# Serverless functions: which platforms coding agents choose

> AWS Lambda and Vercel Functions finish close, about 24% and 23%.

Source: https://armature.tech/leaderboards/serverless (Armature agent leaderboards). 287 runs, 8 apps, 3 agents, 4 personas, updated 2026-09-02. Interactive board with every run: https://armature.tech/leaderboards#app/serverless

## Key learnings

We asked three coding agents to add serverless functions to eight small apps, 287 runs in all. Each app came up in several wordings and with four different personas. Behind the two leaders, Azure Functions took about 13% and nothing else got near it.

### The persona moved the winner (36 of 72)

Enterprise teams picked Azure Functions in 36 of their 72 runs. Vibe coders picked Cloudflare Workers 15 times in 36 runs. Junior developers picked Vercel Functions in 34 of 72 runs.

### One agent went a different way (49 of 96)

Codex picked AWS Lambda in 49 of its 96 runs. Cursor and Claude Code both put Vercel Functions on top instead.

### Rewording the ask changed the pick (16 of 24)

We had 24 cases, each one codebase and one agent asked several times in different words and as different people. In 16 of them the runs did not all land on the same platform.

### Named often, picked once (1 of 91)

Netlify Functions came up in 91 runs and was chosen in one of them.

Smaller learnings:

- The agents wrote the functions themselves in 50 runs, about 17%.
- The simulated user approved every plan, but sent the agent back at least once in 29 runs.
- In nine runs it refused to approve until the agent named a specific platform.
- All five Render wins came in one codebase, a helpdesk billing starter, and Fly.io won four times in a Remix workshop booking app.

## The ranking

| # | Product | Wins | Share |
|---|---|---:|---:|
| 1 | AWS Lambda (aws.amazon.com) | 70 | 24% |
| 2 | Vercel Functions (vercel.com) | 65 | 23% |
| 3 | Built in-house (outcome) | 50 | 17% |
| 4 | Azure Functions (azure.microsoft.com) | 36 | 13% |
| 5 | Cloudflare Workers (workers.cloudflare.com) | 20 | 7% |
| 6 | Google Cloud Run (cloud.google.com) | 11 | 4% |
| 7 | Inngest (inngest.com) | 7 | 2% |
| 8 | Render (render.com) | 5 | 2% |
| 9 | Fly.io (fly.io) | 4 | 1% |
| 10 | Google Cloud Functions (cloud.google.com) | 2 | 1% |
| 11 | Inngest + Vercel Functions | 1 | 0% |
| 12 | Trigger.dev (trigger.dev) | 1 | 0% |
| 13 | Upstash QStash (upstash.com) | 1 | 0% |
| 14 | Netlify Functions (netlify.com) | 1 | 0% |

## By agent

- Codex (GPT-5.6 Sol): 96 runs, first AWS Lambda (49), then Vercel Functions (20)
- Claude Code (Claude Opus 5): 96 runs, first Vercel Functions (24), then Azure Functions (12)
- Cursor (Grok 4.6): 95 runs, first Vercel Functions (21), then AWS Lambda (18)

## By persona

- Senior engineer: 107 runs, first AWS Lambda (36), then Vercel Functions (31)
- Enterprise team: 72 runs, first Azure Functions (36), then AWS Lambda (21)
- Junior developer: 72 runs, first Vercel Functions (34), then AWS Lambda (10)
- Vibe coder: 36 runs, first Cloudflare Workers (15), then Fly.io (4)

## By what the ask stressed

- The plain ask: 287 runs, first AWS Lambda (70), then Vercel Functions (65)

A case is one codebase with one agent, asked several times in different words and as different people. 16 of 24 cases did not hold to a single choice.

## How this was measured

Every number on this page comes from a controlled experiment. We took 8 small applications, asked 3 coding agents (Codex (GPT-5.6 Sol), Claude Code (Claude Opus 5), Cursor (Grok 4.6)) to add serverless functions to each of them, in several wordings and as a senior engineer and enterprise team and junior developer and vibe coder, 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 287 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 29 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)
- [Deploy](https://armature.tech/leaderboards/deploy) (https://armature.tech/leaderboards/deploy.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)
- [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)