ProcArena - PostgreSQL - Direct - From-Scratch Synthesis: leaderboard
Metric: Execution Accuracy (%). Source: arxiv.org. Saturation forecast: Around January 2027. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 | 68.4 |
| 2 | Gemini 3.1 Pro (Preview) | 67.5 |
| 3 | GPT-5.2 | 64.9 |
| 4 | GLM-5.3 | 62.3 |
| 5 | GPT-5.4 Mini | 57.9 |
| 6 | GLM-5.2 | 44.7 |
| 7 | DeepSeek V4 Pro | 39.5 |
Interactive version: theaggregate.ai/benchmark?slug=procarena-postgresql-direct-from-scratch-synthesis · How It Works · Data refreshed daily, snapshot 2026-09-24.