# Text-to-Video Generation on Inseval (test)

Source: [Text-to-Video Generation on Inseval (test)](<https://www.sota2.com/research/sota/text-to-video-generation-on-inseval-test>)

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

Data updated: 2026-02-26T06:04:23.550Z

Evaluation of Text-to-Video Generation models on the Inseval test set, assessed using detailed attribute-based metrics covering action, color, shape, and texture fidelity.

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) | Inseval (test) |
| Metric | Single Action |
| 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

- [Single Action](<https://www.sota2.com/research/sota/text-to-video-generation-on-inseval-test.md?metric=Single%20Action>): Higher is better; unit: PERCENT.

- [Single Color](<https://www.sota2.com/research/sota/text-to-video-generation-on-inseval-test.md?metric=Single%20Color>): Higher is better; unit: PERCENT.

- [Single Shape](<https://www.sota2.com/research/sota/text-to-video-generation-on-inseval-test.md?metric=Single%20Shape>): Higher is better; unit: PERCENT.

- [Single Texture](<https://www.sota2.com/research/sota/text-to-video-generation-on-inseval-test.md?metric=Single%20Texture>): Higher is better; unit: PERCENT.

- [Single Detail](<https://www.sota2.com/research/sota/text-to-video-generation-on-inseval-test.md?metric=Single%20Detail>): Higher is better; unit: PERCENT.

- [Multiple Action](<https://www.sota2.com/research/sota/text-to-video-generation-on-inseval-test.md?metric=Multiple%20Action>): Higher is better; unit: PERCENT.

- [Multiple Color](<https://www.sota2.com/research/sota/text-to-video-generation-on-inseval-test.md?metric=Multiple%20Color>): Higher is better; unit: PERCENT.

- [Multiple Texture](<https://www.sota2.com/research/sota/text-to-video-generation-on-inseval-test.md?metric=Multiple%20Texture>): Higher is better; unit: PERCENT.

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

## Recorded results

| Method | Single Action | Result date | Report paper |
| --- | --- | --- | --- |
| CogVideoX-5B | 0.64 | Not recorded | 68fa76251e209131cea6b7ba |
| Open-Sora Plan v1.3-2.7B | 0.64 | Not recorded | 68fa76251e209131cea6b7ba |
| InstanceCap | 0.56 | Not recorded | 68fa76251e209131cea6b7ba |
| LLaVA | 0.52 | Not recorded | 68fa76251e209131cea6b7ba |
| Pyramid-Flow-2B | 0.44 | Not recorded | 68fa76251e209131cea6b7ba |
| Open-Sora v1.2-1.1B | 0.4 | Not recorded | 68fa76251e209131cea6b7ba |
| Panda-captioner | 0.4 | Not recorded | 68fa76251e209131cea6b7ba |
| ShareGPT4Video | 0.4 | Not recorded | 68fa76251e209131cea6b7ba |

### CogVideoX-5B

Single Action: 0.64. Result ID: 6994117d3a6c3148491ad229.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76251e209131cea6b7ba.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77a01e209131cea74741.md>)

Recorded evaluation configuration: {"Base T2V Model":"CogVideoX-5B"}. This record does not assert independent reproduction.

### Open-Sora Plan v1.3-2.7B

Single Action: 0.64. Result ID: 6994117d3a6c3148491ad22b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76251e209131cea6b7ba.md>)

Recorded evaluation configuration: {"Base T2V Model":"Open-Sora Plan v1.3-2.7B"}. This record does not assert independent reproduction.

### InstanceCap

Single Action: 0.56. Result ID: 6994117d3a6c3148491ad22d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76251e209131cea6b7ba.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76251e209131cea6b7ba.md>)

[Implementation](<https://github.com/NJU-PCALab/InstanceCap>)

Recorded evaluation configuration: {"Base T2V Model":"Open-Sora v1.2-1.1B","Captioning Method":"InstanceCap"}. This record does not assert independent reproduction.

### LLaVA

Single Action: 0.52. Result ID: 6994117d3a6c3148491ad230.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76251e209131cea6b7ba.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76f41e209131cea703bc.md>)

Recorded evaluation configuration: {"Base T2V Model":"Open-Sora v1.2-1.1B","Captioning Method":"LLaVA"}. This record does not assert independent reproduction.

### Pyramid-Flow-2B

Single Action: 0.44. Result ID: 6994117d3a6c3148491ad22a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76251e209131cea6b7ba.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa777b1e209131cea737d3.md>)

Recorded evaluation configuration: {"Base T2V Model":"Pyramid-Flow-2B"}. This record does not assert independent reproduction.

### Open-Sora v1.2-1.1B

Single Action: 0.4. Result ID: 6994117d3a6c3148491ad22c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76251e209131cea6b7ba.md>)

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

Recorded evaluation configuration: {"Base T2V Model":"Open-Sora v1.2-1.1B"}. This record does not assert independent reproduction.

### Panda-captioner

Single Action: 0.4. Result ID: 6994117d3a6c3148491ad22e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76251e209131cea6b7ba.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72581e209131cea55cc0.md>)

Recorded evaluation configuration: {"Base T2V Model":"Open-Sora v1.2-1.1B","Captioning Method":"Panda-captioner"}. This record does not assert independent reproduction.

### ShareGPT4Video

Single Action: 0.4. Result ID: 6994117d3a6c3148491ad22f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76251e209131cea6b7ba.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa738e1e209131cea5d310.md>)

[Implementation](<https://sharegpt4video.github.io/>)

Recorded evaluation configuration: {"Base T2V Model":"Open-Sora v1.2-1.1B","Captioning Method":"ShareGPT4Video"}. This record does not assert independent reproduction.

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