| Model,Backbone,UMT-FVD↓,UMTScore↑,MTScore↑,CHScore↑,GPT4o-MTScore↑ | |
| [Gen-2 (20240610)](https://research.runwayml.com/gen2),DiT,218.99,2.4,0.373,125.25,2.62 | |
| [Pika-2.0 (20240610)](https://www.pika.art/),DiT,223.05,2.317,0.347,75.98,2.48 | |
| [Dream Machine (20240610)](https://lumalabs.ai/dream-machine),DiT,214.91,2.387,0.474,95.97,3.11 | |
| [KeLing (20240610)](https://h5.kwaiying.com/officialWebsite),DiT,202.32,2.517,0.369,74.20,2.74 | |
| [ModelScopeT2V](https://huggingface.co/ali-vilab/text-to-video-ms-1.7b),U-Net,230.74,2.783,0.409,61.01,3.01 | |
| [ZeroScope](https://huggingface.co/cerspense/zeroscope_v2_576w),U-Net,260.61,2.232,0.403,94.67,2.29 | |
| [T2V-Zero](https://github.com/Picsart-AI-Research/Text2Video-Zero),U-Net,250.22,2.559,0.399,18.54,2.62 | |
| [LaVie](https://github.com/Vchitect/LaVie),U-Net,210.39,2.714,0.35,81.32,2.5 | |
| [AnimateDiff-V3](https://github.com/guoyww/AnimateDiff),U-Net,239.31,2.837,0.47,70.36,2.62 | |
| [VideoCrafter2](https://github.com/AILab-CVC/VideoCrafter),U-Net,214.06,2.763,0.437,75.90,2.87 | |
| [MCM-MSLION](https://yhzhai.github.io/mcm/),U-NeT,244.49,2.282,0.422,58.08,3.06 | |
| [MagicTime](https://github.com/PKU-YuanGroup/MagicTime),U-Net,294.72,1.763,0.479,77.98,3.05 | |
| [Latte](https://github.com/Vchitect/Latte),DiT,232.29,2.122,0.366,72.57,2.42 | |
| [OpenSora 1.1](https://github.com/hpcaitech/Open-Sora),DiT,241.09,2.676,0.448,75.94,2.57 | |
| [OpenSora 1.2](https://github.com/hpcaitech/Open-Sora),DiT,210.93,2.681,0.383,51.87,2.5 | |
| [OpenSoraPlan v1.1](https://github.com/PKU-YuanGroup/Open-Sora-Plan),DiT,228.7,2.459,0.331,61.50,2.21 | |
| [OpenSoraPlan v1.2](https://github.com/PKU-YuanGroup/Open-Sora-Plan),DiT,216.9,0.972,0.324,89.76,1.08 | |
| [EasyAnimate-V3](https://github.com/aigc-apps/EasyAnimate),DiT,202.03,2.733,0.352,88.48,2.33 | |
| [CogVideoX-2B](https://github.com/THUDM/CogVideo),DiT,195.52,3.24,0.472,38.64,3.09 |