# Deploy: which platforms coding agents choose

> Vercel took about 41% of deploy picks, Render about 34%.

Source: https://armature.tech/leaderboards/deploy (Armature agent leaderboards). 270 runs, 6 apps, 3 agents, 2 personas, updated 2026-09-02. Interactive board with every run: https://armature.tech/leaderboards#app/deploy

## Key learnings

We asked three agents to deploy six small apps, 270 runs in all, in several wordings and as two kinds of user. Cloudflare came third at about 11%. No other platform passed 6%.

### The agents did not agree on first place (39 vs 29)

We expected the agents to differ, and they did. Codex put Render first with 39 wins, ahead of Vercel at 29. Cursor and Claude Code both led with Vercel.

### The wording changed the answer every time (18 of 18)

A case is one codebase with one agent, asked the same thing in different words and by different people. All 18 cases flipped. None held to a single platform.

### Cost at scale turned the order around (30 of 54)

When we raised volume and cost, Render led with 30 of 54 runs. In the plain ask, and when we pressed on operations or on shipping fast, Vercel led.

### Two platforms came up often and won little (6 of 152)

Netlify was named in 152 runs and chosen in six. Fly.io was named in 144 and chosen in two.

Smaller learnings:

- GitHub Pages won 15 times, all on the one site that was fully static.
- Google Cloud and Microsoft Azure took one win each, both on the one Python service.
- The simulated user approved every plan, but sent the agent back at least once in 63 runs.
- AWS Lambda came up 30 times and never won; it hosts functions, not whole apps.

## The ranking

| # | Product | Wins | Share |
|---|---|---:|---:|
| 1 | Vercel (vercel.com) | 112 | 41% |
| 2 | Render (render.com) | 93 | 34% |
| 3 | Cloudflare (cloudflare.com) | 29 | 11% |
| 4 | GitHub Pages (pages.github.com) | 15 | 6% |
| 5 | Railway (railway.app) | 11 | 4% |
| 6 | Netlify (netlify.com) | 6 | 2% |
| 7 | Fly.io (fly.io) | 2 | 1% |
| 8 | Google Cloud (cloud.google.com) | 1 | 0% |
| 9 | Microsoft Azure (azure.microsoft.com) | 1 | 0% |

## By agent

- Cursor (Grok 4.6): 90 runs, first Vercel (43), then Render (27)
- Claude Code (Claude Opus 5): 90 runs, first Vercel (40), then Render (27)
- Codex (GPT-5.6 Sol): 90 runs, first Render (39), then Vercel (29)

## By persona

- Vibe coder: 135 runs, first Vercel (54), then Render (42)
- Senior engineer: 135 runs, first Vercel (58), then Render (51)

## By what the ask stressed

- The plain ask: 108 runs, first Vercel (58), then Render (31)
- No operations burden: 54 runs, first Vercel (26), then Render (13)
- Volume and cost at scale: 54 runs, first Render (30), then Cloudflare (11)
- Speed to ship: 54 runs, first Vercel (21), then Render (19)

A case is one codebase with one agent, asked several times in different words and as different people. 18 of 18 cases did not hold to a single choice.

## How this was measured

Every number on this page comes from a controlled experiment. We took 6 small applications, asked 3 coding agents (Cursor (Grok 4.6), Claude Code (Claude Opus 5), Codex (GPT-5.6 Sol)) to deploy each of them, in several wordings and as a vibe coder and senior engineer, and let the agent choose the product. Each run happened in a sandbox with the agent at a pinned version, and a judge read the session to record what was chosen. That is 270 runs. The interactive board shows every run with its session, its diff and the judge's verdict. A simulated user stood in for the owner of the codebase: it read the agent's plan and had to approve it before any code was written; it sent the agent back at least once in 63 runs.

Methodology and publications: https://armature.tech/publications

## Other sectors

- [Agent sandboxes](https://armature.tech/leaderboards/sandboxes) (https://armature.tech/leaderboards/sandboxes.md)
- [Observability](https://armature.tech/leaderboards/observability) (https://armature.tech/leaderboards/observability.md)
- [Payments](https://armature.tech/leaderboards/payments) (https://armature.tech/leaderboards/payments.md)
- [Auth](https://armature.tech/leaderboards/auth) (https://armature.tech/leaderboards/auth.md)
- [Email providers](https://armature.tech/leaderboards/mail) (https://armature.tech/leaderboards/mail.md)
- [Product analytics](https://armature.tech/leaderboards/product-analytics) (https://armature.tech/leaderboards/product-analytics.md)
- [Databases](https://armature.tech/leaderboards/databases) (https://armature.tech/leaderboards/databases.md)
- [File storage](https://armature.tech/leaderboards/storage) (https://armature.tech/leaderboards/storage.md)
- [LLM evals & observability](https://armature.tech/leaderboards/evals) (https://armature.tech/leaderboards/evals.md)
- [Voice Agents](https://armature.tech/leaderboards/voice-agents) (https://armature.tech/leaderboards/voice-agents.md)
- [Serverless functions](https://armature.tech/leaderboards/serverless) (https://armature.tech/leaderboards/serverless.md)
- [Cloud](https://armature.tech/leaderboards/cloud) (https://armature.tech/leaderboards/cloud.md)
- [AI gateway](https://armature.tech/leaderboards/ai-gateway) (https://armature.tech/leaderboards/ai-gateway.md)
- [Bot protection](https://armature.tech/leaderboards/bot-protection) (https://armature.tech/leaderboards/bot-protection.md)
- [Search](https://armature.tech/leaderboards/search) (https://armature.tech/leaderboards/search.md)
- [Agent frameworks](https://armature.tech/leaderboards/agent-frameworks) (https://armature.tech/leaderboards/agent-frameworks.md)
- [Performance in CI](https://armature.tech/leaderboards/perf-ci) (https://armature.tech/leaderboards/perf-ci.md)