# Databases: which databases coding agents choose

> Neon took about 66% of 356 runs picking a database.

Source: https://armature.tech/leaderboards/databases (Armature agent leaderboards). 356 runs, 6 apps, 3 agents, 3 personas, updated 2026-09-02. Interactive board with every run: https://armature.tech/leaderboards#app/databases

## Key learnings

We asked three coding agents to pick a database for six small apps, across 356 runs. We asked in several wordings and as three kinds of user. Azure SQL Database came second, with about 10%.

### A residency ask changed the order (15 of 59)

In 59 runs where the ask involved self-hosting, privacy or data residency, Azure Database for PostgreSQL Flexible Server came out on top with 15 wins. Neon took 10 of those runs.

### Wording changed the answer in most cases (11 of 18)

A case here is one codebase with one agent, asked several times in different words. Of 18 cases, 11 did not land on the same product every time.

### Named often, chosen never (105 vs 0)

Turso came up in 105 plans and won none of them. BigQuery was named 66 times without a win. PlanetScale had 63 mentions and no wins.

### One batch job drew the odd picks (7 wins)

All seven wins for MotherDuck came in the Partner inventory pipeline, a weekly Python reporting batch. Tiger Cloud and OVHcloud Managed PostgreSQL each won once in that same codebase.

Smaller learnings:

- The simulated user reads each plan before code is written, and it sent the agent back at least once in 197 runs.
- In 144 runs it would not approve until the agent named a specific product.
- PostgreSQL came up in 354 plans and won nothing, since it is the engine most of these services run.
- SQLite was named 319 times, but there is nothing to sign up for, so that is not a loss.

## The ranking

| # | Product | Wins | Share |
|---|---|---:|---:|
| 1 | Neon (neon.tech) | 236 | 66% |
| 2 | Azure SQL Database (azure.microsoft.com) | 35 | 10% |
| 3 | Azure Database for PostgreSQL Flexible Server (azure.microsoft.com) | 29 | 8% |
| 4 | Amazon RDS for PostgreSQL (aws.amazon.com) | 17 | 5% |
| 5 | Supabase (supabase.com) | 10 | 3% |
| 6 | MotherDuck (motherduck.com) | 7 | 2% |
| 7 | Scaleway Managed Database for PostgreSQL (scaleway.com) | 7 | 2% |
| 8 | Aiven (aiven.io) | 5 | 1% |
| 9 | ClickHouse Cloud (clickhouse.com) | 4 | 1% |
| 10 | DigitalOcean Managed PostgreSQL (digitalocean.com) | 2 | 1% |
| 11 | Azure Cosmos DB (azure.microsoft.com) | 1 | 0% |
| 12 | Tiger Cloud (tigerdata.com) | 1 | 0% |
| 13 | Render Postgres (render.com) | 1 | 0% |
| 14 | OVHcloud Managed PostgreSQL (ovhcloud.com) | 1 | 0% |

## By agent

- Claude Code (Claude Opus 5): 129 runs, first Neon (87), then Azure Database for PostgreSQL Flexible Server (16)
- Cursor (Grok 4.6): 124 runs, first Neon (86), then Azure SQL Database (14)
- Codex (GPT-5.6 Sol): 103 runs, first Neon (63), then Azure SQL Database (13)

## By persona

- Senior engineer: 190 runs, first Neon (72), then Azure SQL Database (35)
- Junior developer: 106 runs, first Neon (104), then Render Postgres (1)
- Vibe coder: 60 runs, first Neon (60)

## By what the ask stressed

- The plain ask: 259 runs, first Neon (194), then Azure SQL Database (29)
- Self-hosting, privacy or residency: 59 runs, first Azure Database for PostgreSQL Flexible Server (15), then Neon (10)
- Volume and cost at scale: 38 runs, first Neon (32), then Supabase (3)

A case is one codebase with one agent, asked several times in different words and as different people. 11 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 (Claude Code (Claude Opus 5), Cursor (Grok 4.6), Codex (GPT-5.6 Sol)) to pick a database for each of them, in several wordings and as a senior engineer 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 356 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 197 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)
- [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)