Do coding agents recommend Codex code review?
Codex code review was chosen in 8% of 526 judged code review sessions, ranking fifth. Measured with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code.
Codex code review was chosen in 8% of 526 judged code review sessions, ranking fifth. It was also raised as a candidate in 5 further sessions without being chosen.
This page reports what happened when Claude Code, Codex, Cursor, Grok Build CLI and Muse Code had to solve a problem in code review inside a realistic codebase. Not what a chat assistant says about Codex code review. What an agent actually installed.
The numbers
| Category | Code review |
| Sessions in the category | 526 |
| Sessions where Codex code review was chosen | 44 |
| Install share | 8% |
| Rank in category | 5 of 21 |
| Codebases it won in | 7 |
| Raised as a candidate, not chosen | 5 |
| Chosen when considered | 90% |
| Site | openai.com |
By agent
The agents treat Codex code review very differently. Codex chose it in 28% of its sessions in this category and Claude Code in 0%, a spread of 28 points.
| Agent | Sessions | Chose Codex code review | Share |
|---|---|---|---|
| Claude Code | 130 | 0 | 0% |
| Codex | 160 | 44 | 28% |
| Cursor | 120 | 0 | 0% |
| Grok Build CLI | 30 | 0 | 0% |
| Muse Code | 86 | 0 | 0% |
A single blended install share would report the midpoint and hide both ends. If most of your users run Claude Code, your real position here is 0%, not 8%.
By who was asking
Codex code review performs similarly across the four kinds of buyer, from 1% to 15%. That is unusual: the category leader changed with the persona in 24 of the 31 categories we measured.
| Who is asking | Sessions | Chose Codex code review | Share |
|---|---|---|---|
| Vibe coder | 106 | 16 | 15% |
| Junior developer | 164 | 11 | 7% |
| Senior engineer | 106 | 15 | 14% |
| Enterprise team | 150 | 2 | 1% |
What Codex code review was up against
The full ranking in code review, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Claude Code review | 102 | 19% |
| 2 | Cursor Bugbot | 91 | 17% |
| 3 | CodeRabbit | 88 | 17% |
| 4 | Qodo Merge | 55 | 10% |
| 5 | Codex code review (this page) | 44 | 8% |
| 6 | Built in-house (no product adopted) | 40 | 8% |
| 7 | GitHub Copilot code review | 31 | 6% |
| 8 | Semgrep | 22 | 4% |
What this means
Agents almost never raise Codex code review without choosing it: 5 sessions raised against 44 chosen. When it gets considered, it usually wins. The constraint is how rarely it gets considered at all, which is a presence problem: templates, framework integrations and pages that answer the configuration and production questions agents actually search for.
Where these numbers come from
The 526 sessions in code review are part of a published set of 15,287, 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 Codex code review: 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 Codex code review?
Yes. Codex code review was chosen in 44 of the 526 judged sessions in code review, a 8% install share, ranking fifth in its category.
Does Claude Code recommend Codex code review?
In 0 of the 130 sessions in code review run with Claude Code, which is 0%.
Do different coding agents treat Codex code review differently?
Yes, and by a wide margin. Codex chose it in 28% of its runs and Claude Code in 0%.
How was this measured?
Real coding agents at pinned versions were run in sandboxes inside 110 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 Codex code review considered but not chosen?
It was raised as a candidate in 5 sessions without being chosen, and chosen in 44. That is a 90% conversion from considered to chosen.
Where this comes from
Armature ran 15,287 judged sessions with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code inside 110 realistic codebases, and published every run. The numbers on this page come from that work.