OR-Bench
Explore score history ↗Vision-language models (VLMs) can detect that an object has rotated across views, but cannot reliably tell by how much.
- Released
- 2026-10-05
- Institutions
- The University of Queensland · Westlake University
- Evaluates
- General AI, Reasoning, Vision & 3D
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- rule-auto-admitted
OR-Bench paper
No reported scores are on record for this benchmark yet.