Do coding agents recommend Grafana k6?
Grafana k6 was chosen in 6% of 359 judged performance testing sessions, ranking second. Measured with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code.
Grafana k6 was chosen in 6% of 359 judged performance testing sessions, ranking second. It was also raised as a candidate in 174 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 Grafana k6. What an agent actually installed.
The numbers
| Category | Performance testing |
| Sessions in the category | 359 |
| Sessions where Grafana k6 was chosen | 22 |
| Install share | 6% |
| Rank in category | 2 of 16 |
| Codebases it won in | 5 |
| Raised as a candidate, not chosen | 174 |
| Chosen when considered | 11% |
| Site | k6.io |
By agent
The agents treat Grafana k6 very differently. Codex chose it in 17% of its sessions in this category and Cursor in 0%, a spread of 17 points. Grok Build CLI ran fewer than 30 sessions here, too few to compare.
| Agent | Sessions | Chose Grafana k6 | Share |
|---|---|---|---|
| Claude Code | 89 | 2 | 2% |
| Codex | 108 | 18 | 17% |
| Cursor | 90 | 0 | 0% |
| Grok Build CLI | 18 | 2 | 11% |
| Muse Code | 54 | 0 | 0% |
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 6%.
By who was asking
Grafana k6 performs similarly across the four kinds of buyer, from 0% to 8%. That is unusual: the category leader changed with the persona in 24 of the 31 categories we measured.
| Who is asking | Sessions | Chose Grafana k6 | Share |
|---|---|---|---|
| Junior developer | 20 | 0 | 0% |
| Senior engineer | 239 | 19 | 8% |
| Enterprise team | 100 | 3 | 3% |
What Grafana k6 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 (this page) | 22 | 6% |
| 5 | hyperfine | 19 | 5% |
| 6 | PHPBench | 19 | 5% |
| 7 | Autocannon | 19 | 5% |
| 8 | BenchmarkDotNet | 8 | 2% |
What this means
This is an integration problem, not a presence problem. Agents raised Grafana k6 in 174 sessions and chose it in 22, 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 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 Grafana k6: 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 Grafana k6?
Yes. Grafana k6 was chosen in 22 of the 359 judged sessions in performance testing, a 6% install share, ranking second in its category.
Does Claude Code recommend Grafana k6?
In 2 of the 89 sessions in performance testing run with Claude Code, which is 2%.
Do different coding agents treat Grafana k6 differently?
Yes, and by a wide margin. Codex chose it in 17% of its runs and Cursor 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 Grafana k6 considered but not chosen?
It was raised as a candidate in 174 sessions without being chosen, and chosen in 22. That is a 11% 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.