Multimodal & Grounded benchmark
Video-MME (with subtitle) leaderboard
Video-MME with subtitle. Every model the catalog carries a published Video-MME (with subtitle) value for, ranked by that value.
CategoryMultimodal & Grounded
MeasureVideo QA with subtitle context
TasksVideo understanding
DifficultyMultimodal video reasoning
Published byQwen3.6 launch benchmarks
A video understanding benchmark that allows subtitle access when answering multimodal questions about videos.
Video-MME (with subtitle) ranking
6 models with a published Video-MME (with subtitle) 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 with subtitle context |
|---|---|---|---|
| 1 |  Qwen3.8 Max | Alibaba | 90.4 |
| 2 | Qwen3.7 Plus | Alibaba | 88.0 |
| 3 |  MiMo-V2.5 | Xiaomi | 87.7 |
| 3 | Qwen3.6-27B | Alibaba | 87.7 |
| 5 | Qwen3.6-35B-A3B | Alibaba | 86.6 |
| 6 |  MiniMax M3 | MiniMax | 85.4 |
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.