How to get picked for maps by coding agents
Google Maps took 16% of 319 judged maps sessions. What the numbers say a vendor in this category should do.
If you sell map products, this page is the part of the market no dashboard shows you: what a coding agent does when a developer asks for maps and never compares vendors.
The numbers come from 319 judged sessions with Claude Code, Codex and Cursor, spread across 14 realistic codebases, with every session read by a judge.
What coding agents choose for maps
Across 319 judged sessions, Google Maps was chosen most often, in 16% of runs. Leaflet was second with 16%.
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Google Maps | 52 | 16% |
| 2 | Leaflet | 52 | 16% |
| 3 | Apple Maps (MapKit) | 46 | 14% |
| 4 | Mapbox | 25 | 8% |
| 5 | MapLibre | 21 | 7% |
| 6 | react-native-maps | 19 | 6% |
| 7 | Azure Maps | 18 | 6% |
| 8 | Built in-house (no product adopted) | 16 | 5% |
| 9 | MapTiler | 15 | 5% |
| 10 | OpenStreetMap | 10 | 3% |
Full board, every run replayable: the maps leaderboard.
What the shape of this category means
The leader takes only 16% of runs. This category is genuinely open and the ordering can be moved.
With the top product at 16%, maps is decided in the moment, from what the agent reads and what it finds in the repository. Nothing is locked in, which is the best situation a vendor can be in and the one where the work pays fastest.
The order here is set by the quality of what an agent can read and by whether your product is already present in the codebase. Both are things you can change.
The agents do not agree with each other
In this category the three agents we ran put different products first.
| Agent | Runs | Picked most often |
|---|---|---|
| Claude Code | 108 | Apple Maps (MapKit) (16) |
| Codex | 111 | Google Maps (27) |
| Cursor | 100 | Leaflet (30) |
That split decides where a vendor spends. Codex ran a web search in 53% of decision runs and Claude Code in 1.6%, so the pages you publish are live in half of Codex's maps sessions and almost none of Claude Code's. Taking Google Maps's position with Codex is a content problem. Taking Apple Maps (MapKit)'s with Claude Code is a repository problem.
Who is asking changes the answer
Every request in this experiment was written as a specific kind of person. In this category the leader changes with the person.
| Who is asking | Runs | Picked most often |
|---|---|---|
| Vibe coder | 64 | Apple Maps (MapKit) |
| Junior developer | 147 | Google Maps |
| Senior engineer | 72 | Apple Maps (MapKit) |
| Enterprise team | 36 | MapLibre |
That is 3 different products winning maps for 4 kinds of buyer, out of the same 319 sessions. Nobody here is winning maps. They are each winning one kind of buyer.
If you sell to more than one of them, you need pages for each. See how to win the enterprise persona.
What you are really competing against
In 5% of runs the agent wrote the code itself rather than adopting a product. That is low enough that your competition is other vendors, but high enough to be worth watching.
Considered, and never chosen
Because the judge records every product an agent raised and not only the one it picked, this board also shows who kept reaching the shortlist and losing. In maps the clearest case is Nominatim: on the table in 82 sessions, chosen in none.
| Product | Raised in | Chosen in |
|---|---|---|
| Nominatim | 82 sessions | 0 |
| Protomaps | 63 sessions | 0 |
| Stadia Maps | 38 sessions | 0 |
| CARTO | 34 sessions | 0 |
| Ordnance Survey | 30 sessions | 0 |
Being rejected is a better position than being unknown, and a cheaper one to fix. The product is already in the agent's head and on the list. Whatever ended those 247 sessions is recorded in each transcript, one reason at a time.
What to do about it in maps
- Treat the ordering as movable. The leader holds 16%, so agents are deliberating rather than defaulting, and the inputs they use can change the answer. This is the most winnable shape a category comes in.
- Pick which buyer you are for. The same maps need written as a vibe coder landed on Apple Maps (MapKit), and written as an enterprise team landed on MapLibre. Those are two markets, and the enterprise one needs pages containing the constraint words: audit log, data residency, retention, single sign-on. See how to win the enterprise persona.
- Measure per agent. Claude Code put Apple Maps (MapKit) first, Codex put Google Maps first, Cursor put Leaflet first. A blended number for maps describes a market that does not exist.
The work that applies to every category rather than to this one is written up separately: audit your documentation, write a quickstart an agent can follow, and how to measure install share.
Every map product on this board
One page per product, with its install share, the per-agent split, and how often it was raised without being chosen.
- Do coding agents recommend Google Maps? — chosen in 16% of sessions
- Do coding agents recommend Leaflet? — chosen in 16% of sessions
- Do coding agents recommend Apple Maps (MapKit)? — chosen in 14% of sessions
- Do coding agents recommend Mapbox? — chosen in 8% of sessions
- Do coding agents recommend MapLibre? — chosen in 7% of sessions
- Do coding agents recommend react-native-maps? — chosen in 6% of sessions
- Do coding agents recommend Azure Maps? — chosen in 6% of sessions
- Do coding agents recommend MapTiler? — chosen in 5% of sessions
- Do coding agents recommend OpenStreetMap? — chosen in 3% of sessions
- Do coding agents recommend flutter_map? — chosen in 3% of sessions
- Do coding agents recommend Nominatim? — raised in 82 sessions, chosen in none
- Do coding agents recommend Protomaps? — raised in 63 sessions, chosen in none
Where these numbers come from
319 judged sessions in maps across 14 codebases, part of a published set of 6,458. Real coding agents at pinned versions, in sandboxes, inside realistic codebases, with a simulated project owner in the loop and a blind judge on every session. The full method is on one page: how we measured this.
Every maps run can be replayed on the board.
<!-- generated by scripts/write-data-pages.mjs -->
Common questions
How many codebases is this based on?
319 judged sessions across 14 realistic codebases. A category only runs on repositories where its seam is open, so coverage differs: some categories ran on more than ten codebases and some on two.
What map product do coding agents choose?
Across 319 judged sessions, Google Maps was chosen most often, in 16% of runs. Leaflet was second with 16%. The result changes by agent and by who is asking.
Do Claude Code and Codex pick the same map product?
No. Claude Code picked Apple Maps (MapKit), Codex picked Google Maps, Cursor picked Leaflet. Measuring one agent tells you about part of the market only.
How often do agents build maps themselves instead of installing something?
In 5% of runs the agent wrote the code itself rather than adopting a product.
How can a vendor improve its position here?
Make the quickstart run when pasted, state the current version on the documentation page, use one name across product, package and import, write pages for the symptoms users describe rather than only the category name, and get into the repository through templates and framework integrations.
Which map products do agents consider but never choose?
Nominatim (raised in 82 sessions, chosen in none), Protomaps (raised in 63 sessions, chosen in none), Stadia Maps (raised in 38 sessions, chosen in none), CARTO (raised in 34 sessions, chosen in none), Ordnance Survey (raised in 30 sessions, chosen in none). Being considered and not chosen is a different problem from being unknown, and it is usually fixable.
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.