| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Text-to-Video Generation | 200-sequence multi-cultural benchmark | NC Score4.82 | 10 | |
| Multi-shot Generation | multi-cultural benchmark I2V | Temporal Alignment (TA)20.62 | 6 | |
| Multi-shot Video Generation | Multi-cultural benchmark 6+ shots | NC Score5 | 4 | |
| Multi-shot Video Generation | Multi-cultural benchmark 5 shots | NC Score4.91 | 4 | |
| Multi-shot Video Generation | Multi-cultural benchmark 3-4 shots | NC Score4.98 | 4 | |
| Multi-shot Generation | multi-cultural benchmark (R2V) | Temporal Alignment (TA)17.98 | 2 | |
| Multi-shot Generation | multi-cultural benchmark T2V | Text Alignment Score (TA)19.17 | 2 |