MUSE (Text-to-CAD) - Geometric Validity: leaderboard
Metric: Geometric validity (%): share of the 106 design specifications whose exported STEP model passes all four binary geometry checks (watertight, manifold, self-intersection free, overlap free), one CadQuery script per design specification, executed in a sandbox; funnel evaluation, so a sample that fails a stage scores zero on every later stage; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 15 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 | 68.87 |
| 2 | Gemini 3.1 Pro (Preview) | 58.49 |
| 3 | Claude Opus 4.7 | 58.49 |
| 4 | GLM-5.1 | 27.36 |
| 5 | Claude 3.7 Sonnet | 23.58 |
| 6 | Llama 3.1 70B | 23.58 |
| 7 | Qwen 2.5 72B | 20.75 |
| 8 | GPT-4o | 13.21 |
| 9 | Qwen 3.5 122B A10B | 13.21 |
| 10 | MiniMax-M2.7 | 10.38 |
| 11 | MiniMax-M2.5 | 10.38 |
| 12 | Qwen 3.6 35B A3B | 5.66 |
| 13 | GLM-4.7 Flash | 5.66 |
| 14 | Llama 3.1 8B | 1.89 |
Interactive version: theaggregate.ai/benchmark?slug=muse-text-to-cad-geometric-validity · How It Works · Data refreshed daily, snapshot 2026-10-07.