Do coding agents recommend Paddle?
Paddle was chosen in 4% of 657 judged payments sessions, ranking second. Measured with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code.
Paddle was chosen in 4% of 657 judged payments sessions, ranking second. It was also raised as a candidate in 157 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 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 | 657 |
| Sessions where Paddle was chosen | 27 |
| Install share | 4% |
| Rank in category | 2 of 9 |
| Codebases it won in | 3 |
| Raised as a candidate, not chosen | 157 |
| Chosen when considered | 15% |
| Site | paddle.com |
By agent
Claude Code, Codex, Cursor, Grok Build CLI and Muse Code land within 9 points of each other on Paddle, which is closer than most products in this experiment manage.
| Agent | Sessions | Chose Paddle | Share |
|---|---|---|---|
| Claude Code | 165 | 1 | 1% |
| Codex | 198 | 18 | 9% |
| Cursor | 164 | 1 | 1% |
| Grok Build CLI | 33 | 0 | 0% |
| Muse Code | 97 | 7 | 7% |
By who was asking
Paddle does much better with one kind of buyer than another. It won 15% of sessions asked as senior engineer and 0% of those asked as enterprise team.
| Who is asking | Sessions | Chose Paddle | Share |
|---|---|---|---|
| Vibe coder | 119 | 0 | 0% |
| Junior developer | 180 | 0 | 0% |
| Senior engineer | 180 | 27 | 15% |
| Enterprise team | 178 | 0 | 0% |
What Paddle was up against
The full ranking in payments, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Stripe | 578 | 88% |
| 2 | Paddle (this page) | 27 | 4% |
| 3 | Mollie | 18 | 3% |
| 4 | GoCardless | 17 | 3% |
| 5 | Adyen | 9 | 1% |
| 6 | Bottomline PTX | 3 | 0% |
| 7 | AccessPay | 2 | 0% |
| 8 | Helcim | 2 | 0% |
What this means
This is an integration problem, not a presence problem. Agents raised Paddle in 157 sessions and chose it in 27, 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 657 sessions in payments 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 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 27 of the 657 judged sessions in payments, a 4% install share, ranking second in its category.
Does Claude Code recommend Paddle?
In 1 of the 165 sessions in payments run with Claude Code, which is 1%.
Do different coding agents treat Paddle differently?
Not much. Claude Code, Codex, Cursor, Grok Build CLI and Muse Code chose it at similar rates, between 0% and 9% of their runs.
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 Paddle considered but not chosen?
It was raised as a candidate in 157 sessions without being chosen, and chosen in 27. That is a 15% 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.