Benchmark
BenchCAD
BenchCAD is a benchmark for programmatic CAD reasoning built from 17,900 execution-verified CadQuery programs spanning 106 industrial part families…
- Modality
- multimodal
- Categories
- multimodal, reasoning, code, vision
- Openness
- unknown
- Source
- llm_stats
- Reported scores
- 4
Reported scores
llm_stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Claude Sonnet 5 | Anthropic | 0.373 | 2026-06-30 | evidence |
| GPT-5.6 Luna | OpenAI | 0.631 | 2026-07-09 | evidence |
| GPT-5.6 Sol | OpenAI | 0.706 | 2026-07-09 | evidence |
| GPT-5.6 Terra | OpenAI | 0.623 | 2026-07-09 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.