knowledge benchmark
VideoSimpleQA
VideoSimpleQA evaluates factual knowledge grounded in video content, measuring how accurately models answer short, fact-seeking questions about videos.
Updated Aug 11, 2026
Models2
Model coverage2
MetricScore
EvidenceB
VideoSimpleQA Ranking
Higher score ranks better on this benchmark.
| 1 | BY | 76.4% | 100.0% | 2 | C | |
| 2 | BY | 71.4% | 0.0% | 2 | C |
VideoSimpleQA Score Distribution
A closer view of the leading scores on this benchmark.
VideoSimpleQA Highlights
The leading models and scores on this benchmark.
What is VideoSimpleQA?
What VideoSimpleQA measures and how its scores work.
VideoSimpleQA evaluates factual knowledge grounded in video content, measuring how accurately models answer short, fact-seeking questions about videos.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- VideoSimpleQA
- Modality
- multimodal
- Primary category
- knowledge
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- videosimpleqa|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about VideoSimpleQA.
Which model scores highest on VideoSimpleQA?
Seed 2.1 Pro is currently ranked first with 76.4%.
What does VideoSimpleQA measure?
VideoSimpleQA evaluates factual knowledge grounded in video content, measuring how accurately models answer short, fact-seeking questions about videos.
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.