Multimodal & Grounded benchmark
MLVU (M-Avg) leaderboard
MLVU mean average. Every model the catalog carries a published MLVU (M-Avg) value for, ranked by that value.
CategoryMultimodal & Grounded
MeasureVideo QA and understanding
TasksGeneral video understanding
DifficultyBroad multimodal video reasoning
Published byQwen3.6 launch benchmarks
A multi-task video understanding benchmark averaged across MLVU categories.
MLVU (M-Avg) ranking
4 models with a published MLVU (M-Avg) value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Video QA and understanding |
|---|---|---|---|
| 1 |  Qwen3.8 Max | Alibaba | 90.8 |
| 2 | Qwen3.7 Plus | Alibaba | 87.4 |
| 3 | Qwen3.6-27B | Alibaba | 86.6 |
| 4 | Qwen3.6-35B-A3B | Alibaba | 86.2 |
Evidence key: Observed
Rows are ordered by the value Qwen3.6 launch benchmarks published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.