Do coding agents recommend Daytona?
Daytona was chosen in 14% of 520 judged code sandboxes sessions, ranking fourth. Measured with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code.
Daytona was chosen in 14% of 520 judged code sandboxes sessions, ranking fourth. It was also raised as a candidate in 383 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 code sandboxes inside a realistic codebase. Not what a chat assistant says about Daytona. What an agent actually installed.
The numbers
| Category | Code sandboxes |
| Sessions in the category | 520 |
| Sessions where Daytona was chosen | 73 |
| Install share | 14% |
| Rank in category | 4 of 7 |
| Codebases it won in | 5 |
| Raised as a candidate, not chosen | 383 |
| Chosen when considered | 16% |
| Site | daytona.io |
By agent
The agents treat Daytona very differently. Codex chose it in 29% of its sessions in this category and Grok Build CLI in 0%, a spread of 29 points.
| Agent | Sessions | Chose Daytona | Share |
|---|---|---|---|
| Claude Code | 129 | 1 | 1% |
| Codex | 170 | 49 | 29% |
| Cursor | 136 | 13 | 10% |
| Grok Build CLI | 34 | 0 | 0% |
| Muse Code | 51 | 10 | 20% |
A single blended install share would report the midpoint and hide both ends. If most of your users run Grok Build CLI, your real position here is 0%, not 14%.
By who was asking
Daytona does much better with one kind of buyer than another. It won 55% of sessions asked as enterprise team and 9% of those asked as senior engineer.
| Who is asking | Sessions | Chose Daytona | Share |
|---|---|---|---|
| Senior engineer | 464 | 42 | 9% |
| Enterprise team | 56 | 31 | 55% |
What Daytona was up against
The full ranking in code sandboxes, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | E2B | 227 | 44% |
| 2 | Modal | 131 | 25% |
| 3 | Vercel Sandbox | 81 | 16% |
| 4 | Daytona (this page) | 73 | 14% |
| 5 | Anthropic Code Execution | 3 | 1% |
| 6 | Runloop Devboxes | 3 | 1% |
| 7 | Cloudflare Workers | 2 | 0% |
What this means
This is an integration problem, not a presence problem. Agents raised Daytona in 383 sessions and chose it in 73, so it reaches the shortlist and then loses. Something at the last step is costing the session, and in our data that is usually a quickstart that does not run when pasted, documentation describing an interface that changed, or a package name that does not match the product name.
That is the cheaper of the two problems to have. The reason is written down in each losing transcript.
Where these numbers come from
The 520 sessions in code sandboxes are part of a published set of 15,287, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: how we measured this.
Every code sandboxes run can be replayed on the board.
If you work on Daytona: 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 Daytona?
Yes. Daytona was chosen in 73 of the 520 judged sessions in code sandboxes, a 14% install share, ranking fourth in its category.
Does Claude Code recommend Daytona?
In 1 of the 129 sessions in code sandboxes run with Claude Code, which is 1%.
Do different coding agents treat Daytona differently?
Yes, and by a wide margin. Codex chose it in 29% of its runs and Grok Build CLI in 0%.
How was this measured?
Real coding agents at pinned versions were run in sandboxes inside 110 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 Daytona considered but not chosen?
It was raised as a candidate in 383 sessions without being chosen, and chosen in 73. That is a 16% conversion from considered to chosen.
Where this comes from
Armature ran 15,287 judged sessions with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code inside 110 realistic codebases, and published every run. The numbers on this page come from that work.