CADBench — leaderboard
Metric: IoU Aggregate (self-reported). Source: benchmarklist.com. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.7 | 41.2 |
| 2 | Gemini 3.1 Pro (Preview) | 38.2 |
| 3 | GPT-5.4 | 15.8 |
| 4 | Qwen 3.5 27B | 1.5 |
| 5 | Qwen 3.5 9B | 0 |
Interactive version: theaggregate.ai/benchmark?slug=cadbench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.