Video-MME - Long Videos without Subtitles
Multimodal · 2024-05-31
The long-duration subset of Video-MME (videos of roughly 30-60 minutes, 900 multiple-choice questions) answered from the video frames without subtitles, as OpenAI reports it under "Video-MME (long, no subtitles)". Scores are answer accuracy; not comparable with the overall no-subtitles Video-MME score, which averages short, medium and long videos. Higher is better.
Top models (higher is better)
| Model | Score |
|---|---|
| GPT-4.1 | 72.0 |
| GPT-4o (2024-11-20) | 65.3 |