Do coding agents recommend Apple Maps (MapKit)?
Apple Maps (MapKit) was chosen in 14% of 759 judged maps sessions, ranking third. Measured with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code.
Apple Maps (MapKit) was chosen in 14% of 759 judged maps sessions, ranking third. It was also raised as a candidate in 1 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 Apple Maps (MapKit). What an agent actually installed.
The numbers
| Category | Maps |
| Sessions in the category | 759 |
| Sessions where Apple Maps (MapKit) was chosen | 104 |
| Install share | 14% |
| Rank in category | 3 of 49 |
| Codebases it won in | 2 |
| Raised as a candidate, not chosen | 1 |
| Chosen when considered | 99% |
| Site | developer.apple.com |
By agent
Claude Code, Codex, Cursor, Grok Build CLI and Muse Code agree closely on Apple Maps (MapKit), choosing it at rates within 4 points of each other.
| Agent | Sessions | Chose Apple Maps (MapKit) | Share |
|---|---|---|---|
| Claude Code | 164 | 23 | 14% |
| Codex | 227 | 28 | 12% |
| Cursor | 154 | 24 | 16% |
| Grok Build CLI | 37 | 6 | 16% |
| Muse Code | 177 | 23 | 13% |
By who was asking
Apple Maps (MapKit) does much better with one kind of buyer than another. It won 34% of sessions asked as senior engineer and 0% of those asked as enterprise team.
| Who is asking | Sessions | Chose Apple Maps (MapKit) | Share |
|---|---|---|---|
| Vibe coder | 163 | 49 | 30% |
| Junior developer | 247 | 0 | 0% |
| Senior engineer | 162 | 55 | 34% |
| Enterprise team | 187 | 0 | 0% |
What Apple Maps (MapKit) was up against
The full ranking in maps, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Google Maps | 133 | 18% |
| 2 | Leaflet | 125 | 16% |
| 3 | Apple Maps (MapKit) (this page) | 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
Agents almost never raise Apple Maps (MapKit) without choosing it: 1 sessions raised against 104 chosen. When it gets considered, it usually wins. The constraint is how rarely it gets considered at all, which is a presence problem: templates, framework integrations and pages that answer the configuration and production questions agents actually search for.
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 Apple Maps (MapKit): 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 Apple Maps (MapKit)?
Yes. Apple Maps (MapKit) was chosen in 104 of the 759 judged sessions in maps, a 14% install share, ranking third in its category.
Does Claude Code recommend Apple Maps (MapKit)?
In 23 of the 164 sessions in maps run with Claude Code, which is 14%.
Do different coding agents treat Apple Maps (MapKit) differently?
Not much. Claude Code, Codex, Cursor, Grok Build CLI and Muse Code chose it at similar rates, between 12% and 16% of their runs.
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 Apple Maps (MapKit) considered but not chosen?
It was raised as a candidate in 1 sessions without being chosen, and chosen in 104. That is a 99% 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.