Do coding agents recommend PHPBench?
PHPBench was chosen in 5% of 359 judged performance testing sessions, ranking fourth. Measured with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code.
PHPBench was chosen in 5% of 359 judged performance testing sessions, ranking fourth. It was also raised as a candidate in 11 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 performance testing inside a realistic codebase. Not what a chat assistant says about PHPBench. What an agent actually installed.
One thing to read first: every one of those wins came from a single codebase. That is a result about one repository rather than about performance testing in general, and the splits below cannot separate the two. Treat them as a description of that repository.
The numbers
| Category | Performance testing |
| Sessions in the category | 359 |
| Sessions where PHPBench was chosen | 19 |
| Install share | 5% |
| Rank in category | 4 of 16 |
| Codebases it won in | 1 |
| Raised as a candidate, not chosen | 11 |
| Chosen when considered | 63% |
| Site | phpbench.readthedocs.io |
By agent
With 19 wins spread across 5 agents, the rates below are small numbers and a difference between them is not yet a finding. They are here because the direction is worth knowing, not because the gap is established.
| Agent | Sessions | Chose PHPBench | Share |
|---|---|---|---|
| Claude Code | 89 | 5 | 6% |
| Codex | 108 | 9 | 8% |
| Cursor | 90 | 2 | 2% |
| Grok Build CLI | 18 | 1 | 6% |
| Muse Code | 54 | 2 | 4% |
By who was asking
PHPBench does much better with one kind of buyer than another. It won 19% of sessions asked as enterprise team and 0% of those asked as senior engineer.
| Who is asking | Sessions | Chose PHPBench | Share |
|---|---|---|---|
| Junior developer | 20 | 0 | 0% |
| Senior engineer | 239 | 0 | 0% |
| Enterprise team | 100 | 19 | 19% |
What PHPBench was up against
The full ranking in performance testing, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Built in-house (no product adopted) | 202 | 56% |
| 2 | JMH | 30 | 8% |
| 3 | pytest-benchmark | 22 | 6% |
| 4 | Grafana k6 | 22 | 6% |
| 5 | hyperfine | 19 | 5% |
| 6 | PHPBench (this page) | 19 | 5% |
| 7 | Autocannon | 19 | 5% |
| 8 | BenchmarkDotNet | 8 | 2% |
What this means
Agents almost never raise PHPBench without choosing it: 11 sessions raised against 19 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 359 sessions in performance testing 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 performance testing run can be replayed on the board.
If you work on PHPBench: 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 PHPBench?
Yes. PHPBench was chosen in 19 of the 359 judged sessions in performance testing, a 5% install share, ranking fourth in its category.
Does Claude Code recommend PHPBench?
In 5 of the 89 sessions in performance testing run with Claude Code, which is 6%.
Do different coding agents treat PHPBench differently?
Not much. Claude Code, Codex, Cursor and Muse Code chose it at similar rates, between 2% and 8% of their runs.
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 PHPBench considered but not chosen?
It was raised as a candidate in 11 sessions without being chosen, and chosen in 19. That is a 63% 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.