multimodal benchmark
Video-MME
Video-MME is the first-ever comprehensive evaluation benchmark of Multi-modal Large Language Models (MLLMs) in video analysis. It features 900 videos totaling 254 hours with 2,700 human-annotated question-answer pairs across 6 primary visual domains (Knowledge, Film & Television, Sports Competition, Life Record, Multilingual, and others) and 30 subfields. The benchmark evaluates models across diverse temporal dimensions (11 seconds to 1 hour), integrates multi-modal inputs including video frames, subtitles, and audio, and uses rigorous manual labeling by expert annotators for precise assessment.
Updated Aug 7, 2026
Published models17
Registry coverage17
MetricScore
EvidenceB
Video-MME leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | BY | 89.2% | 100.0% | 17 | C | |
| 2 | BY | 89.0% | 93.8% | 17 | C | |
| 3 | AC | 88.0% | 87.5% | 17 | C | |
| 4 | XI | 87.7% | 81.3% | 17 | C | |
| 5 | MA | 87.4% | 75.0% | 17 | C | |
| 6 | MI | 85.4% | 68.8% | 17 | C | |
| 7 | GO | 84.8% | 62.5% | 17 | C | |
| 8 | AC | 84.2% | 56.3% | 17 | C | |
| 9 | GO | 78.6% | 50.0% | 17 | C | |
| 10 | AM Nova 2 OmniAmazon | 77.9% | 43.8% | 17 | C | |
| 11 | GO | 76.1% | 37.5% | 17 | C | |
| 12 | AC | 74.5% | 31.3% | 17 | C | |
| 13 | AC | 73.3% | 25.0% | 17 | C | |
| 14 | AC | 71.8% | 18.8% | 17 | C | |
| 15 | AC | 71.4% | 12.5% | 17 | C | |
| 16 | GO | 66.2% | 6.3% | 17 | C | |
| 17 | MI | 55.0% | 0.0% | 17 | C |
Score distribution
Top published rows on the benchmark's original scale.
Video-MME highlights
The top published results on this benchmark's own scale.
What is Video-MME?
Definition and scoring fields from the benchmark registry.
Video-MME is the first-ever comprehensive evaluation benchmark of Multi-modal Large Language Models (MLLMs) in video analysis. It features 900 videos totaling 254 hours with 2,700 human-annotated question-answer pairs across 6 primary visual domains (Knowledge, Film & Television, Sports Competition, Life Record, Multilingual, and others) and 30 subfields. The benchmark evaluates models across diverse temporal dimensions (11 seconds to 1 hour), integrates multi-modal inputs including video frames, subtitles, and audio, and uses rigorous manual labeling by expert annotators for precise assessment.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- Video-MME
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- video-mme|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about Video-MME.
Which model scores highest on Video-MME?
Seed 2.1 Pro is currently ranked first with 89.2%.
What does Video-MME measure?
Video-MME is the first-ever comprehensive evaluation benchmark of Multi-modal Large Language Models (MLLMs) in video analysis. It features 900 videos totaling 254 hours with 2,700 human-annotated question-answer pairs across 6 primary visual domains (Knowledge, Film & Television, Sports Competition, Life Record, Multilingual, and others) and 30 subfields. The benchmark evaluates models across diverse temporal dimensions (11 seconds to 1 hour), integrates multi-modal inputs including video frames, subtitles, and audio, and uses rigorous manual labeling by expert annotators for precise assessment.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
17 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.