Long Video Event Prediction on MILES
62.81AccuracyVISTA
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| VISTA2026.05 | 62.81 | 25.73 | 32.52 | 25.34 | 63.42 | |
| Video-RAG2026.05 | 44.71 | 17.78 | 21.71 | 18.13 | 45.62 | |
| VideoAgentvariant=F2026.05 | 43.24 | 16.41 | 19.77 | 17.42 | 44.15 | |
| LongVILAfine-tuning=true2026.05 | 42.21 | 15.84 | 18.03 | 16.31 | 41.32 | |
| Goldfish2026.05 | 41.72 | 15.47 | 19.31 | 16.51 | 43.57 | |
| Video-CCAMfine-tuning=true2026.05 | 41.03 | 15.72 | 18.51 | 16.21 | 40.24 | |
| VideoAgentvariant=W2026.05 | 41.03 | 15.67 | 18.12 | 16.35 | 42.31 | |
| LongVILA2026.05 | 40.38 | 14.41 | 17.71 | 15.01 | 42.32 | |
| LongLLaVA2026.05 | 38.61 | 13.44 | 16.41 | 14.79 | 39.71 | |
| Video-CCAM2026.05 | 38.46 | 13.12 | 16.23 | 14.41 | 40.24 | |
| Movie-LLM2026.05 | 37.5 | 13.92 | 16.12 | 13.35 | 39.57 | |
| Video-XL2026.05 | 36.24 | 12.63 | 15.23 | 12.97 | 38.01 | |
| LLaMA-VID2026.05 | 35.47 | 12.75 | 14.51 | 12.21 | 35.85 | |
| LLaMA-VIDfine-tuning=true2026.05 | 35.1 | 12.87 | 14.35 | 12.48 | 36.85 | |
| MovieChatfine-tuning=true2026.05 | 34.78 | 12.67 | 14.53 | 12.41 | 35.18 | |
| MovieChat2026.05 | 33.33 | 12.12 | 13.83 | 11.62 | 35.13 | |
| OC-2-Reasoning2026.05 | 27.88 | 7.16 | 8.14 | 6.93 | 32.14 | |
| VLEP2026.05 | 25.16 | — | — | — | — |