| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Video Question Answering | VCGBench (test) | Score3.51 | 16 | |
| Video Text Generation | VCGBench | Correct Information (CI)3.64 | 14 | |
| Video Question Answering | VCGBench ActivityNet | CI3.27 | 9 | |
| Video-based Text Generation | VCGBench 1.0 (test) | CI3.81 | 6 | |
| Video Conversation | VCGBench-Diverse (test) | CI Score2.46 | 6 |