From the experiment

Do coding agents recommend Azure Maps?

Azure Maps was chosen in 6% of 319 judged maps sessions, ranking seventh. Measured with Claude Code, Codex and Cursor.

Published September 11, 2026 Read as Markdown

Azure Maps was chosen in 6% of 319 judged maps sessions, ranking seventh. It was also raised as a candidate in 22 further sessions without being chosen.

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 Azure Maps. What an agent actually installed.

One thing to read first: every one of those wins came from a single codebase. That is a result about one repository rather than about maps in general, and the splits below cannot separate the two. Treat them as a description of that repository.

The numbers

CategoryMaps
Sessions in the category319
Sessions where Azure Maps was chosen18
Install share6%
Rank in category7 of 32
Codebases it won in1
Raised as a candidate, not chosen22
Chosen when considered45%
Siteazure.microsoft.com

By agent

With 18 wins spread across three agents, the rates below are small numbers and a difference between them is not yet a finding. They are here because the direction is worth knowing, not because the gap is established.

AgentSessionsChose Azure MapsShare
Claude Code10844%
Codex11198%
Cursor10055%

By who was asking

Azure Maps performs similarly across the four kinds of buyer, from 0% to 12%. That is unusual: the category leader changed with the persona in 19 of the 23 categories we measured.

Who is askingSessionsChose Azure MapsShare
Vibe coder6400%
Junior developer1471812%
Senior engineer7200%
Enterprise team3600%

What Azure Maps was up against

The full ranking in maps, from the same sessions:

#ProductRuns wonShare
1Google Maps5216%
2Leaflet5216%
3Apple Maps (MapKit)4614%
4Mapbox258%
5MapLibre217%
6react-native-maps196%
7Azure Maps (this page)186%
8Built in-house (no product adopted)165%

What this means

Azure Maps was raised in 22 sessions and chosen in 18. That ratio is balanced enough that the ceiling is presence rather than integration: the product converts reasonably when it is on the table, and it is not on the table often enough.

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 Azure 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 Azure Maps?

Yes. Azure Maps was chosen in 18 of the 319 judged sessions in maps, a 6% install share, ranking seventh in its category.

Does Claude Code recommend Azure Maps?

In 4 of the 108 sessions in maps run with Claude Code, which is 4%.

Do different coding agents treat Azure Maps differently?

Not much. The three agents chose it at similar rates, between 4% and 8% 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.

How often is Azure Maps considered but not chosen?

It was raised as a candidate in 22 sessions without being chosen, and chosen in 18. That is a 45% conversion from considered to chosen.

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