Do coding agents recommend Google Maps?
Google Maps is the most chosen map product, taking 18% of 759 judged maps sessions. Measured with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code.
Google Maps is the most chosen map product, taking 18% of 759 judged maps sessions. It was also raised as a candidate in 474 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 Google Maps. What an agent actually installed.
The numbers
| Category | Maps |
| Sessions in the category | 759 |
| Sessions where Google Maps was chosen | 133 |
| Install share | 18% |
| Rank in category | 1 of 49 |
| Codebases it won in | 9 |
| Raised as a candidate, not chosen | 474 |
| Chosen when considered | 22% |
| Site | mapsplatform.google.com |
By agent
The agents treat Google Maps very differently. Codex chose it in 24% of its sessions in this category and Grok Build CLI in 3%, a spread of 21 points.
| Agent | Sessions | Chose Google Maps | Share |
|---|---|---|---|
| Claude Code | 164 | 19 | 12% |
| Codex | 227 | 54 | 24% |
| Cursor | 154 | 20 | 13% |
| Grok Build CLI | 37 | 1 | 3% |
| Muse Code | 177 | 39 | 22% |
A single blended install share would report the midpoint and hide both ends. If most of your users run Grok Build CLI, your real position here is 3%, not 18%.
By who was asking
Google Maps does much better with one kind of buyer than another. It won 28% of sessions asked as junior developer and 9% of those asked as vibe coder.
| Who is asking | Sessions | Chose Google Maps | Share |
|---|---|---|---|
| Vibe coder | 163 | 15 | 9% |
| Junior developer | 247 | 69 | 28% |
| Senior engineer | 162 | 29 | 18% |
| Enterprise team | 187 | 20 | 11% |
What Google Maps was up against
The full ranking in maps, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Google Maps (this page) | 133 | 18% |
| 2 | Leaflet | 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
Leading a category is a position to defend rather than a result to celebrate. In our data, leaders lose ground in exactly two situations: when the person asking is an enterprise buyer with procurement constraints, and when a competitor's documentation is easier for an agent to integrate correctly.
The defence is unglamorous. Keep the quickstart running. Keep the version current on the page. Keep the names aligned. Stay in the templates.
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 Google Maps: 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 Google Maps?
Yes. Google Maps was chosen in 133 of the 759 judged sessions in maps, a 18% install share, ranking first in its category.
Does Claude Code recommend Google Maps?
In 19 of the 164 sessions in maps run with Claude Code, which is 12%.
Do different coding agents treat Google Maps differently?
Yes, and by a wide margin. Codex chose it in 24% of its runs and Grok Build CLI in 3%.
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 Google Maps considered but not chosen?
It was raised as a candidate in 474 sessions without being chosen, and chosen in 133. That is a 22% 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.