multimodal benchmark
MMBench-Video
A long-form multi-shot benchmark for holistic video understanding that incorporates approximately 600 web videos from YouTube spanning 16 major categories, with each video ranging from 30 seconds to 6 minutes. Includes roughly 2,000 original question-answer pairs covering 26 fine-grained capabilities.
Updated Aug 11, 2026
Models3
Model coverage3
MetricScore
EvidenceB
MMBench-Video Ranking
Higher score ranks better on this benchmark.
| 01 | AC | 2.0% | 100.0% | 3 | C | |
| 02 | AC | 1.9% | 50.0% | 3 | C | |
| 03 | AC | 1.8% | 0.0% | 3 | C |
MMBench-Video Score Distribution
A closer view of the leading scores on this benchmark.
MMBench-Video Highlights
The leading models and scores on this benchmark.
What is MMBench-Video?
What MMBench-Video measures and how its scores work.
A long-form multi-shot benchmark for holistic video understanding that incorporates approximately 600 web videos from YouTube spanning 16 major categories, with each video ranging from 30 seconds to 6 minutes. Includes roughly 2,000 original question-answer pairs covering 26 fine-grained capabilities.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- MMBench-Video
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- mmbench-video|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about MMBench-Video.
Which model scores highest on MMBench-Video?
Qwen2.5 VL 72B Instruct is currently ranked first with 2.0%.
What does MMBench-Video measure?
A long-form multi-shot benchmark for holistic video understanding that incorporates approximately 600 web videos from YouTube spanning 16 major categories, with each video ranging from 30 seconds to 6 minutes. Includes roughly 2,000 original question-answer pairs covering 26 fine-grained capabilities.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
3 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.