ProcArena - Oracle - Interactive - Code Composition: leaderboard
Metric: Execution Accuracy (%). Source: arxiv.org. Saturation forecast: Around 2029. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 | 29.7 |
| 2 | Gemini 3.1 Pro (Preview) | 28 |
| 3 | GLM-5.3 | 23.7 |
| 4 | GPT-5.2 | 22 |
| 5 | GPT-5.4 Mini | 22 |
| 6 | DeepSeek V4 Pro | 19.5 |
| 7 | GLM-5.2 | 16.9 |
Interactive version: theaggregate.ai/benchmark?slug=procarena-oracle-interactive-code-composition · How It Works · Data refreshed daily, snapshot 2026-09-24.