Agent leaderboards / All sectors / Databases
Databases: which databases coding agents choose
Neon took about 66% of the database picks.
Read this leaderboard as textrankings, key learnings, method
Key learnings
We asked Cursor, Claude Code and Codex to pick a database for six small apps, across 356 runs. We asked in different words and as different people. Azure SQL Database came second at about 10%.
Residency and privacy asks moved the order
In the 59 runs where the ask involved self-hosting, privacy or residency, Azure Database for PostgreSQL Flexible Server led with 15 wins. Neon took 10 of those. In the 259 plain asks it took 194.
The wording changed the answer more often than not
Take one codebase with one agent, asked several times in different words. In 11 of 18 such cases the runs did not all land on the same product.
Two of the three personas barely varied
Junior developers picked Neon in 104 of 106 runs. All 60 vibe coder runs went the same way. Senior engineers spread wider, sending 35 runs to Azure SQL Database.
Named in many plans, chosen in none
Turso was mentioned in 105 runs and won nothing. BigQuery had 66 mentions and PlanetScale 63, both without a win.
- The simulated user sent the agent back at least once in 197 runs.
- In 144 runs it refused to approve the plan until the agent named a specific product.
- PostgreSQL came up in 354 runs but is the engine most of these services run, not a service to sign up for.
- MotherDuck won seven times, all of them in the partner inventory pipeline, a Python batch job.
The ranking356 runs
| Product | Wins | Share | ||
|---|---|---|---|---|
| 1 | Neonneon.tech | 236 | 66% | |
| 2 | Azure SQL Databaseazure.microsoft.com | 35 | 10% | |
| 3 | Azure Database for PostgreSQL Flexible Serverazure.microsoft.com | 29 | 8% | |
| 4 | Amazon RDS for PostgreSQLaws.amazon.com | 17 | 5% | |
| 5 | Supabasesupabase.com | 10 | 3% | |
| 6 | MotherDuckmotherduck.com | 7 | 2% | |
| 7 | Scaleway Managed Database for PostgreSQLscaleway.com | 7 | 2% | |
| 8 | Aivenaiven.io | 5 | 1% | |
| 9 | ClickHouse Cloudclickhouse.com | 4 | 1% | |
| 10 | DigitalOcean Managed PostgreSQLdigitalocean.com | 2 | 1% | |
| 11 | Azure Cosmos DBazure.microsoft.com | 1 | 0% | |
| 12 | Tiger Cloudtigerdata.com | 1 | 0% | |
| 13 | Render Postgresrender.com | 1 | 0% | |
| 14 | OVHcloud Managed PostgreSQLovhcloud.com | 1 | 0% |
By agent, by persona, by wording
By agent
| Claude Code · Claude Opus 5129 runs | Neon · 87then Azure Database for PostgreSQL Flexible Server · 16 |
| Cursor · Grok 4.6124 runs | Neon · 86then Azure SQL Database · 14 |
| Codex · GPT-5.6 Sol103 runs | Neon · 63then Azure SQL Database · 13 |
By persona
| Senior engineer190 runs | Neon · 72then Azure SQL Database · 35 |
| Junior developer106 runs | Neon · 104then Render Postgres · 1 |
| Vibe coder60 runs | Neon · 60 |
By what the ask stressed
| The plain ask259 runs | Neon · 194then Azure SQL Database · 29 |
| Self-hosting, privacy or residency59 runs | Azure Database for PostgreSQL Flexible Server · 15then Neon · 10 |
| Volume and cost at scale38 runs | Neon · 32then 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 database.
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. Read the methodology and the publications.
If you sell in this sector: what these numbers mean for a vendor.
Open the interactive boardThis page as Markdown