multimodal benchmark
VideoSimpleQA
VideoSimpleQA evaluates factual knowledge grounded in video content, measuring how accurately models answer short, fact-seeking questions about videos.
Updated Aug 7, 2026
Published models2
Registry coverage2
MetricScore
EvidenceB
VideoSimpleQA leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | BY | 76.4% | 100.0% | 2 | C | |
| 2 | BY | 71.4% | 0.0% | 2 | C |
Score distribution
Top published rows on the benchmark's original scale.
VideoSimpleQA highlights
The top published results on this benchmark's own scale.
What is VideoSimpleQA?
Definition and scoring fields from the benchmark registry.
VideoSimpleQA evaluates factual knowledge grounded in video content, measuring how accurately models answer short, fact-seeking questions about videos.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- VideoSimpleQA
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- videosimpleqa|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
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 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.