# Motion-conditioned Audio-Video Generation on Audio-Video Generation Evaluation Set

Source: [Motion-conditioned Audio-Video Generation on Audio-Video Generation Evaluation Set](<https://www.sota2.com/research/sota/motion-conditioned-audio-video-generation-on-audio-video-generation-evaluation-set>)

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

Data updated: 2026-04-13T08:39:56.715Z

Evaluation of models generating synchronized audio and video content, conditioned on motion, using a comprehensive set of metrics covering perceptual quality, temporal consistency, and alignment scores (e.g., FVD, CLIP-T, AS).

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 | Motion-conditioned Audio-Video Generation |
| Dataset (including any stated split) | Audio-Video Generation Evaluation Set |
| Metric | AS |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [AS](<https://www.sota2.com/research/sota/motion-conditioned-audio-video-generation-on-audio-video-generation-evaluation-set.md?metric=AS>): Higher is better; unit: SCALAR.

- [FVD](<https://www.sota2.com/research/sota/motion-conditioned-audio-video-generation-on-audio-video-generation-evaluation-set.md?metric=FVD>): Lower is better; unit: SCALAR.

- [CE](<https://www.sota2.com/research/sota/motion-conditioned-audio-video-generation-on-audio-video-generation-evaluation-set.md?metric=CE>): Higher is better; unit: SCALAR.

- [CU](<https://www.sota2.com/research/sota/motion-conditioned-audio-video-generation-on-audio-video-generation-evaluation-set.md?metric=CU>): Higher is better; unit: SCALAR.

- [PC](<https://www.sota2.com/research/sota/motion-conditioned-audio-video-generation-on-audio-video-generation-evaluation-set.md?metric=PC>): Higher is better; unit: SCALAR.

- [PQ](<https://www.sota2.com/research/sota/motion-conditioned-audio-video-generation-on-audio-video-generation-evaluation-set.md?metric=PQ>): Higher is better; unit: SCALAR.

- [CLAP Score](<https://www.sota2.com/research/sota/motion-conditioned-audio-video-generation-on-audio-video-generation-evaluation-set.md?metric=CLAP%20Score>): Higher is better; unit: SCALAR.

- [CLIP-T](<https://www.sota2.com/research/sota/motion-conditioned-audio-video-generation-on-audio-video-generation-evaluation-set.md?metric=CLIP-T>): Higher is better; unit: SCALAR.

- [FGAS](<https://www.sota2.com/research/sota/motion-conditioned-audio-video-generation-on-audio-video-generation-evaluation-set.md?metric=FGAS>): Higher is better; unit: SCALAR.

- [ETE](<https://www.sota2.com/research/sota/motion-conditioned-audio-video-generation-on-audio-video-generation-evaluation-set.md?metric=ETE>): Higher is better; unit: SCALAR.

- [MAIC](<https://www.sota2.com/research/sota/motion-conditioned-audio-video-generation-on-audio-video-generation-evaluation-set.md?metric=MAIC>): Higher is better; unit: SCALAR.

- [TE](<https://www.sota2.com/research/sota/motion-conditioned-audio-video-generation-on-audio-video-generation-evaluation-set.md?metric=TE>): Higher is better; unit: SCALAR.

## Recorded results

| Method | AS | Result date | Report paper |
| --- | --- | --- | --- |
| MOVA | 4.63 | Not recorded | 69dc78647d0172140ec78940 |
| Tora3 | 4.61 | Not recorded | 69dc78647d0172140ec78940 |
| AVControl | 4.52 | Not recorded | 69dc78647d0172140ec78940 |
| Ovi | 4.4 | Not recorded | 69dc78647d0172140ec78940 |
| LTX-2 | 4.31 | Not recorded | 69dc78647d0172140ec78940 |

### MOVA

AS: 4.63. Result ID: 69dcabb347f34ce924c3a833.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78647d0172140ec78940.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698abc3bc97a0b3e3b5de514.md>)

[Implementation](<https://github.com/OpenMOSS/MOVA>)

Recorded evaluation configuration: {"# Params":"30.00B"}. This record does not assert independent reproduction.

### Tora3

AS: 4.61. Result ID: 69dcabb347f34ce924c3a835.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78647d0172140ec78940.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69dc78647d0172140ec78940.md>)

Recorded evaluation configuration: {"# Params":"12.25B"}. This record does not assert independent reproduction.

### AVControl

AS: 4.52. Result ID: 69dcabb347f34ce924c3a834.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78647d0172140ec78940.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c60ee20636e5bf4afc835c.md>)

Recorded evaluation configuration: {"# Params":"22.32B"}. This record does not assert independent reproduction.

### Ovi

AS: 4.4. Result ID: 69dcabb347f34ce924c3a832.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78647d0172140ec78940.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bd21e209131cea8ab7e.md>)

Recorded evaluation configuration: {"# Params":"11.66B"}. This record does not assert independent reproduction.

### LTX-2

AS: 4.31. Result ID: 69dcabb347f34ce924c3a831.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78647d0172140ec78940.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695de86e53fdd5c361743bb8.md>)

[Implementation](<https://github.com/Lightricks/LTX-2>)

Recorded evaluation configuration: {"# Params":"22.16B"}. This record does not assert independent reproduction.

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