# Agent leaderboards by sector

Which tools coding agents choose, from 5292 sandboxed runs with Claude Code, Codex and Cursor. Source: https://armature.tech/leaderboards/sectors. Interactive board: https://armature.tech/leaderboards

> Which tools do coding agents choose?

We asked three coding agents, Cursor, Claude Code and Codex, to add one capability to a small app and pick the product themselves. That ran 5292 times, across 18 sectors and 51 apps. Most sectors have a favorite, few have a default.

### Five sectors have one obvious winner (5 of 18)

In five sectors the leading product took at least half the runs. Stripe is the strongest, with about 88% in [Payments](https://armature.tech/leaderboards/payments). Neon took about 66% in [Databases](https://armature.tech/leaderboards/databases), and AWS about 62% in [Cloud](https://armature.tech/leaderboards/cloud).

### Half the sectors are still contested (9 of 18)

Nine sectors have a leader with between 22% and half the runs. Vercel leads [Deploy](https://armature.tech/leaderboards/deploy) with about 41%. In [AI gateway](https://armature.tech/leaderboards/ai-gateway) no product got past 22%.

### Sometimes the agents write it themselves (13%)

Across every run, the agents built the capability in-house about 13% of the time. In three sectors they did that more often than they picked any product. In [Performance in CI](https://armature.tech/leaderboards/perf-ci) it was about 52% of runs.

## Sectors

- [Agent sandboxes](https://armature.tech/leaderboards/sandboxes): 299 runs, E2B leads with 42%. Markdown: https://armature.tech/leaderboards/sandboxes.md
- [Observability](https://armature.tech/leaderboards/observability): 360 runs, Sentry leads with 37%. Markdown: https://armature.tech/leaderboards/observability.md
- [Payments](https://armature.tech/leaderboards/payments): 395 runs, Stripe leads with 88%. Markdown: https://armature.tech/leaderboards/payments.md
- [Deploy](https://armature.tech/leaderboards/deploy): 270 runs, Vercel leads with 41%. Markdown: https://armature.tech/leaderboards/deploy.md
- [Auth](https://armature.tech/leaderboards/auth): 201 runs, WorkOS AuthKit leads with 26%. Markdown: https://armature.tech/leaderboards/auth.md
- [Email providers](https://armature.tech/leaderboards/mail): 208 runs, Resend leads with 36%. Markdown: https://armature.tech/leaderboards/mail.md
- [Product analytics](https://armature.tech/leaderboards/product-analytics): 359 runs, PostHog leads with 53%. Markdown: https://armature.tech/leaderboards/product-analytics.md
- [Databases](https://armature.tech/leaderboards/databases): 356 runs, Neon leads with 66%. Markdown: https://armature.tech/leaderboards/databases.md
- [File storage](https://armature.tech/leaderboards/storage): 90 runs, Amazon S3 leads with 46%. Markdown: https://armature.tech/leaderboards/storage.md
- [LLM evals & observability](https://armature.tech/leaderboards/evals): 288 runs, Langfuse leads with 34%. Markdown: https://armature.tech/leaderboards/evals.md
- [Voice Agents](https://armature.tech/leaderboards/voice-agents): 308 runs, Vapi leads with 24%. Markdown: https://armature.tech/leaderboards/voice-agents.md
- [Serverless functions](https://armature.tech/leaderboards/serverless): 287 runs, AWS Lambda leads with 24%. Markdown: https://armature.tech/leaderboards/serverless.md
- [Cloud](https://armature.tech/leaderboards/cloud): 215 runs, AWS leads with 62%. Markdown: https://armature.tech/leaderboards/cloud.md
- [AI gateway](https://armature.tech/leaderboards/ai-gateway): 140 runs, Portkey leads with 21%. Markdown: https://armature.tech/leaderboards/ai-gateway.md
- [Bot protection](https://armature.tech/leaderboards/bot-protection): 160 runs, Cloudflare Turnstile leads with 57%. Markdown: https://armature.tech/leaderboards/bot-protection.md
- [Search](https://armature.tech/leaderboards/search): 459 runs, Postgres Full-Text Search leads with 17%. Markdown: https://armature.tech/leaderboards/search.md
- [Agent frameworks](https://armature.tech/leaderboards/agent-frameworks): 681 runs, Vercel AI SDK leads with 14%. Markdown: https://armature.tech/leaderboards/agent-frameworks.md
- [Performance in CI](https://armature.tech/leaderboards/perf-ci): 216 runs, JMH leads with 10%. Markdown: https://armature.tech/leaderboards/perf-ci.md