RealCADBench - Execution Rate: leaderboard
Metric: Execution Rate (0-1). Source: arxiv.org. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 | 0.93 |
| 2 | Claude Opus 4.8 | 0.89 |
| 3 | Gemini 3.1 Pro (Preview) | 0.88 |
| 4 | GPT-5.4 | 0.8 |
| 5 | Qwen 3.8 27B | 0.8 |
| 6 | Seed 2.0 Pro | 0.43 |
| 7 | Kimi K3 | 0.34 |
Interactive version: theaggregate.ai/benchmark?slug=realcadbench-execution-rate · How It Works · Data refreshed daily, snapshot 2026-09-20.