Benchmarks / Reasoning
CAD-Eval
Uses Epoch AI's external CAD-Eval overall pass-rate leaderboard. Score: CAD-Eval overall pass rate. Collected by Jake Boggs' benchmark dashboard.
CAD-Eval
Higher is better · best effort per model
full table below
| # | Model | Effort | Score |
|---|---|---|---|
| 1 | o3 | medium | 74.0% |
| 2 | Gemini 2.5 Pro | high | 64.0% |
| 3 | o4 mini | medium | 62.0% |
| 4 | o1 | medium | 56.0% |
| 5 | Sonnet 3.7 | medium | 54.0% |
| 6 | o3 mini | medium | 54.0% |
| 7 | GPT-4.1 | high | 42.0% |
| 8 | Gemini 1.5 Pro | none | 34.0% |
| 9 | Gemini 2.0 Flash | medium | 30.0% |
| 10 | GPT-4o | high | 26.0% |
| 11 | GPT-4.1 Mini | high | 16.0% |
| 12 | Haiku 3 | medium | 12.0% |