Video Question Answering on EgoSchema (Full/Subset Metrics)
72.2Accuracy (Subset)A.I.R.
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| A.I.R.Venue=-, Base Model=InternVL3-8B, #Frames=≤322025.10 | 72.2 | 63.3 | |
| A.I.R.Venue=-, Base Model=GPT-4o, #Frames=≤322025.10 | 72 | — | |
| AKEYSVenue=arXiv’25, Base Model=GPT-4o, #Frames=≤322025.10 | 68.6 | 63.6 | |
| T*Venue=CVPR’25, Base Model=LLaVA-OV-7B, #Frames=82025.10 | 66.6 | — | |
| DrVideoVenue=CVPR’25, Base Model=GPT-4, #Frames=-2025.10 | 66.4 | 61 | |
| A.I.R.Venue=-, Base Model=Qwen2VL-7B, #Frames=≤322025.10 | 66.2 | 62.5 | |
| A.I.R.Venue=-, Base Model=LLaVA-OV-7B, #Frames=≤322025.10 | 63.2 | 61.4 | |
| VideoAgent2Venue=arXiv’25, Base Model=GPT-4o, #Frames=-2025.10 | — | 75.4 |