AI benchmarks and leaderboards are different things
Learn the difference between a benchmark, an evaluation run and a leaderboard, and use each to answer the right question.
Model reports
OmniVideoBench
1,000 audio-visual reasoning questions over 628 videos (seconds to 30 minutes long), targeting synergistic audio-visual understanding in Omni MLLMs, by the NJU-LINK team; an ICLR 2026 poster. Video length and audio-video correlation vary widely, so per-model results depend heavily on which subset is sampled and on frame/audio chunking strategy.
Evaluation context and evidence
- Source
- Model reports
- Publisher
- Not recorded
- Benchmark release
- 2025-10-12
- Collected
- Not recorded
- Modality
- Not recorded
These are source-reported observations, not independent reruns by this site. Check the task version, evaluation protocol, unit and reporting date before comparing models. Results from different setups are not a universal ranking.
Original sources
Reported results 0
This source record has no numeric results in our collection. That does not mean a score of zero or that no public results exist. Consult the original resources above.