Event-level script generation on V2S 5-minute videos (test)
47.4Character ScoreSeed-2.0-pro
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| Seed-2.0-proOmni=×2026.04 | 47.4 | 68.1 | 42.9 | 35.7 | 10.3 | 40.9 | 67.1 | |
| Gemini-2.5-proOmni=✓2026.04 | 41.7 | 75 | 41.9 | 39 | 17 | 42.9 | 73.4 | |
| Seed-1.8Omni=×2026.04 | 40.9 | 54.4 | 35.1 | 29.6 | 12.4 | 34.5 | 50.7 | |
| Gemini-2.5-flashOmni=✓2026.04 | 40.1 | 75.5 | 42.8 | 36.5 | 22.8 | 43.6 | 74.3 | |
| Gemini-3-proOmni=✓2026.04 | 39.8 | 68.8 | 37.4 | 35.4 | 13.3 | 38.9 | 64.4 | |
| OmniScriptParam./B=8, Omni=✓2026.04 | 39.2 | 72.2 | 33.7 | 31.9 | 11.6 | 37.7 | 69.3 | |
| Qwen3VLParam./B=235/22, Omni=×2026.04 | 38.1 | 58.6 | 33 | 29.1 | 6 | 33 | 62 | |
| Qwen3VLParam./B=32, Omni=×2026.04 | 37.1 | 57.1 | 31.3 | 28.7 | 7.2 | 32.3 | 52.5 | |
| Qwen3VL-TParam./B=235/22, Omni=×, Thinking mode=true2026.04 | 35.7 | 57.6 | 27.4 | 23.9 | 6.5 | 30.2 | 54.8 | |
| TimeChat-CaptionerParam./B=8, Omni=✓, Segment-wise processing=true2026.04 | 31.2 | 36.8 | 36.2 | 31.8 | 25.4 | 32.3 | 64 | |
| Qwen3VLParam./B=8, Omni=×2026.04 | 30.4 | 49.6 | 26.9 | 25.3 | 6.6 | 27.7 | 47.6 | |
| Gemini-3-flashOmni=✓2026.04 | 28.8 | 50.3 | 28.2 | 25.5 | 11.2 | 28.8 | 44.3 | |
| MiniCPM-O-4.5Param./B=9, Omni=✓, Segment-wise processing=true2026.04 | 26.7 | 59.1 | 32.3 | 23.4 | 17.7 | 31.8 | 54.7 | |
| Qwen3VL-TParam./B=32, Omni=×, Thinking mode=true2026.04 | 24.4 | 37.5 | 22.1 | 18.9 | 7 | 22 | 34.6 | |
| TimeChat-CaptionerParam./B=8, Omni=✓2026.04 | 6.9 | 6.9 | 6.6 | 9.7 | 8.2 | 7.7 | 16.1 | |
| Qwen3-OmniParam./B=30/3, Omni=✓2026.04 | 4.9 | 3.4 | 5.5 | 7.3 | 4.4 | 5.1 | 12.8 | |
| Qwen3-Omni-TParam./B=30/3, Omni=✓, Thinking mode=true2026.04 | 3.2 | 3.5 | 3.8 | 6.8 | 2.3 | 3.9 | 3 | |
| MiniCPM-O-4.5Param./B=9, Omni=✓2026.04 | 3.1 | 8 | 2.9 | 3.2 | 2.4 | 3.9 | 3.2 |