Do coding agents recommend Modal?
Modal was chosen in 25% of 299 judged code sandboxes sessions, ranking second. Measured with Claude Code, Codex and Cursor.
Modal was chosen in 25% of 299 judged code sandboxes sessions, ranking second. It was also raised as a candidate in 224 further sessions without being chosen.
This page reports what happened when Claude Code, Codex and Cursor had to solve a problem in code sandboxes inside a realistic codebase. Not what a chat assistant says about Modal. What an agent actually installed.
The numbers
| Category | Code sandboxes |
| Sessions in the category | 299 |
| Sessions where Modal was chosen | 74 |
| Install share | 25% |
| Rank in category | 2 of 7 |
| Codebases it won in | 5 |
| Raised as a candidate, not chosen | 224 |
| Chosen when considered | 25% |
| Site | modal.com |
By agent
The three agents treat Modal very differently. Codex chose it in 48% of its sessions in this category and Cursor in 0%, a spread of 48 points.
| Agent | Sessions | Chose Modal | Share |
|---|---|---|---|
| Claude Code | 95 | 25 | 26% |
| Codex | 102 | 49 | 48% |
| Cursor | 102 | 0 | 0% |
A single blended install share would report the midpoint and hide both ends. If most of your users run Cursor, your real position here is 0%, not 25%.
By who was asking
Modal does much better with one kind of buyer than another. It won 26% of sessions asked as senior engineer and 10% of those asked as enterprise team.
| Who is asking | Sessions | Chose Modal | Share |
|---|---|---|---|
| Senior engineer | 269 | 71 | 26% |
| Enterprise team | 30 | 3 | 10% |
What Modal was up against
The full ranking in code sandboxes, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | E2B | 127 | 42% |
| 2 | Modal (this page) | 74 | 25% |
| 3 | Daytona | 47 | 16% |
| 4 | Vercel Sandbox | 43 | 14% |
| 5 | Anthropic Code Execution | 3 | 1% |
| 6 | Runloop Devboxes | 3 | 1% |
| 7 | Cloudflare Workers | 2 | 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 299 sessions in code sandboxes 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 code sandboxes run can be replayed on the board.
If you work on Modal: 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 Modal?
Yes. Modal was chosen in 74 of the 299 judged sessions in code sandboxes, a 25% install share, ranking second in its category.
Does Claude Code recommend Modal?
In 25 of the 95 sessions in code sandboxes run with Claude Code, which is 26%.
Do different coding agents treat Modal differently?
Yes, and by a wide margin. Codex chose it in 48% of its runs and Cursor in 0%.
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 Modal considered but not chosen?
It was raised as a candidate in 224 sessions without being chosen, and chosen in 74. That is a 25% 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.