multimodal benchmark
VideoMME w sub. Leaderboard
VideoMME w sub. is a multimodal video-analysis benchmark with 900 videos totaling 254 hours and 2,700 question-answer pairs across 6 primary visual domains and 30 subfields.
Updated Sep 5, 2026
Models10
Model coverage10
MetricScore
EvidenceB
VideoMME w sub. Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAC | Score90.40% | Percentile100.00% | Participants10 | EvidenceC | Evaluated |
| Rank02 | ModelAC | Score87.70% | Percentile88.89% | Participants10 | EvidenceC | Evaluated |
| Rank03 | ModelAC | Score87.30% | Percentile77.78% | Participants10 | EvidenceC | Evaluated |
| Rank04 | ModelAC | Score87.00% | Percentile66.67% | Participants10 | EvidenceC | Evaluated |
| Rank05 | ModelOP | Score86.70% | Percentile55.56% | Participants10 | EvidenceC | Evaluated |
| Rank06 | ModelAC | Score86.60% | Percentile44.44% | Participants10 | EvidenceC | Evaluated |
| Rank07 | ModelAC | Score86.60% | Percentile33.33% | Participants10 | EvidenceC | Evaluated |
| Rank08 | ModelAC | Score77.90% | Percentile22.22% | Participants10 | EvidenceC | Evaluated |
| Rank09 | ModelAC | Score72.40% | Percentile11.11% | Participants10 | EvidenceC | Evaluated |
| Rank10 | ModelAC | Score71.60% | Percentile0.00% | Participants10 | EvidenceC | Evaluated |
VideoMME w sub. Highlights
The leading models and scores on this benchmark.
VideoMME w sub. Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for VideoMME w sub.
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is VideoMME w sub.?
What VideoMME w sub. measures and how its scores work.
VideoMME w sub. is a benchmark for evaluating multimodal large language models in video analysis using video frames, subtitles, and audio.
It measures temporal understanding across videos ranging from 11 seconds to 1 hour, with a Score reported as a ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- VideoMME w sub.
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about VideoMME w sub..
Which model scores highest on VideoMME w sub.?
Qwen3.8 Max is currently ranked first with 90.40%.
What are the top three models on VideoMME w sub.?
The current leaders are Qwen3.8 Max (90.40%), Qwen3.6-27B (87.70%), and Qwen3.5-122B-A10B (87.30%).
Which VideoMME w sub. model has the lowest official input price?
Qwen2.5-Omni-7B has the lowest matched official input price at $0.10 input / $0.40 output per 1M tokens.
Which models are fastest among VideoMME w sub. results?
The fastest matched records are GPT-5 (100.00 tok/s via OpenAI) and Qwen3.8 Max (60.87 tok/s via DeepInfra).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.