This dataset repo contains three partitions of the Reasoning-Intensive Video with Audio understanding Benchmark (RivaBench).

Academic.json: The Academic partition. Video and audio resources can be found at https://github.com/Jack-ZC8/M3AV-dataset
StandUp.json: The Standup partition. Videos and audios are provided.
synthdec.json: The synthetic video detection partition. Videos and whether they are synthesized or not are provided.

Reference

@inproceedings{
  sun2025videosalmonno1,
  title={{video-SALMONN-o1}: Reasoning-enhanced Audio-visual Large Language Model},
  author={Guangzhi Sun, Yudong Yang, Jimin Zhuang, Changli Tang, Yixuan Li, Wei Li, Zejun MA, Chao Zhang},
  booktitle={ICML},
  year={2025}
}