Video Generation on VBench (7 Key Perceptual Metrics)
99.01Background ConsistencyTTOM
Evaluation results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| TTOMBase Model=Wan2.1-14B2025.10 | 99.01 | 95.77 | 99.52 | 98.95 | 66.02 | 66.19 | 68.37 | |
| Wan2.1-14BBase Model=Wan2.1-14B2025.10 | 98.09 | 97.52 | 99.46 | 98.3 | 65.46 | 66.07 | 69.43 | |
| TTOMBase Model=CogVideoX-5B2025.10 | 97.73 | 96.82 | 98.6 | 98.55 | 54.26 | 62.73 | 65.27 | |
| LVDBase Model=Wan2.1-14B2025.10 | 97.19 | 95.31 | 99.42 | 98.35 | 54.76 | 64.37 | 56.02 | |
| CogVideoX-5BBase Model=CogVideoX-5B2025.10 | 96.81 | 96.56 | 98.53 | 98.15 | 56.16 | 62.07 | 65.34 | |
| LVDBase Model=CogVideoX-5B2025.10 | 96.02 | 95.32 | 98.23 | 98.3 | 46.72 | 60.08 | 57.82 | |
| BANSABackbone Model=Wan2.1 14B2025.05 | 0.9596 | 0.9302 | 0.9938 | 0.9772 | 0.6277 | 0.6601 | 0.6529 | |
| VanillaBackbone Model=Wan2.1 14B2025.05 | 0.9587 | 0.929 | 0.9931 | 0.9759 | 0.5916 | 0.6572 | 0.6552 | |
| VanillaBackbone Model=IPOC-2B2025.05 | 0.9535 | 0.9273 | 0.9918 | 0.9741 | 0.7527 | 0.6554 | 0.664 | |
| BANSABackbone Model=IPOC-2B2025.05 | 0.9534 | 0.9281 | 0.9921 | 0.9745 | 0.7721 | 0.6561 | 0.6644 | |
| SEVAModality=RGB2026.03 | 0.9301 | — | 0.9349 | — | — | 0.406 | 0.6428 | |
| VoyagerModality=RGBD2026.03 | 0.9281 | — | 0.9455 | — | — | 0.3823 | 0.5932 | |
| DeepVerseModality=RGBD2026.03 | 0.9261 | — | 0.9452 | — | — | 0.3871 | 0.6011 | |
| AetherModality=RGBD2026.03 | 0.9246 | — | 0.9363 | — | — | 0.3902 | 0.6026 | |
| StereoWorldModality=RGB2026.03 | 0.9242 | — | 0.9363 | — | — | 0.4427 | 0.6651 | |
| ViewCrafterModality=RGB2026.03 | 0.9145 | — | 0.9063 | — | — | 0.4031 | 0.619 |