MEventBench
Explore score history ↗MEventBench is a multi-event long video understanding benchmark introduced alongside the MoD-VLLM framework, evaluating temporal grounding and semantic understanding.
- Released
- 2026-07-17
- Institutions
- Tsinghua University · Beijing National Research Center for Information Science and Technology
- Evaluates
- General AI, Reasoning, Vision & 3D
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
MEventBench paper
No reported scores are on record for this benchmark yet.