From the experiment

Do coding agents recommend Apple Maps (MapKit)?

Apple Maps (MapKit) was chosen in 14% of 319 judged maps sessions, ranking third. Measured with Claude Code, Codex and Cursor.

Published September 11, 2026 Read as Markdown

Apple Maps (MapKit) was chosen in 14% of 319 judged maps sessions, ranking third.

This page reports what happened when Claude Code, Codex and Cursor 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

CategoryMaps
Sessions in the category319
Sessions where Apple Maps (MapKit) was chosen46
Install share14%
Rank in category3 of 32
Codebases it won in2
Raised as a candidate, not chosen0
Chosen when considered100%
Sitedeveloper.apple.com

By agent

The three agents agree closely on Apple Maps (MapKit), choosing it at rates within 3 points of each other.

AgentSessionsChose Apple Maps (MapKit)Share
Claude Code1081615%
Codex1111413%
Cursor1001616%

By who was asking

Apple Maps (MapKit) does much better with one kind of buyer than another. It won 34% of sessions asked as vibe coder and 0% of those asked as enterprise team.

Who is askingSessionsChose Apple Maps (MapKit)Share
Vibe coder642234%
Junior developer14700%
Senior engineer722433%
Enterprise team3600%

What Apple Maps (MapKit) was up against

The full ranking in maps, from the same sessions:

#ProductRuns wonShare
1Google Maps5216%
2Leaflet5216%
3Apple Maps (MapKit) (this page)4614%
4Mapbox258%
5MapLibre217%
6react-native-maps196%
7Azure Maps186%
8Built in-house (no product adopted)165%

What this means

Agents almost never raise Apple Maps (MapKit) without choosing it: 0 sessions raised against 46 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 319 sessions in maps are part of a published set of 6,458, 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 46 of the 319 judged sessions in maps, a 14% install share, ranking third in its category.

Does Claude Code recommend Apple Maps (MapKit)?

In 16 of the 108 sessions in maps run with Claude Code, which is 15%.

Do different coding agents treat Apple Maps (MapKit) differently?

Not much. The three agents chose it at similar rates, between 13% and 16% of their runs.

How was this measured?

Real coding agents at pinned versions were run in sandboxes inside 63 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.

Where this comes from

Armature ran 6,458 judged sessions with Claude Code, Codex and Cursor inside 63 realistic codebases, and published every run. The numbers on this page come from that work.

Read next

All library pages