← Benchmarks
BenchCAD (with Python tool)
BenchCAD variant evaluated with access to a Python tool for programmatic CAD reasoning.
id benchcad-with-python-tool · max 1 · 5 models reported
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 5.5 Anthropic | 0.96 |
| 2 | GPT-6 Astra OpenAI | 0.96 |
| 3 | GPT-5.6 Sol OpenAI | 0.83 |
| 4 | GPT-5.6 Terra OpenAI | 0.78 |
| 5 | GPT-5.6 Luna OpenAI | 0.74 |