multimodal benchmark
VideoMME w/o sub.
Video-MME is a comprehensive evaluation benchmark for multi-modal large language models in video analysis. It features 900 videos across 6 primary visual domains with 30 subfields, ranging from 11 seconds to 1 hour in duration, with 2,700 question-answer pairs. The benchmark evaluates MLLMs' capabilities in processing sequential visual data and multi-modal content including video frames, subtitles, and audio.
Updated Aug 7, 2026
Published models10
Registry coverage10
MetricScore
EvidenceB
VideoMME w/o sub. leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | AC | 83.9% | 100.0% | 10 | C | |
| 2 | AC | 82.8% | 88.9% | 10 | C | |
| 3 | AC | 82.5% | 77.8% | 10 | C | |
| 4 | AC | 82.5% | 66.7% | 10 | C | |
| 5 | AC | 79.2% | 55.6% | 10 | C | |
| 6 | AC | 79.0% | 44.4% | 10 | C | |
| 7 | AC | 77.3% | 33.3% | 10 | C | |
| 8 | AC | 73.3% | 22.2% | 10 | C | |
| 9 | AC | 70.5% | 11.1% | 10 | C | |
| 10 | AC | 65.1% | 0.0% | 10 | C |
Score distribution
Top published rows on the benchmark's original scale.
VideoMME w/o sub. highlights
The top published results on this benchmark's own scale.
What is VideoMME w/o sub.?
Definition and scoring fields from the benchmark registry.
Video-MME is a comprehensive evaluation benchmark for multi-modal large language models in video analysis. It features 900 videos across 6 primary visual domains with 30 subfields, ranging from 11 seconds to 1 hour in duration, with 2,700 question-answer pairs. The benchmark evaluates MLLMs' capabilities in processing sequential visual data and multi-modal content including video frames, subtitles, and audio.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- VideoMME w/o sub.
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- videomme-w-o-sub.|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about VideoMME w/o sub..
Which model scores highest on VideoMME w/o sub.?
Qwen3.5-122B-A10B is currently ranked first with 83.9%.
What does VideoMME w/o sub. measure?
Video-MME is a comprehensive evaluation benchmark for multi-modal large language models in video analysis. It features 900 videos across 6 primary visual domains with 30 subfields, ranging from 11 seconds to 1 hour in duration, with 2,700 question-answer pairs. The benchmark evaluates MLLMs' capabilities in processing sequential visual data and multi-modal content including video frames, subtitles, and audio.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
10 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.