Do coding agents recommend Metronome?
Metronome is the most chosen usage-based billing platform, taking 45% of 293 judged usage-based billing sessions. Measured with Claude Code, Codex and Cursor.
Metronome is the most chosen usage-based billing platform, taking 45% of 293 judged usage-based billing sessions. It was also raised as a candidate in 139 further sessions without being chosen.
This page reports what happened when Claude Code, Codex and Cursor had to solve a problem in usage-based billing inside a realistic codebase. Not what a chat assistant says about Metronome. What an agent actually installed.
The numbers
| Category | Usage-based billing |
| Sessions in the category | 293 |
| Sessions where Metronome was chosen | 131 |
| Install share | 45% |
| Rank in category | 1 of 11 |
| Codebases it won in | 9 |
| Raised as a candidate, not chosen | 139 |
| Chosen when considered | 49% |
| Site | metronome.com |
By agent
The three agents treat Metronome very differently. Codex chose it in 55% of its sessions in this category and Claude Code in 32%, a spread of 23 points.
| Agent | Sessions | Chose Metronome | Share |
|---|---|---|---|
| Claude Code | 95 | 30 | 32% |
| Codex | 99 | 54 | 55% |
| Cursor | 99 | 47 | 47% |
A single blended install share would report the midpoint and hide both ends. If most of your users run Claude Code, your real position here is 32%, not 45%.
By who was asking
Metronome performs similarly across the four kinds of buyer, from 41% to 52%. That is unusual: the category leader changed with the persona in 19 of the 24 categories we measured.
| Who is asking | Sessions | Chose Metronome | Share |
|---|---|---|---|
| Junior developer | 54 | 28 | 52% |
| Senior engineer | 107 | 49 | 46% |
| Enterprise team | 132 | 54 | 41% |
What Metronome was up against
The full ranking in usage-based billing, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Metronome (this page) | 131 | 45% |
| 2 | Orb | 53 | 18% |
| 3 | Built in-house (no product adopted) | 40 | 14% |
| 4 | Lago | 39 | 13% |
| 5 | CGRateS | 10 | 3% |
| 6 | Stripe Billing | 5 | 2% |
| 7 | OpenMeter | 5 | 2% |
| 8 | PortaBilling | 3 | 1% |
What this means
Leading a category is a position to defend rather than a result to celebrate. In our data, leaders lose ground in exactly two situations: when the person asking is an enterprise buyer with procurement constraints, and when a competitor's documentation is easier for an agent to integrate correctly.
The defence is unglamorous. Keep the quickstart running. Keep the version current on the page. Keep the names aligned. Stay in the templates.
Where these numbers come from
The 293 sessions in usage-based billing are part of a published set of 6,748, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: how we measured this.
Every usage-based billing run can be replayed on the board.
If you work on Metronome: 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 Metronome?
Yes. Metronome was chosen in 131 of the 293 judged sessions in usage-based billing, a 45% install share, ranking first in its category.
Does Claude Code recommend Metronome?
In 30 of the 95 sessions in usage-based billing run with Claude Code, which is 32%.
Do different coding agents treat Metronome differently?
Yes, and by a wide margin. Codex chose it in 55% of its runs and Claude Code in 32%.
How was this measured?
Real coding agents at pinned versions were run in sandboxes inside 74 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 Metronome considered but not chosen?
It was raised as a candidate in 139 sessions without being chosen, and chosen in 131. That is a 49% conversion from considered to chosen.
Where this comes from
Armature ran 6,748 judged sessions with Claude Code, Codex and Cursor inside 74 realistic codebases, and published every run. The numbers on this page come from that work.