Statebench
Explore score history ↗Evaluates world-state reasoning in video continuation through 200 cross-segment tasks across past-visible, occluded-process, and complex-transition state categories, with scoring based on state equivalence, state correctness, and hallucination rate.
- Released
- 2026-09-03
- Evaluates
- General AI, Reasoning, Vision & 3D
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- ai-reviewed
Statebench paper and code
No reported scores are on record for this benchmark yet.