multimodal benchmark
OVBench
OVBench is an online video understanding benchmark that evaluates a model's ability to perceive, memorize, and reason about real-time video streams as they unfold.
Updated Aug 11, 2026
Models2
Model coverage2
MetricScore
EvidenceB
OVBench Ranking
Higher score ranks better on this benchmark.
| 1 | BY | 70.0% | 100.0% | 2 | C | |
| 2 | BY | 69.7% | 0.0% | 2 | C |
OVBench Score Distribution
A closer view of the leading scores on this benchmark.
OVBench Highlights
The leading models and scores on this benchmark.
What is OVBench?
What OVBench measures and how its scores work.
OVBench is an online video understanding benchmark that evaluates a model's ability to perceive, memorize, and reason about real-time video streams as they unfold.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- OVBench
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- ovbench|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about OVBench.
Which model scores highest on OVBench?
Seed 2.1 Pro is currently ranked first with 70.0%.
What does OVBench measure?
OVBench is an online video understanding benchmark that evaluates a model's ability to perceive, memorize, and reason about real-time video streams as they unfold.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
2 model results are currently shown.
Does this benchmark affect the overall score?
No. This benchmark is shown for reference but does not contribute to the overall score.