multimodal benchmark
BenchCAD
BenchCAD is a benchmark for programmatic CAD reasoning built from 17,900 execution-verified CadQuery programs spanning 106 industrial part families, roughly half anchored to real ISO, DIN, EN, ASME, and IEC specification tables. It decomposes CAD capability into matched tasks; the Vision2Code task requires models to generate CadQuery code from multi-view renders, scored by voxel IoU against the reference geometry.
Updated Aug 11, 2026
Models4
Model coverage4
MetricScore
EvidenceB
BenchCAD Ranking
Higher score ranks better on this benchmark.
| 01 | OP | 70.6% | 100.0% | 4 | C | |
| 02 | OP | 63.1% | 66.7% | 4 | C | |
| 03 | OP | 62.3% | 33.3% | 4 | C | |
| 04 | AN | 37.3% | 0.0% | 4 | C |
BenchCAD Score Distribution
A closer view of the leading scores on this benchmark.
BenchCAD Highlights
The leading models and scores on this benchmark.
What is BenchCAD?
What BenchCAD measures and how its scores work.
BenchCAD is a benchmark for programmatic CAD reasoning built from 17,900 execution-verified CadQuery programs spanning 106 industrial part families, roughly half anchored to real ISO, DIN, EN, ASME, and IEC specification tables. It decomposes CAD capability into matched tasks; the Vision2Code task requires models to generate CadQuery code from multi-view renders, scored by voxel IoU against the reference geometry.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- BenchCAD
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- benchcad|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about BenchCAD.
Which model scores highest on BenchCAD?
GPT-5.6 Sol is currently ranked first with 70.6%.
What does BenchCAD measure?
BenchCAD is a benchmark for programmatic CAD reasoning built from 17,900 execution-verified CadQuery programs spanning 106 industrial part families, roughly half anchored to real ISO, DIN, EN, ASME, and IEC specification tables. It decomposes CAD capability into matched tasks; the Vision2Code task requires models to generate CadQuery code from multi-view renders, scored by voxel IoU against the reference geometry.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
4 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.