Do coding agents recommend Google Cloud Storage?
Google Cloud Storage was chosen in 20% of 90 judged file storage sessions, ranking third. Measured with Claude Code, Codex and Cursor.
Google Cloud Storage was chosen in 20% of 90 judged file storage sessions, ranking third. It was also raised as a candidate in 32 further sessions without being chosen.
This page reports what happened when Claude Code, Codex and Cursor had to solve a problem in file storage inside a realistic codebase. Not what a chat assistant says about Google Cloud Storage. 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 file storage in general, and the splits below cannot separate the two. Treat them as a description of that repository.
The numbers
| Category | File storage |
| Sessions in the category | 90 |
| Sessions where Google Cloud Storage was chosen | 18 |
| Install share | 20% |
| Rank in category | 3 of 5 |
| Codebases it won in | 1 |
| Raised as a candidate, not chosen | 32 |
| Chosen when considered | 36% |
| Site | cloud.google.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.
| Agent | Sessions | Chose Google Cloud Storage | Share |
|---|---|---|---|
| Claude Code | 30 | 6 | 20% |
| Codex | 30 | 6 | 20% |
| Cursor | 30 | 6 | 20% |
By who was asking
Google Cloud Storage does much better with one kind of buyer than another. It won 50% of sessions asked as enterprise team and 0% of those asked as senior engineer.
| Who is asking | Sessions | Chose Google Cloud Storage | Share |
|---|---|---|---|
| Junior developer | 18 | 0 | 0% |
| Senior engineer | 27 | 0 | 0% |
| Enterprise team | 36 | 18 | 50% |
What Google Cloud Storage was up against
The full ranking in file storage, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Amazon S3 | 41 | 46% |
| 2 | Azure Blob Storage | 18 | 20% |
| 3 | Google Cloud Storage (this page) | 18 | 20% |
| 4 | Cloudflare R2 | 12 | 13% |
| 5 | Tigris | 1 | 1% |
What this means
A solid second or third position in a category means the agent is genuinely choosing rather than reaching automatically. That is a winnable position, because the inputs it uses can be changed.
The fastest gains are usually in the sessions that were nearly won: read them, find the step where the agent moved on, and fix that step.
Where these numbers come from
The 90 sessions in file storage are part of a published set of 5,292, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: how we measured this.
Every file storage run can be replayed on the board.
If you work on Google Cloud Storage: 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 Cloud Storage?
Yes. Google Cloud Storage was chosen in 18 of the 90 judged sessions in file storage, a 20% install share, ranking third in its category.
Does Claude Code recommend Google Cloud Storage?
In 6 of the 30 sessions in file storage run with Claude Code, which is 20%.
Do different coding agents treat Google Cloud Storage differently?
Not much. The three agents chose it at similar rates, between 20% and 20% of their runs.
How was this measured?
Real coding agents at pinned versions were run in sandboxes inside 51 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 Cloud Storage considered but not chosen?
It was raised as a candidate in 32 sessions without being chosen, and chosen in 18. That is a 36% conversion from considered to chosen.
Where this comes from
Armature ran 5,292 judged sessions with Claude Code, Codex and Cursor inside 51 realistic codebases, and published every run. The numbers on this page come from that work.