# Short Video Generation on VBench-Long 60 seconds Source: [Short Video Generation on VBench-Long 60 seconds]() Collection index: [llms.txt]() Data updated: 2026-03-16T08:49:45.731Z Evaluation of models generating short videos (up to 60 seconds) using the VBench-Long dataset, assessed across perceptual quality, consistency, temporal stability, and overall average performance metrics. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Short Video Generation | | Dataset (including any stated split) | VBench-Long 60 seconds | | Metric | Aesthetic Quality | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 13 of 13 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Aesthetic Quality](): Higher is better; unit: PERCENT. - [Background Consistency](): Higher is better; unit: PERCENT. - [Imaging Quality](): Higher is better; unit: PERCENT. - [Motion Smoothness](): Higher is better; unit: PERCENT. - [Subject Consistency](): Higher is better; unit: PERCENT. - [Temporal Flickering Score](): Higher is better; unit: PERCENT. - [Overall Average](): Higher is better; unit: PERCENT. - [Delta](): Higher is better; unit: SCALAR. ## Recorded results | Method | Aesthetic Quality | Result date | Report paper | | --- | --- | --- | --- | | Deep Forcing | 59.63 | Not recorded | 69b78e9d0636e5bf4afbdcc2 | | MemRoPE | 58.76 | Not recorded | 69b78e9d0636e5bf4afbdcc2 | | ∞-RoPE | 58.52 | Not recorded | 69b78e9d0636e5bf4afbdcc2 | | Rolling Forcing | 58.34 | Not recorded | 69b78e9d0636e5bf4afbdcc2 | | LongLive | 57.93 | Not recorded | 69b78e9d0636e5bf4afbdcc2 | | MemRoPE | 57.77 | Not recorded | 69b78e9d0636e5bf4afbdcc2 | | SkyReels-V2 | 57.64 | Not recorded | 69b78e9d0636e5bf4afbdcc2 | | Deep Forcing | 57.3 | Not recorded | 69b78e9d0636e5bf4afbdcc2 | | CausVid | 57.06 | Not recorded | 69b78e9d0636e5bf4afbdcc2 | | Self-Forcing | 56.96 | Not recorded | 69b78e9d0636e5bf4afbdcc2 | | ∞-RoPE | 54.97 | Not recorded | 69b78e9d0636e5bf4afbdcc2 | | MAGI-1 | 52.1 | Not recorded | 69b78e9d0636e5bf4afbdcc2 | | NOVA | 47.53 | Not recorded | 69b78e9d0636e5bf4afbdcc2 | ### Deep Forcing Aesthetic Quality: 59.63. Result ID: 69b7c41247f34ce9249f7eeb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"LongLive"}. This record does not assert independent reproduction. ### MemRoPE Aesthetic Quality: 58.76. Result ID: 69b7c41247f34ce9249f7eed. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"LongLive"}. This record does not assert independent reproduction. ### ∞-RoPE Aesthetic Quality: 58.52. Result ID: 69b7c41247f34ce9249f7eec. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"LongLive"}. This record does not assert independent reproduction. ### Rolling Forcing Aesthetic Quality: 58.34. Result ID: 69b7c41247f34ce9249f7ee5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### LongLive Aesthetic Quality: 57.93. Result ID: 69b7c41247f34ce9249f7eea. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"LongLive"}. This record does not assert independent reproduction. ### MemRoPE Aesthetic Quality: 57.77. Result ID: 69b7c41247f34ce9249f7ee9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Self-Forcing"}. This record does not assert independent reproduction. ### SkyReels-V2 Aesthetic Quality: 57.64. Result ID: 69b7c41247f34ce9249f7ee3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Deep Forcing Aesthetic Quality: 57.3. Result ID: 69b7c41247f34ce9249f7ee7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Self-Forcing"}. This record does not assert independent reproduction. ### CausVid Aesthetic Quality: 57.06. Result ID: 69b7c41247f34ce9249f7ee4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Self-Forcing Aesthetic Quality: 56.96. Result ID: 69b7c41247f34ce9249f7ee6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Self-Forcing"}. This record does not assert independent reproduction. ### ∞-RoPE Aesthetic Quality: 54.97. Result ID: 69b7c41247f34ce9249f7ee8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Self-Forcing"}. This record does not assert independent reproduction. ### MAGI-1 Aesthetic Quality: 52.1. Result ID: 69b7c41247f34ce9249f7ee2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### NOVA Aesthetic Quality: 47.53. Result ID: 69b7c41247f34ce9249f7ee1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.