Do coding agents recommend Vercel Sandbox?
Vercel Sandbox was chosen in 16% of 520 judged code sandboxes sessions, ranking third. Measured with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code.
Vercel Sandbox was chosen in 16% of 520 judged code sandboxes sessions, ranking third. It was also raised as a candidate in 179 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 Vercel Sandbox. What an agent actually installed.
The numbers
| Category | Code sandboxes |
| Sessions in the category | 520 |
| Sessions where Vercel Sandbox was chosen | 81 |
| Install share | 16% |
| Rank in category | 3 of 7 |
| Codebases it won in | 4 |
| Raised as a candidate, not chosen | 179 |
| Chosen when considered | 31% |
| Site | vercel.com |
By agent
The agents treat Vercel Sandbox very differently. Claude Code chose it in 31% of its sessions in this category and Muse Code in 0%, a spread of 31 points.
| Agent | Sessions | Chose Vercel Sandbox | Share |
|---|---|---|---|
| Claude Code | 129 | 40 | 31% |
| Codex | 170 | 15 | 9% |
| Cursor | 136 | 18 | 13% |
| Grok Build CLI | 34 | 8 | 24% |
| Muse Code | 51 | 0 | 0% |
A single blended install share would report the midpoint and hide both ends. If most of your users run Muse Code, your real position here is 0%, not 16%.
By who was asking
Vercel Sandbox performs similarly across the four kinds of buyer, from 14% to 27%. That is unusual: the category leader changed with the persona in 24 of the 31 categories we measured.
| Who is asking | Sessions | Chose Vercel Sandbox | Share |
|---|---|---|---|
| Senior engineer | 464 | 66 | 14% |
| Enterprise team | 56 | 15 | 27% |
What Vercel Sandbox 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 (this page) | 81 | 16% |
| 4 | Daytona | 73 | 14% |
| 5 | Anthropic Code Execution | 3 | 1% |
| 6 | Runloop Devboxes | 3 | 1% |
| 7 | Cloudflare Workers | 2 | 0% |
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 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 Vercel Sandbox: 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 Vercel Sandbox?
Yes. Vercel Sandbox was chosen in 81 of the 520 judged sessions in code sandboxes, a 16% install share, ranking third in its category.
Does Claude Code recommend Vercel Sandbox?
In 40 of the 129 sessions in code sandboxes run with Claude Code, which is 31%.
Do different coding agents treat Vercel Sandbox differently?
Yes, and by a wide margin. Claude Code chose it in 31% of its runs and Muse Code 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 Vercel Sandbox considered but not chosen?
It was raised as a candidate in 179 sessions without being chosen, and chosen in 81. That is a 31% 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.