CadEval: leaderboard
CAD and technical-code evaluation tasks for model coding capability tracking.
Metric: Score (self-reported). Source: benchmarklist.com. Status: saturated. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | O3 | 74 |
| 2 | Gemini 2.5 Pro (Preview 06-05) | 64 |
| 3 | O4 Mini (Medium) | 62 |
| 4 | O1 | 56 |
| 5 | Claude 3.7 Sonnet | 54 |
| 6 | GPT-4.1 | 42 |
| 7 | Gemini 1.5 Flash | 34 |
| 8 | Claude 3.5 Haiku | 32 |
| 9 | GPT-4o | 26 |
| 10 | GPT-4.1 Mini | 16 |
Interactive version: theaggregate.ai/benchmark?slug=cadeval · How It Works · Data refreshed daily, snapshot 2026-09-05.