CadEval: leaderboard
CAD and technical-code evaluation tasks for model coding capability tracking.
Metric: Score (imported). Source: neosignal.io. Source: benchmarklist.com. Saturation forecast: Estimated already saturated. 10 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | O3 | 74 | #124 |
| 2 | Gemini 2.5 Pro (Preview 06-05) | 64 | #106 |
| 3 | O4 Mini (Medium) | 62 | #180 (O4 Mini) |
| 4 | O1 | 56 | #183 |
| 5 | Claude 3.7 Sonnet | 54 | #249 |
| 6 | GPT-4.1 | 42 | #248 |
| 7 | Gemini 1.5 Flash | 34 | #618 |
| 8 | Claude 3.5 Haiku | 32 | #568 |
| 9 | GPT-4o | 26 | #343 |
| 10 | GPT-4.1 Mini | 16 | #355 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=cadeval · How It Works · Data refreshed daily, snapshot 2026-10-20.