3DCodeBench
Explore score history ↗3DCodeBench evaluates vision-language model agents on procedural 3D modeling by converting text and image references into Blender Python code. It includes 212 object categories with ground-truth scripts, and scores outputs on executability, image similarity (SigLIP-2/DINOv3), 3D shape distance (Chamfer/Uni3D), and LLM-as-judge, plus a human-preference ranking platform.
- Released
- 2026-05-31
- Institutions
- University of Southern California · Google (United States)
- Evaluates
- General AI, Geometric reasoning, Multimodal
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
3DCodeBench paper and code
No reported scores are on record for this benchmark yet.