EgoSafetyBench
Explore score history ↗EgoSafetyBench is a diagnostic egocentric video benchmark of 1,200 robot-view scenarios to evaluate vision-language models as runtime safety guards. It assesses situational awareness across routine, suspicious, obvious, and contextual hazards, and visual-channel robustness against misleading in-scene text.
- Released
- 2026-06-30
- Institutions
- Seoul National University
- Evaluates
- Robotics, Robotics & Embodied AI, Safety
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
EgoSafetyBench paper
No reported scores are on record for this benchmark yet.