| audio-visual-question-answering-on-dailyomni | OmniSeek (ours) | – | Accuracy: 80.0 |
| audio-visual-question-answering-on-futureomni | OmniSeek (ours) | – | Accuracy: 58.3 |
| audio-visual-question-answering-on-lvomnibench | OmniSeek (ours) | – | Accuracy: 44.2 |
| audio-visual-question-answering-on-omnivideobench | OmniSeek (ours) | – | Accuracy: 47.7 |
| audio-visual-question-answering-on-worldsense | OmniSeek (ours) | – | Accuracy: 62.4 |
| video-question-answering-on-lvbench | OmniSeek (ours) | – | Accuracy: 51.4 |
| video-question-answering-on-mlvu | OmniSeek (ours) | – | Accuracy: 77.1 |
| video-question-answering-on-videoholmes | OmniSeek (ours) | – | Accuracy: 74.6 |