Do coding agents recommend Orb?
Orb was chosen in 18% of 293 judged usage-based billing sessions, ranking second. Measured with Claude Code, Codex and Cursor.
Orb was chosen in 18% of 293 judged usage-based billing sessions, ranking second. It was also raised as a candidate in 218 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 Orb. What an agent actually installed.
The numbers
| Category | Usage-based billing |
| Sessions in the category | 293 |
| Sessions where Orb was chosen | 53 |
| Install share | 18% |
| Rank in category | 2 of 11 |
| Codebases it won in | 9 |
| Raised as a candidate, not chosen | 218 |
| Chosen when considered | 20% |
| Site | withorb.com |
By agent
The three agents land within 14 points of each other on Orb, which is closer than most products in this experiment manage.
| Agent | Sessions | Chose Orb | Share |
|---|---|---|---|
| Claude Code | 95 | 24 | 25% |
| Codex | 99 | 18 | 18% |
| Cursor | 99 | 11 | 11% |
By who was asking
Orb performs similarly across the four kinds of buyer, from 15% to 28%. That is unusual: the category leader changed with the persona in 19 of the 24 categories we measured.
| Who is asking | Sessions | Chose Orb | Share |
|---|---|---|---|
| Junior developer | 54 | 15 | 28% |
| Senior engineer | 107 | 18 | 17% |
| Enterprise team | 132 | 20 | 15% |
What Orb was up against
The full ranking in usage-based billing, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Metronome | 131 | 45% |
| 2 | Orb (this page) | 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
A solid second or third position in a category means the agent is genuinely choosing rather than reaching automatically. That is a winnable position, because the inputs it uses can be changed.
The fastest gains are usually in the sessions that were nearly won: read them, find the step where the agent moved on, and fix that step.
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 Orb: 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 Orb?
Yes. Orb was chosen in 53 of the 293 judged sessions in usage-based billing, a 18% install share, ranking second in its category.
Does Claude Code recommend Orb?
In 24 of the 95 sessions in usage-based billing run with Claude Code, which is 25%.
Do different coding agents treat Orb differently?
Yes, and by a wide margin. Claude Code chose it in 25% of its runs and Cursor in 11%.
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 Orb considered but not chosen?
It was raised as a candidate in 218 sessions without being chosen, and chosen in 53. That is a 20% 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.