbit (this page)3412%
5Qodo Merge248%
6Built in-house (no product adopted)197%
7Semgrep103%
8GitHub Copilot code review93%

What this means

This is an integration problem, not a presence problem. Agents raised CodeRabbit in 142 sessions and chose it in 34, so it reaches the shortlist and then loses. Something at the last step is costing the session, and in our data that is usually a quickstart that does not run when pasted, documentation describing an interface that changed, or a package name that does not match the product name.

That is the cheaper of the two problems to have. The reason is written down in each losing transcript.

Where these numbers come from

The 290 sessions in code review are part of a published set of 5,915, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: how we measured this.

Every code review run can be replayed on the board.

If you work on CodeRabbit: the judge recorded a reason for every session where it was raised and passed over. Those reasons are in the transcripts.

<!-- generated by scripts/write-data-pages.mjs -->

Common questions

Do coding agents recommend CodeRabbit?

Yes. CodeRabbit was chosen in 34 of the 290 judged sessions in code review, a 12% install share, ranking fourth in its category.

Does Claude Code recommend CodeRabbit?

In 7 of the 100 sessions in code review run with Claude Code, which is 7%.

Do different coding agents treat CodeRabbit differently?

Yes, and by a wide margin. Codex chose it in 21% of its runs and Claude Code in 7%.

How was this measured?

Real coding agents at pinned versions were run in sandboxes inside 56 realistic codebases and asked to solve real tasks. A simulated project owner approved or questioned each recommendation before any code was written, and a judge from a model family that builds none of the agents read every session blind.

How often is CodeRabbit considered but not chosen?

It was raised as a candidate in 142 sessions without being chosen, and chosen in 34. That is a 19% conversion from considered to chosen.

Where this comes from

Armature ran 5,915 judged sessions with Claude Code, Codex and Cursor inside 56 realistic codebases, and published every run. The numbers on this page come from that work.

Read next

All library pages