# Text-to-Video Generation on VBench Long latest (leaderboard)

Source: [Text-to-Video Generation on VBench Long latest (leaderboard)](<https://www.sota2.com/research/sota/text-to-video-generation-on-vbench-long-latest-leaderboard>)

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

Data updated: 2026-02-26T06:04:52.411Z

Evaluation of Text-to-Video Generation models using the VBench Long dataset (latest leaderboard configuration), assessed across detailed perceptual and consistency metrics including Subject Consistency, Temporal Flicker, Aesthetic Quality, and various semantic scores.

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 Long latest (leaderboard) |
| Metric | Subject Consistency |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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

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

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

- [Temporal Flicker Score](<https://www.sota2.com/research/sota/text-to-video-generation-on-vbench-long-latest-leaderboard.md?metric=Temporal%20Flicker%20Score>): Higher is better; unit: PERCENT.

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

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

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

- [Dynamics Degree](<https://www.sota2.com/research/sota/text-to-video-generation-on-vbench-long-latest-leaderboard.md?metric=Dynamics%20Degree>): Higher is better; unit: PERCENT.

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

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

- [Object Classification Accuracy](<https://www.sota2.com/research/sota/text-to-video-generation-on-vbench-long-latest-leaderboard.md?metric=Object%20Classification%20Accuracy>): Higher is better; unit: PERCENT.

- [Multiple Objects Consistency](<https://www.sota2.com/research/sota/text-to-video-generation-on-vbench-long-latest-leaderboard.md?metric=Multiple%20Objects%20Consistency>): Higher is better; unit: PERCENT.

- [Human Action Fidelity](<https://www.sota2.com/research/sota/text-to-video-generation-on-vbench-long-latest-leaderboard.md?metric=Human%20Action%20Fidelity>): Higher is better; unit: PERCENT.

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

- [Spatial Relations](<https://www.sota2.com/research/sota/text-to-video-generation-on-vbench-long-latest-leaderboard.md?metric=Spatial%20Relations>): Higher is better; unit: PERCENT.

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

- [Appearance Style Fidelity](<https://www.sota2.com/research/sota/text-to-video-generation-on-vbench-long-latest-leaderboard.md?metric=Appearance%20Style%20Fidelity>): Higher is better; unit: PERCENT.

- [Temporal Style Fidelity](<https://www.sota2.com/research/sota/text-to-video-generation-on-vbench-long-latest-leaderboard.md?metric=Temporal%20Style%20Fidelity>): Higher is better; unit: PERCENT.

- [Overall Consistency Score](<https://www.sota2.com/research/sota/text-to-video-generation-on-vbench-long-latest-leaderboard.md?metric=Overall%20Consistency%20Score>): Higher is better; unit: PERCENT.

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

## Recorded results

| Method | Subject Consistency | Result date | Report paper |
| --- | --- | --- | --- |
| Kling | 98.33 | Not recorded | 68fa78c41e209131cea7a639 |
| LinGen | 98.3 | Not recorded | 68fa78c41e209131cea7a639 |
| Runway Gen-3 | 97.1 | Not recorded | 68fa78c41e209131cea7a639 |
| Mochi-1 | 96.99 | Not recorded | 68fa78c41e209131cea7a639 |
| OpenSora V1.2 | 96.75 | Not recorded | 68fa78c41e209131cea7a639 |
| CogVideoX-5B | 96.23 | Not recorded | 68fa78c41e209131cea7a639 |
| Mira | 96.23 | Not recorded | 68fa78c41e209131cea7a639 |

### Kling

Subject Consistency: 98.33. Result ID: 6995a1943badfaffe69e5713.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78c41e209131cea7a639.md>)

Recorded evaluation configuration: {"Max. Raw Frames":"313"}. This record does not assert independent reproduction.

### LinGen

Subject Consistency: 98.3. Result ID: 6995a1943badfaffe69e5718.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78c41e209131cea7a639.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78c41e209131cea7a639.md>)

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

Recorded evaluation configuration: {"Max. Raw Frames":"1088"}. This record does not assert independent reproduction.

### Runway Gen-3

Subject Consistency: 97.1. Result ID: 6995a1943badfaffe69e5712.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78c41e209131cea7a639.md>)

Recorded evaluation configuration: {"Max. Raw Frames":"256"}. This record does not assert independent reproduction.

### Mochi-1

Subject Consistency: 96.99. Result ID: 6995a1943badfaffe69e5715.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78c41e209131cea7a639.md>)

Recorded evaluation configuration: {"Max. Raw Frames":"163"}. This record does not assert independent reproduction.

### OpenSora V1.2

Subject Consistency: 96.75. Result ID: 6995a1943badfaffe69e5716.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78c41e209131cea7a639.md>)

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

Recorded evaluation configuration: {"Max. Raw Frames":"408"}. This record does not assert independent reproduction.

### CogVideoX-5B

Subject Consistency: 96.23. Result ID: 6995a1943badfaffe69e5714.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78c41e209131cea7a639.md>)

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

Recorded evaluation configuration: {"Max. Raw Frames":"48"}. This record does not assert independent reproduction.

### Mira

Subject Consistency: 96.23. Result ID: 6995a1943badfaffe69e5717.

[Reporting paper](<https://www.sota2.com/research/paper/68fa78c41e209131cea7a639.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74041e209131cea5f415.md>)

[Implementation](<https://github.com/mira-space/MiraData>)

Recorded evaluation configuration: {"Max. Raw Frames":"60"}. This record does not assert independent reproduction.

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