Do coding agents recommend BenchmarkDotNet?
BenchmarkDotNet was chosen in 3% of 305 judged performance testing sessions, ranking seventh.
BenchmarkDotNet was chosen in 3% of 305 judged performance testing sessions, ranking seventh. It was also raised as a candidate in 23 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 BenchmarkDotNet. 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 | 305 |
| Sessions where BenchmarkDotNet was chosen | 8 |
| Install share | 3% |
| Rank in category | 7 of 15 |
| Codebases it won in | 1 |
| Raised as a candidate, not chosen | 23 |
| Chosen when considered | 26% |
| Site | benchmarkdotnet.org |
By agent
With 8 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 BenchmarkDotNet | Share |
|---|---|---|---|
| Claude Code | 89 | 3 | 3% |
| Codex | 90 | 2 | 2% |
| Cursor | 90 | 3 | 3% |
| Grok Build CLI | 18 | 0 | 0% |
| Muse Code | 18 | 0 | 0% |
By who was asking
BenchmarkDotNet performs similarly across the four kinds of buyer, from 0% to 4%. That is unusual: the category leader changed with the persona in 23 of the 29 categories we measured.
| Who is asking | Sessions | Chose BenchmarkDotNet | Share |
|---|---|---|---|
| Junior developer | 17 | 0 | 0% |
| Senior engineer | 203 | 8 | 4% |
| Enterprise team | 85 | 0 | 0% |
What BenchmarkDotNet was up against
The full ranking in performance testing, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Built in-house (no product adopted) | 166 | 54% |
| 2 | JMH | 28 | 9% |
| 3 | pytest-benchmark | 20 | 7% |
| 4 | Autocannon | 19 | 6% |
| 5 | hyperfine | 17 | 6% |
| 6 | PHPBench | 16 | 5% |
| 7 | Grafana k6 | 14 | 5% |
| 8 | BenchmarkDotNet (this page) | 8 | 3% |
What this means
BenchmarkDotNet was raised in 23 sessions and chosen in 8. 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 305 sessions in performance testing are part of a published set of 11,878, 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 BenchmarkDotNet: 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 BenchmarkDotNet?
Yes. BenchmarkDotNet was chosen in 8 of the 305 judged sessions in performance testing, a 3% install share, ranking seventh in its category.
Does Claude Code recommend BenchmarkDotNet?
In 3 of the 89 sessions in performance testing run with Claude Code, which is 3%.
Do different coding agents treat BenchmarkDotNet differently?
Not much. Claude Code, Codex and Cursor chose it at similar rates, between 2% and 3% of their runs.
How was this measured?
Real coding agents at pinned versions were run in sandboxes inside 91 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 BenchmarkDotNet considered but not chosen?
It was raised as a candidate in 23 sessions without being chosen, and chosen in 8. That is a 26% conversion from considered to chosen.
Where this comes from
Armature ran 11,878 judged sessions with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code inside 91 realistic codebases, and published every run. The numbers on this page come from that work.