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 11, 2026
Models10
Model coverage10
MetricScore
EvidenceB
VideoMME w/o sub. Ranking
Higher score ranks better on this benchmark.
| 01 | AC | 83.9% | 100.0% | 10 | C | |
| 02 | AC | 82.8% | 88.9% | 10 | C | |
| 03 | AC | 82.5% | 77.8% | 10 | C | |
| 04 | AC | 82.5% | 66.7% | 10 | C | |
| 05 | AC | 79.2% | 55.6% | 10 | C | |
| 06 | AC | 79.0% | 44.4% | 10 | C | |
| 07 | AC | 77.3% | 33.3% | 10 | C | |
| 08 | AC | 73.3% | 22.2% | 10 | C | |
| 09 | AC | 70.5% | 11.1% | 10 | C | |
| 10 | AC | 65.1% | 0.0% | 10 | C |
VideoMME w/o sub. Score Distribution
A closer view of the leading scores on this benchmark.
VideoMME w/o sub. Highlights
The leading models and scores on this benchmark.
What is VideoMME w/o sub.?
What VideoMME w/o sub. measures and how its scores work.
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. This benchmark is not independently verified and has an evidence level of B.
- Family
- VideoMME w/o sub.
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- videomme-w-o-sub.|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
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 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.