long context benchmark
MLVU Leaderboard
MLVU is a benchmark for multi-task long video understanding in multimodal large language models.
Updated Sep 5, 2026
Models10
Model coverage10
MetricScore
EvidenceB
MLVU Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAC | Score87.40% | Percentile100.00% | Participants10 | EvidenceC | Evaluated |
| Rank02 | ModelAC | Score87.30% | Percentile88.89% | Participants10 | EvidenceC | Evaluated |
| Rank03 | ModelAC | Score86.70% | Percentile77.78% | Participants10 | EvidenceC | Evaluated |
| Rank04 | ModelAC | Score86.60% | Percentile66.67% | Participants10 | EvidenceC | Evaluated |
| Rank05 | ModelAC | Score86.20% | Percentile55.56% | Participants10 | EvidenceC | Evaluated |
| Rank06 | ModelAC | Score85.90% | Percentile44.44% | Participants10 | EvidenceC | Evaluated |
| Rank07 | ModelAC | Score85.60% | Percentile33.33% | Participants10 | EvidenceC | Evaluated |
| Rank08 | ModelAC | Score84.30% | Percentile22.22% | Participants10 | EvidenceC | Evaluated |
| Rank09 | ModelAC | Score83.80% | Percentile11.11% | Participants10 | EvidenceC | Evaluated |
| Rank10 | ModelAC | Score70.20% | Percentile0.00% | Participants10 | EvidenceC | Evaluated |
MLVU Highlights
The leading models and scores on this benchmark.
MLVU Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for MLVU
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is MLVU?
What MLVU measures and how its scores work.
MLVU evaluates multimodal large language models on videos ranging from 3 minutes to 2 hours across 9 distinct tasks.
It measures performance on tasks including reasoning, captioning, recognition, and summarization, reported as a Score ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- MLVU
- Modality
- multimodal
- Primary category
- long context
- 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 MLVU.
Which model scores highest on MLVU?
Qwen3.7-Plus is currently ranked first with 87.40%.
What are the top three models on MLVU?
The current leaders are Qwen3.7-Plus (87.40%), Qwen3.5-122B-A10B (87.30%), and Qwen3.6 Plus (86.70%).
Which MLVU model has the lowest official input price?
Qwen3.6-35B-A3B has the lowest matched official input price at $0.25 input / $1.5 output per 1M tokens.
Which models are fastest among MLVU results?
No matched runtime record is currently available.
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.