VisualLeakBench
Explore score history ↗VisualLeakBench is a 500-image benchmark for evaluating action-boundary propagation failures in vision-language agents, with stratified subsets and oracle diagnostics.
- Released
- 2026-05-29
- Evaluates
- Agents, General AI, Multimodal
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
VisualLeakBench paper
No reported scores are on record for this benchmark yet.