# Text-conditional Motion Synthesis on HumanML3D 16 (test)

Source: [Text-conditional Motion Synthesis on HumanML3D 16 (test)](<https://www.sota2.com/research/sota/text-conditional-motion-synthesis-on-humanml3d-16-test>)

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

Data updated: 2026-02-26T05:59:14.875Z

Evaluation of models synthesizing human motion sequences conditioned on text prompts using the HumanML3D 16 test set. Key metrics include R-Precision variants (Top-1, 2, 3), FID, MM-Dist, Diversity, and MModality 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-conditional Motion Synthesis |
| Dataset (including any stated split) | HumanML3D 16 (test) |
| Metric | R-Precision Top-1 |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 15 of 15 |
| 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

- [R-Precision Top-1](<https://www.sota2.com/research/sota/text-conditional-motion-synthesis-on-humanml3d-16-test.md?metric=R-Precision%20Top-1>): Higher is better; unit: SCALAR.

- [R-Precision Top-2](<https://www.sota2.com/research/sota/text-conditional-motion-synthesis-on-humanml3d-16-test.md?metric=R-Precision%20Top-2>): Higher is better; unit: SCALAR.

- [R-Precision Top-3](<https://www.sota2.com/research/sota/text-conditional-motion-synthesis-on-humanml3d-16-test.md?metric=R-Precision%20Top-3>): Higher is better; unit: SCALAR.

- [FID](<https://www.sota2.com/research/sota/text-conditional-motion-synthesis-on-humanml3d-16-test.md?metric=FID>): Lower is better; unit: SCALAR.

- [MM-Dist](<https://www.sota2.com/research/sota/text-conditional-motion-synthesis-on-humanml3d-16-test.md?metric=MM-Dist>): Lower is better; unit: SCALAR.

- [Diversity](<https://www.sota2.com/research/sota/text-conditional-motion-synthesis-on-humanml3d-16-test.md?metric=Diversity>): Higher is better; unit: SCALAR.

- [MModality](<https://www.sota2.com/research/sota/text-conditional-motion-synthesis-on-humanml3d-16-test.md?metric=MModality>): Higher is better; unit: SCALAR.

## Recorded results

| Method | R-Precision Top-1 | Result date | Report paper |
| --- | --- | --- | --- |
| BAMM | 0.525 | Not recorded | 68fa72bc1e209131cea58432 |
| BAMM | 0.522 | Not recorded | 68fa72bc1e209131cea58432 |
| MoMask | 0.521 | Not recorded | 68fa72bc1e209131cea58432 |
| MMM | 0.515 | Not recorded | 68fa72bc1e209131cea58432 |
| AttT2M | 0.499 | Not recorded | 68fa72bc1e209131cea58432 |
| M2DM | 0.497 | Not recorded | 68fa72bc1e209131cea58432 |
| Fg-T2M | 0.492 | Not recorded | 68fa72bc1e209131cea58432 |
| Motion Diffuse | 0.491 | Not recorded | 68fa72bc1e209131cea58432 |
| T2M-GPT | 0.491 | Not recorded | 68fa72bc1e209131cea58432 |
| MLD | 0.481 | Not recorded | 68fa72bc1e209131cea58432 |
| T2M | 0.455 | Not recorded | 68fa72bc1e209131cea58432 |
| TEMOS | 0.424 | Not recorded | 68fa72bc1e209131cea58432 |
| TM2T | 0.424 | Not recorded | 68fa72bc1e209131cea58432 |
| MDM | 0.32 | Not recorded | 68fa72bc1e209131cea58432 |
| Hier | 0.301 | Not recorded | 68fa72bc1e209131cea58432 |

### BAMM

R-Precision Top-1: 0.525. Result ID: 69928ebc3a6c3148490fc57c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72bc1e209131cea58432.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72bc1e209131cea58432.md>)

[Implementation](<https://exitudio.github.io/BAMM-page>)

Recorded evaluation configuration: {"Ground-truth motion length":false}. This record does not assert independent reproduction.

### BAMM

R-Precision Top-1: 0.522. Result ID: 69928ebc3a6c3148490fc57d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72bc1e209131cea58432.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72bc1e209131cea58432.md>)

[Implementation](<https://exitudio.github.io/BAMM-page>)

Recorded evaluation configuration: {"Ground-truth motion length":true}. This record does not assert independent reproduction.

### MoMask

R-Precision Top-1: 0.521. Result ID: 69928ebc3a6c3148490fc57b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72bc1e209131cea58432.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa715d1e209131cea50e45.md>)

[Implementation](<https://ericguo5513.github.io/momask/>)

Recorded evaluation configuration: {"Ground-truth motion length":false}. This record does not assert independent reproduction.

### MMM

R-Precision Top-1: 0.515. Result ID: 69928ebc3a6c3148490fc57a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72bc1e209131cea58432.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72ac1e209131cea57c37.md>)

[Implementation](<https://exitudio.github.io/MMM-page>)

Recorded evaluation configuration: {"Ground-truth motion length":true}. This record does not assert independent reproduction.

### AttT2M

R-Precision Top-1: 0.499. Result ID: 69928ebc3a6c3148490fc579.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72bc1e209131cea58432.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa707f1e209131cea4b7fa.md>)

[Implementation](<https://github.com/ZcyMonkey/AttT2M>)

Recorded evaluation configuration: {"Ground-truth motion length":false}. This record does not assert independent reproduction.

### M2DM

R-Precision Top-1: 0.497. Result ID: 69928ebc3a6c3148490fc577.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72bc1e209131cea58432.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70701e209131cea4af95.md>)

Recorded evaluation configuration: {"Ground-truth motion length":true}. This record does not assert independent reproduction.

### Fg-T2M

R-Precision Top-1: 0.492. Result ID: 69928ebc3a6c3148490fc576.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72bc1e209131cea58432.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa708c1e209131cea4baa8.md>)

Recorded evaluation configuration: {"Ground-truth motion length":false}. This record does not assert independent reproduction.

### Motion Diffuse

R-Precision Top-1: 0.491. Result ID: 69928ebc3a6c3148490fc575.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72bc1e209131cea58432.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d571e209131cea3944b.md>)

[Implementation](<https://mingyuan-zhang.github.io/projects/MotionDiffuse.html>)

Recorded evaluation configuration: {"Ground-truth motion length":false}. This record does not assert independent reproduction.

### T2M-GPT

R-Precision Top-1: 0.491. Result ID: 69928ebc3a6c3148490fc578.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72bc1e209131cea58432.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70b31e209131cea4ca96.md>)

[Implementation](<https://mael-zys.github.io/T2M-GPT/>)

Recorded evaluation configuration: {"Ground-truth motion length":false}. This record does not assert independent reproduction.

### MLD

R-Precision Top-1: 0.481. Result ID: 69928ebc3a6c3148490fc574.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72bc1e209131cea58432.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f6f1e209131cea458d9.md>)

[Implementation](<https://github.com/chenfengye/motion-latent-diffusion>)

Recorded evaluation configuration: {"Ground-truth motion length":true}. This record does not assert independent reproduction.

### T2M

R-Precision Top-1: 0.455. Result ID: 69928ebc3a6c3148490fc572.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72bc1e209131cea58432.md>)

Recorded evaluation configuration: {"Ground-truth motion length":false}. This record does not assert independent reproduction.

### TEMOS

R-Precision Top-1: 0.424. Result ID: 69928ebc3a6c3148490fc570.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72bc1e209131cea58432.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d111e209131cea376cf.md>)

[Implementation](<https://mathis.petrovich.fr/temos/>)

Recorded evaluation configuration: {"Ground-truth motion length":true}. This record does not assert independent reproduction.

### TM2T

R-Precision Top-1: 0.424. Result ID: 69928ebc3a6c3148490fc571.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72bc1e209131cea58432.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d341e209131cea38620.md>)

[Implementation](<https://ericguo5513.github.io/TM2T/>)

Recorded evaluation configuration: {"Ground-truth motion length":false}. This record does not assert independent reproduction.

### MDM

R-Precision Top-1: 0.32. Result ID: 69928ebc3a6c3148490fc573.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72bc1e209131cea58432.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d8f1e209131cea3a994.md>)

[Implementation](<https://github.com/GuyTevet/motion-diffusion-model>)

Recorded evaluation configuration: {"Ground-truth motion length":true}. This record does not assert independent reproduction.

### Hier

R-Precision Top-1: 0.301. Result ID: 69928ebc3a6c3148490fc56f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72bc1e209131cea58432.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e671e209131cea3fbf5.md>)

Recorded evaluation configuration: {"Ground-truth motion length":false}. This record does not assert independent reproduction.

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