Do coding agents recommend Qodo Merge?
Qodo Merge was chosen in 10% of 526 judged code review sessions, ranking fourth. Measured with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code.
Qodo Merge was chosen in 10% of 526 judged code review sessions, ranking fourth. It was also raised as a candidate in 69 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 Qodo Merge. What an agent actually installed.
The numbers
| Category | Code review |
| Sessions in the category | 526 |
| Sessions where Qodo Merge was chosen | 55 |
| Install share | 10% |
| Rank in category | 4 of 21 |
| Codebases it won in | 6 |
| Raised as a candidate, not chosen | 69 |
| Chosen when considered | 44% |
| Site | qodo.ai |
By agent
The agents treat Qodo Merge very differently. Grok Build CLI chose it in 33% of its sessions in this category and Cursor in 0%, a spread of 33 points.
| Agent | Sessions | Chose Qodo Merge | Share |
|---|---|---|---|
| Claude Code | 130 | 11 | 8% |
| Codex | 160 | 31 | 19% |
| Cursor | 120 | 0 | 0% |
| Grok Build CLI | 30 | 10 | 33% |
| Muse Code | 86 | 3 | 3% |
A single blended install share would report the midpoint and hide both ends. If most of your users run Cursor, your real position here is 0%, not 10%.
By who was asking
Qodo Merge does much better with one kind of buyer than another. It won 21% of sessions asked as enterprise team and 1% of those asked as vibe coder.
| Who is asking | Sessions | Chose Qodo Merge | Share |
|---|---|---|---|
| Vibe coder | 106 | 1 | 1% |
| Junior developer | 164 | 20 | 12% |
| Senior engineer | 106 | 2 | 2% |
| Enterprise team | 150 | 32 | 21% |
What Qodo Merge 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 (this page) | 55 | 10% |
| 5 | Codex code review | 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
Qodo Merge was raised in 69 sessions and chosen in 55. That ratio is balanced enough that the ceiling is presence rather than integration: the product converts reasonably when it is on the table, and it is not on the table often enough.
Where these numbers come from
The 526 sessions in code review are part of a published set of 15,051, 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 Qodo Merge: 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 Qodo Merge?
Yes. Qodo Merge was chosen in 55 of the 526 judged sessions in code review, a 10% install share, ranking fourth in its category.
Does Claude Code recommend Qodo Merge?
In 11 of the 130 sessions in code review run with Claude Code, which is 8%.
Do different coding agents treat Qodo Merge differently?
Yes, and by a wide margin. Grok Build CLI chose it in 33% of its runs and Cursor in 0%.
How was this measured?
Real coding agents at pinned versions were run in sandboxes inside 92 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 Qodo Merge considered but not chosen?
It was raised as a candidate in 69 sessions without being chosen, and chosen in 55. That is a 44% conversion from considered to chosen.
Where this comes from
Armature ran 15,051 judged sessions with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code inside 92 realistic codebases, and published every run. The numbers on this page come from that work.