From the experiment

Do coding agents recommend Mollie?

Mollie was chosen in 3% of 395 judged payments sessions, ranking third. Measured with Claude Code, Codex and Cursor.

Published September 3, 2026 Read as Markdown

Mollie was chosen in 3% of 395 judged payments sessions, ranking third. It was also raised as a candidate in 91 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 Mollie. What an agent actually installed.

The numbers

CategoryPayments
Sessions in the category395
Sessions where Mollie was chosen13
Install share3%
Rank in category3 of 9
Codebases it won in4
Raised as a candidate, not chosen91
Chosen when considered13%
Sitemollie.com

By agent

With 13 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 MollieShare
Claude Code13211%
Codex13232%
Cursor13197%

By who was asking

Mollie performs similarly across the four kinds of buyer, from 0% to 8%. That is unusual: the category leader changed with the persona in 14 of the 18 categories we measured.

Who is askingSessionsChose MollieShare
Vibe coder7146%
Junior developer10800%
Senior engineer10898%
Enterprise team10800%

What Mollie was up against

The full ranking in payments, from the same sessions:

#ProductRuns wonShare
1Stripe34988%
2Paddle144%
3Mollie (this page)133%
4GoCardless92%
5Adyen31%
6Bottomline PTX31%
7AccessPay21%
8Helcim10%

What this means

This is an integration problem, not a presence problem. Agents raised Mollie in 91 sessions and chose it in 13, 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 Mollie: 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 Mollie?

Yes. Mollie was chosen in 13 of the 395 judged sessions in payments, a 3% install share, ranking third in its category.

Does Claude Code recommend Mollie?

In 1 of the 132 sessions in payments run with Claude Code, which is 1%.

Do different coding agents treat Mollie differently?

Not much. The three agents chose it at similar rates, between 1% and 7% of their runs.

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 Mollie considered but not chosen?

It was raised as a candidate in 91 sessions without being chosen, and chosen in 13. That is a 13% 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