# Long Video Generation on VBench Long 120 seconds

Source: [Long Video Generation on VBench Long 120 seconds](<https://www.sota2.com/research/sota/long-video-generation-on-vbench-long-120-seconds>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-16T08:49:45.810Z

Evaluation of Long Video Generation models using the VBench Long 120 seconds dataset, assessed using perceptual quality, consistency metrics, and summary statistics (Average, Delta).

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 | Long Video Generation |
| Dataset (including any stated split) | VBench Long 120 seconds |
| Metric | Aesthetic Quality |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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](<https://www.sota2.com/research/sota/long-video-generation-on-vbench-long-120-seconds.md?metric=Aesthetic%20Quality>): Higher is better; unit: PERCENT.

- [Background Consistency](<https://www.sota2.com/research/sota/long-video-generation-on-vbench-long-120-seconds.md?metric=Background%20Consistency>): Higher is better; unit: PERCENT.

- [Imaging Quality](<https://www.sota2.com/research/sota/long-video-generation-on-vbench-long-120-seconds.md?metric=Imaging%20Quality>): Higher is better; unit: PERCENT.

- [Motion Smoothness](<https://www.sota2.com/research/sota/long-video-generation-on-vbench-long-120-seconds.md?metric=Motion%20Smoothness>): Higher is better; unit: PERCENT.

- [Subject Consistency](<https://www.sota2.com/research/sota/long-video-generation-on-vbench-long-120-seconds.md?metric=Subject%20Consistency>): Higher is better; unit: PERCENT.

- [Temporal Flickering](<https://www.sota2.com/research/sota/long-video-generation-on-vbench-long-120-seconds.md?metric=Temporal%20Flickering>): Higher is better; unit: PERCENT.

- [Average Score](<https://www.sota2.com/research/sota/long-video-generation-on-vbench-long-120-seconds.md?metric=Average%20Score>): Higher is better; unit: PERCENT.

- [Delta](<https://www.sota2.com/research/sota/long-video-generation-on-vbench-long-120-seconds.md?metric=Delta>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Aesthetic Quality | Result date | Report paper |
| --- | --- | --- | --- |
| MemRoPE | 59.25 | Not recorded | 69b78e9d0636e5bf4afbdcc2 |
| Deep Forcing | 59.16 | Not recorded | 69b78e9d0636e5bf4afbdcc2 |
| ∞-RoPE | 57.87 | Not recorded | 69b78e9d0636e5bf4afbdcc2 |
| LongLive | 57.21 | Not recorded | 69b78e9d0636e5bf4afbdcc2 |
| Deep Forcing | 56.86 | Not recorded | 69b78e9d0636e5bf4afbdcc2 |
| MemRoPE | 56.77 | Not recorded | 69b78e9d0636e5bf4afbdcc2 |
| Self-Forcing | 55.11 | Not recorded | 69b78e9d0636e5bf4afbdcc2 |
| ∞-RoPE | 52.82 | Not recorded | 69b78e9d0636e5bf4afbdcc2 |

### MemRoPE

Aesthetic Quality: 59.25. Result ID: 69b7c41247f34ce9249f7efa.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e9d0636e5bf4afbdcc2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b78e9d0636e5bf4afbdcc2.md>)

Recorded evaluation configuration: {"Base Model":"LongLive"}. This record does not assert independent reproduction.

### Deep Forcing

Aesthetic Quality: 59.16. Result ID: 69b7c41247f34ce9249f7ef8.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e9d0636e5bf4afbdcc2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6932675bd6b0dd3342934580.md>)

Recorded evaluation configuration: {"Base Model":"LongLive"}. This record does not assert independent reproduction.

### ∞-RoPE

Aesthetic Quality: 57.87. Result ID: 69b7c41247f34ce9249f7ef9.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e9d0636e5bf4afbdcc2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/692689c7d6b0dd3342930656.md>)

Recorded evaluation configuration: {"Base Model":"LongLive"}. This record does not assert independent reproduction.

### LongLive

Aesthetic Quality: 57.21. Result ID: 69b7c41247f34ce9249f7ef7.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e9d0636e5bf4afbdcc2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c251e209131cea8cb13.md>)

Recorded evaluation configuration: {"Base Model":"LongLive"}. This record does not assert independent reproduction.

### Deep Forcing

Aesthetic Quality: 56.86. Result ID: 69b7c41247f34ce9249f7ef4.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e9d0636e5bf4afbdcc2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6932675bd6b0dd3342934580.md>)

Recorded evaluation configuration: {"Base Model":"Self-Forcing"}. This record does not assert independent reproduction.

### MemRoPE

Aesthetic Quality: 56.77. Result ID: 69b7c41247f34ce9249f7ef6.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e9d0636e5bf4afbdcc2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b78e9d0636e5bf4afbdcc2.md>)

Recorded evaluation configuration: {"Base Model":"Self-Forcing"}. This record does not assert independent reproduction.

### Self-Forcing

Aesthetic Quality: 55.11. Result ID: 69b7c41247f34ce9249f7ef3.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e9d0636e5bf4afbdcc2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa793a1e209131cea7cb5a.md>)

Recorded evaluation configuration: {"Base Model":"Self-Forcing"}. This record does not assert independent reproduction.

### ∞-RoPE

Aesthetic Quality: 52.82. Result ID: 69b7c41247f34ce9249f7ef5.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e9d0636e5bf4afbdcc2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/692689c7d6b0dd3342930656.md>)

Recorded evaluation configuration: {"Base Model":"Self-Forcing"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
