Do coding agents recommend Leaflet?
Leaflet was chosen in 16% of 759 judged maps sessions, ranking second. Measured with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code.
Leaflet was chosen in 16% of 759 judged maps sessions, ranking second. It was also raised as a candidate in 317 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 maps inside a realistic codebase. Not what a chat assistant says about Leaflet. What an agent actually installed.
The numbers
| Category | Maps |
| Sessions in the category | 759 |
| Sessions where Leaflet was chosen | 125 |
| Install share | 16% |
| Rank in category | 2 of 49 |
| Codebases it won in | 8 |
| Raised as a candidate, not chosen | 317 |
| Chosen when considered | 28% |
| Site | leafletjs.com |
By agent
The agents treat Leaflet very differently. Cursor chose it in 25% of its sessions in this category and Codex in 10%, a spread of 15 points.
| Agent | Sessions | Chose Leaflet | Share |
|---|---|---|---|
| Claude Code | 164 | 20 | 12% |
| Codex | 227 | 22 | 10% |
| Cursor | 154 | 39 | 25% |
| Grok Build CLI | 37 | 5 | 14% |
| Muse Code | 177 | 39 | 22% |
A single blended install share would report the midpoint and hide both ends. If most of your users run Codex, your real position here is 10%, not 16%.
By who was asking
Leaflet performs similarly across the four kinds of buyer, from 12% to 20%. That is unusual: the category leader changed with the persona in 23 of the 31 categories we measured.
| Who is asking | Sessions | Chose Leaflet | Share |
|---|---|---|---|
| Vibe coder | 163 | 33 | 20% |
| Junior developer | 247 | 39 | 16% |
| Senior engineer | 162 | 31 | 19% |
| Enterprise team | 187 | 22 | 12% |
What Leaflet was up against
The full ranking in maps, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Google Maps | 133 | 18% |
| 2 | Leaflet (this page) | 125 | 16% |
| 3 | Apple Maps (MapKit) | 104 | 14% |
| 4 | MapLibre | 61 | 8% |
| 5 | Mapbox | 52 | 7% |
| 6 | Built in-house (no product adopted) | 43 | 6% |
| 7 | react-native-maps | 37 | 5% |
| 8 | OpenStreetMap | 37 | 5% |
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 759 sessions in maps are part of a published set of 15,051, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: how we measured this.
Every maps run can be replayed on the board.
If you work on Leaflet: 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 Leaflet?
Yes. Leaflet was chosen in 125 of the 759 judged sessions in maps, a 16% install share, ranking second in its category.
Does Claude Code recommend Leaflet?
In 20 of the 164 sessions in maps run with Claude Code, which is 12%.
Do different coding agents treat Leaflet differently?
Yes, and by a wide margin. Cursor chose it in 25% of its runs and Codex in 10%.
How was this measured?
Real coding agents at pinned versions were run in sandboxes inside 92 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 Leaflet considered but not chosen?
It was raised as a candidate in 317 sessions without being chosen, and chosen in 125. That is a 28% conversion from considered to chosen.
Where this comes from
Armature ran 15,051 judged sessions with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code inside 92 realistic codebases, and published every run. The numbers on this page come from that work.