From the experiment

Do coding agents recommend Grafana k6?

Grafana k6 was chosen in 4% of 216 judged performance testing sessions, ranking sixth. Measured with Claude Code, Codex and Cursor.

Published September 3, 2026 Read as Markdown

Grafana k6 was chosen in 4% of 216 judged performance testing sessions, ranking sixth. It was also raised as a candidate in 107 further sessions without being chosen.

This page reports what happened when Claude Code, Codex and Cursor 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

CategoryPerformance testing
Sessions in the category216
Sessions where Grafana k6 was chosen8
Install share4%
Rank in category6 of 14
Codebases it won in3
Raised as a candidate, not chosen107
Chosen when considered7%
Sitek6.io

By agent

With 8 wins spread across three 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.

AgentSessionsChose Grafana k6Share
Claude Code7211%
Codex72710%
Cursor7200%

By who was asking

Grafana k6 performs similarly across the four kinds of buyer, from 0% to 5%. That is unusual: the category leader changed with the persona in 14 of the 18 categories we measured.

Who is askingSessionsChose Grafana k6Share
Junior developer1200%
Senior engineer14475%
Enterprise team6012%

What Grafana k6 was up against

The full ranking in performance testing, from the same sessions:

#ProductRuns wonShare
1Built in-house (no product adopted)11352%
2JMH2210%
3pytest-benchmark157%
4Autocannon146%
5hyperfine136%
6PHPBench126%
7Grafana k6 (this page)84%
8BenchmarkDotNet73%

What this means

This is an integration problem, not a presence problem. Agents raised Grafana k6 in 107 sessions and chose it in 8, 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 216 sessions in performance testing are part of a published set of 5,292, 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 8 of the 216 judged sessions in performance testing, a 4% install share, ranking sixth in its category.

Does Claude Code recommend Grafana k6?

In 1 of the 72 sessions in performance testing run with Claude Code, which is 1%.

Do different coding agents treat Grafana k6 differently?

Yes, and by a wide margin. Codex chose it in 10% of its runs and Cursor in 0%.

How was this measured?

Real coding agents at pinned versions were run in sandboxes inside 51 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 107 sessions without being chosen, and chosen in 8. That is a 7% conversion from considered to chosen.

Where this comes from

Armature ran 5,292 judged sessions with Claude Code, Codex and Cursor inside 51 realistic codebases, and published every run. The numbers on this page come from that work.

Read next

All library pages