# Text-to-Video Generation on VBench (Total Score and Detailed Semantic Metrics)

Source: [Text-to-Video Generation on VBench (Total Score and Detailed Semantic Metrics)](<https://www.sota2.com/research/sota/text-to-video-generation-on-vbench-total-score-and-detailed-semantic-metrics>)

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

Data updated: 2026-05-15T07:21:52.233Z

Evaluation of Text-to-Video Generation models on the VBench dataset, reporting the Total Score alongside detailed metrics covering temporal stability (Temporal Flickering) and semantic fidelity (Human Action, Object Class, Multiple Objects, Spatial Relationship).

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 | Text-to-Video Generation |
| Dataset (including any stated split) | VBench |
| Metric | Total Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 14 of 14 |
| 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

- [Total Score](<https://www.sota2.com/research/sota/text-to-video-generation-on-vbench-total-score-and-detailed-semantic-metrics.md?metric=Total%20Score>): Higher is better; unit: PERCENT.

- [Temporal Flickering](<https://www.sota2.com/research/sota/text-to-video-generation-on-vbench-total-score-and-detailed-semantic-metrics.md?metric=Temporal%20Flickering>): Higher is better; unit: PERCENT.

- [Imaging Quality](<https://www.sota2.com/research/sota/text-to-video-generation-on-vbench-total-score-and-detailed-semantic-metrics.md?metric=Imaging%20Quality>): Higher is better; unit: PERCENT.

- [Human Action](<https://www.sota2.com/research/sota/text-to-video-generation-on-vbench-total-score-and-detailed-semantic-metrics.md?metric=Human%20Action>): Higher is better; unit: PERCENT.

- [Object Class](<https://www.sota2.com/research/sota/text-to-video-generation-on-vbench-total-score-and-detailed-semantic-metrics.md?metric=Object%20Class>): Higher is better; unit: PERCENT.

- [Multiple Objects](<https://www.sota2.com/research/sota/text-to-video-generation-on-vbench-total-score-and-detailed-semantic-metrics.md?metric=Multiple%20Objects>): Higher is better; unit: PERCENT.

- [Spatial Relationship](<https://www.sota2.com/research/sota/text-to-video-generation-on-vbench-total-score-and-detailed-semantic-metrics.md?metric=Spatial%20Relationship>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Total Score | Result date | Report paper |
| --- | --- | --- | --- |
| RAPO++ | 82.65 | Not recorded | 68fc59603ef7ccd74e452523 |
| RAPO | 82.38 | Not recorded | 68fc59603ef7ccd74e452523 |
| LaVie | 80.89 | Not recorded | 68fc59603ef7ccd74e452523 |
| RAPO++ | 80.75 | Not recorded | 68fc59603ef7ccd74e452523 |
| RAPO | 79.97 | Not recorded | 68fc59603ef7ccd74e452523 |
| Prompt Refiner | 79.75 | Not recorded | 68fc59603ef7ccd74e452523 |
| GPT4 | 79.69 | Not recorded | 68fc59603ef7ccd74e452523 |
| PAE | 79.17 | Not recorded | 68fc59603ef7ccd74e452523 |
| Promptist | 79.13 | Not recorded | 68fc59603ef7ccd74e452523 |
| GPT4 | 77.4 | Not recorded | 68fc59603ef7ccd74e452523 |
| Prompt Refiner | 77.23 | Not recorded | 68fc59603ef7ccd74e452523 |
| Latte | 77.03 | Not recorded | 68fc59603ef7ccd74e452523 |
| PAE | 76.83 | Not recorded | 68fc59603ef7ccd74e452523 |
| Promptist | 76.65 | Not recorded | 68fc59603ef7ccd74e452523 |

### RAPO++

Total Score: 82.65. Result ID: 6a06c98947f34ce924edf8ee.

[Reporting paper](<https://www.sota2.com/research/paper/68fc59603ef7ccd74e452523.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fc59603ef7ccd74e452523.md>)

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

### RAPO

Total Score: 82.38. Result ID: 6a06c98947f34ce924edf8ed.

[Reporting paper](<https://www.sota2.com/research/paper/68fc59603ef7ccd74e452523.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fc59603ef7ccd74e452523.md>)

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

### LaVie

Total Score: 80.89. Result ID: 6a06c98947f34ce924edf8e8.

[Reporting paper](<https://www.sota2.com/research/paper/68fc59603ef7ccd74e452523.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70ae1e209131cea4c7e4.md>)

[Implementation](<https://vchitect.github.io/LaVie-project/>)

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

### RAPO++

Total Score: 80.75. Result ID: 6a06c98947f34ce924edf8f5.

[Reporting paper](<https://www.sota2.com/research/paper/68fc59603ef7ccd74e452523.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fc59603ef7ccd74e452523.md>)

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

### RAPO

Total Score: 79.97. Result ID: 6a06c98947f34ce924edf8f4.

[Reporting paper](<https://www.sota2.com/research/paper/68fc59603ef7ccd74e452523.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fc59603ef7ccd74e452523.md>)

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

### Prompt Refiner

Total Score: 79.75. Result ID: 6a06c98947f34ce924edf8ea.

[Reporting paper](<https://www.sota2.com/research/paper/68fc59603ef7ccd74e452523.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76751e209131cea6d260.md>)

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

### GPT4

Total Score: 79.69. Result ID: 6a06c98947f34ce924edf8e9.

[Reporting paper](<https://www.sota2.com/research/paper/68fc59603ef7ccd74e452523.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa727a1e209131cea56a1e.md>)

[Implementation](<https://github.com/openai/evals>)

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

### PAE

Total Score: 79.17. Result ID: 6a06c98947f34ce924edf8ec.

[Reporting paper](<https://www.sota2.com/research/paper/68fc59603ef7ccd74e452523.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72d51e209131cea58cb1.md>)

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

### Promptist

Total Score: 79.13. Result ID: 6a06c98947f34ce924edf8eb.

[Reporting paper](<https://www.sota2.com/research/paper/68fc59603ef7ccd74e452523.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71a41e209131cea523e3.md>)

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

### GPT4

Total Score: 77.4. Result ID: 6a06c98947f34ce924edf8f0.

[Reporting paper](<https://www.sota2.com/research/paper/68fc59603ef7ccd74e452523.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa727a1e209131cea56a1e.md>)

[Implementation](<https://github.com/openai/evals>)

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

### Prompt Refiner

Total Score: 77.23. Result ID: 6a06c98947f34ce924edf8f1.

[Reporting paper](<https://www.sota2.com/research/paper/68fc59603ef7ccd74e452523.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76751e209131cea6d260.md>)

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

### Latte

Total Score: 77.03. Result ID: 6a06c98947f34ce924edf8ef.

[Reporting paper](<https://www.sota2.com/research/paper/68fc59603ef7ccd74e452523.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa785e1e209131cea78093.md>)

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

### PAE

Total Score: 76.83. Result ID: 6a06c98947f34ce924edf8f3.

[Reporting paper](<https://www.sota2.com/research/paper/68fc59603ef7ccd74e452523.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72d51e209131cea58cb1.md>)

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

### Promptist

Total Score: 76.65. Result ID: 6a06c98947f34ce924edf8f2.

[Reporting paper](<https://www.sota2.com/research/paper/68fc59603ef7ccd74e452523.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71a41e209131cea523e3.md>)

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

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