ProcArena - PostgreSQL - Interactive - Code Repair: leaderboard
ProcArena tests PL/SQL synthesis and editing on PostgreSQL and Oracle by executing generated code against held-out calls and checking outputs and persistent database state. Direct generation and interactive tool-assisted development are separate evaluation modes. This series reports ProcArena - PostgreSQL - Interactive - Code Repair from 2609.06527v1, S5.T6: Execution Accuracy (%). Higher is better.
Metric: Execution Accuracy (%). Source: arxiv.org. Saturation forecast: Around February 2027. 7 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 74.2 | #66 |
| 2 | GPT-5.5 | 71.7 | #34 |
| 3 | GPT-5.2 | 60.8 | #116 |
| 4 | GLM-5.3 | 55 | #45 |
| 5 | GPT-5.4 Mini | 54.2 | #229 |
| 6 | GLM-5.2 | 52.5 | #82 |
| 7 | DeepSeek V4 Pro | 29.2 | #113 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #6 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=procarena-postgresql-interactive-code-repair · How It Works · Data refreshed daily, snapshot 2026-11-07.