| Benchmark | Model | Rank | Results |
|---|---|---|---|
| video-question-answering-on-activitynet-qa | IPFormer-VideoLLM | – | Accuracy: 50.1 |
| zeroshot-video-question-answer-on-activitynet-qa | IPFormer-VideoLLM | – | Accuracy: 50.1 |
| zeroshot-video-question-answer-on-msrvtt-qa | IPFormer-VideoLLM | – | Accuracy: 63.2 |
| zeroshot-video-question-answer-on-msvd-qa | IPFormer-VideoLLM | – | Accuracy: 73.8 |