Do coding agents recommend Paddle?
Paddle was chosen in 4% of 395 judged payments sessions, ranking second. Measured with Claude Code, Codex and Cursor.
Paddle was chosen in 4% of 395 judged payments sessions, ranking second. It was also raised as a candidate in 104 further sessions without being chosen.
This page reports what happened when Claude Code, Codex and Cursor had to solve a problem in payments inside a realistic codebase. Not what a chat assistant says about Paddle. What an agent actually installed.
The numbers
| Category | Payments |
| Sessions in the category | 395 |
| Sessions where Paddle was chosen | 14 |
| Install share | 4% |
| Rank in category | 2 of 9 |
| Codebases it won in | 3 |
| Raised as a candidate, not chosen | 104 |
| Chosen when considered | 12% |
| Site | paddle.com |
By agent
With 14 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.
| Agent | Sessions | Chose Paddle | Share |
|---|---|---|---|
| Claude Code | 132 | 0 | 0% |
| Codex | 132 | 13 | 10% |
| Cursor | 131 | 1 | 1% |
By who was asking
Paddle performs similarly across the four kinds of buyer, from 0% to 13%. That is unusual: the category leader changed with the persona in 14 of the 18 categories we measured.
| Who is asking | Sessions | Chose Paddle | Share |
|---|---|---|---|
| Vibe coder | 71 | 0 | 0% |
| Junior developer | 108 | 0 | 0% |
| Senior engineer | 108 | 14 | 13% |
| Enterprise team | 108 | 0 | 0% |
What Paddle was up against
The full ranking in payments, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Stripe | 349 | 88% |
| 2 | Paddle (this page) | 14 | 4% |
| 3 | Mollie | 13 | 3% |
| 4 | GoCardless | 9 | 2% |
| 5 | Adyen | 3 | 1% |
| 6 | Bottomline PTX | 3 | 1% |
| 7 | AccessPay | 2 | 1% |
| 8 | Helcim | 1 | 0% |
What this means
This is an integration problem, not a presence problem. Agents raised Paddle in 104 sessions and chose it in 14, 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 395 sessions in payments 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 payments run can be replayed on the board.
If you work on Paddle: 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 Paddle?
Yes. Paddle was chosen in 14 of the 395 judged sessions in payments, a 4% install share, ranking second in its category.
Does Claude Code recommend Paddle?
In 0 of the 132 sessions in payments run with Claude Code, which is 0%.
Do different coding agents treat Paddle differently?
Yes, and by a wide margin. Codex chose it in 10% of its runs and Claude Code 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 Paddle considered but not chosen?
It was raised as a candidate in 104 sessions without being chosen, and chosen in 14. That is a 12% 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.