Benchmark
CADWorld Benchmark
What is CADWorld?
Evaluates long-horizon computer use in FreeCAD through 200 tasks spanning 11 mechanical-CAD workflow categories, with success determined by executable checks…
- Released
- 2026-09-14
- Evaluates
- CAD, Geometric reasoning, Manufacturing & Process Control, Science & Engineering
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- ai-reviewed
- Reported scores
- 0
Source provenance
- Original evidence https://arxiv.org/abs/2609.16251
CADWorld paper
No reported scores are on record for this benchmark yet.