multimodal benchmark
MMVU Leaderboard
MMVU (Multimodal Multi-disciplinary Video Understanding) is a multimodal benchmark for evaluating models on video understanding tasks across multiple disciplines.
Updated Sep 5, 2026
Models5
Model coverage5
MetricScore
EvidenceB
MMVU Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelZA | Score80.50% | Percentile100.00% | Participants5 | EvidenceC | Evaluated |
| Rank02 | ModelMA | Score80.40% | Percentile75.00% | Participants5 | EvidenceC | Evaluated |
| Rank03 | ModelAC | Score74.70% | Percentile50.00% | Participants5 | EvidenceC | Evaluated |
| Rank04 | ModelAC | Score73.30% | Percentile25.00% | Participants5 | EvidenceC | Evaluated |
| Rank05 | ModelAC | Score72.30% | Percentile0.00% | Participants5 | EvidenceC | Evaluated |
MMVU Highlights
The leading models and scores on this benchmark.
MMVU Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for MMVU
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is MMVU?
What MMVU measures and how its scores work.
MMVU is a benchmark for evaluating multimodal models on video understanding tasks across multiple disciplines.
MMVU measures comprehension and reasoning capabilities on video content, with the metric reported as Score in ratio units.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- MMVU
- 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 MMVU.
Which model scores highest on MMVU?
GLM-5.3-Flash is currently ranked first with 80.50%.
What are the top three models on MMVU?
The current leaders are GLM-5.3-Flash (80.50%), Kimi K2.5 (80.40%), and Qwen3.5-122B-A10B (74.70%).
Which MMVU model has the lowest official input price?
GLM-5.3-Flash has the lowest matched official input price at $0.08 input / $0.25 output per 1M tokens.
Which models are fastest among MMVU results?
The fastest matched records are GLM-5.3-Flash (74.28 tok/s via FriendliAI).
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.