Video Understanding on VideoVista
79.67AccuracyLinVT-Qwen2-VL
Evaluation Results
| Method | Links | |
|---|---|---|
| LinVT-Qwen2-VLSize=7B2024.12 | 79.67 | |
| LinVT-InternVL2Size=8B2024.12 | 78.64 | |
| LinVT-MolmoSize=7B2024.12 | 77.41 | |
| MECoT2025.12 | 74.23 | |
| LV-OV2025.12 | 72.99 | |
| KangarooSize=8B2024.12 | 69.5 | |
| Video-CCAMSize=9B2024.12 | 69 | |
| LinVT-BLIP-3Size=4B2024.12 | 68.62 | |
| VILA-1.5Size=8B2024.12 | 66.12 | |
| ShareGPT4VideoSize=8B2024.12 | 64.18 | |
| VideoChat2-HDSize=7B2024.12 | 61.58 | |
| VideoLLaMA 2# Frames=16, Parameters=7B2024.06 | 60.47 | |
| VideoLLaMA2Size=7B2024.12 | 60.47 | |
| PLLAVASize=7B2024.12 | 60.36 | |
| LinVT-AquilaSize=2B2024.12 | 60.13 | |
| Video-LLaVASize=7B2024.12 | 56.96 | |
| LLaMA-VIDSize=7B2024.12 | 56.87 | |
| LLaVA-NeXT-VideoSize=7B2024.12 | 56.66 | |
| LinVT-MiphaSize=1.6B2024.12 | 55.62 | |
| MiniGPT4-VideoSize=7B2024.12 | 53.58 | |
| VideoChatGPTSize=7B2024.12 | 36.65 |