# Text-to-motion generation on HumanML3D 1 (test)

Source: [Text-to-motion generation on HumanML3D 1 (test)](<https://www.sota2.com/research/sota/text-to-motion-generation-on-humanml3d-1-test>)

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

Data updated: 2026-02-26T05:59:14.434Z

Evaluation of models generating human motion sequences conditioned on text prompts using the HumanML3D 1 test set. Key metrics include R-Precision variants, FID, MM-Dist, and Diversity 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-motion generation |
| Dataset (including any stated split) | HumanML3D 1 (test) |
| Metric | R-Precision (Top 1) |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 32 of 32 |
| 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-to-motion-generation-on-humanml3d-1-test.md?metric=R-Precision%20(Top%201)>): Higher is better; unit: SCALAR.

- [R-Precision (Top 2)](<https://www.sota2.com/research/sota/text-to-motion-generation-on-humanml3d-1-test.md?metric=R-Precision%20(Top%202)>): Higher is better; unit: SCALAR.

- [R-Precision (Top 3)](<https://www.sota2.com/research/sota/text-to-motion-generation-on-humanml3d-1-test.md?metric=R-Precision%20(Top%203)>): Higher is better; unit: SCALAR.

- [FID](<https://www.sota2.com/research/sota/text-to-motion-generation-on-humanml3d-1-test.md?metric=FID>): Lower is better; unit: SCALAR.

- [MM-Dist](<https://www.sota2.com/research/sota/text-to-motion-generation-on-humanml3d-1-test.md?metric=MM-Dist>): Lower is better; unit: SCALAR.

- [Diversity](<https://www.sota2.com/research/sota/text-to-motion-generation-on-humanml3d-1-test.md?metric=Diversity>): Higher is better; unit: SCALAR.

- [Multi-Modality Score](<https://www.sota2.com/research/sota/text-to-motion-generation-on-humanml3d-1-test.md?metric=Multi-Modality%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | R-Precision (Top 1) | Result date | Report paper |
| --- | --- | --- | --- |
| TCA-T2M | 0.517 | Not recorded | 699bdedf09c33900fcd8035c |
| MG-MotionLLM | 0.516 | Not recorded | 699bdedf09c33900fcd8035c |
| PGR2M Recons. | 0.514 | Not recorded | 69535c8353fdd5c36173d923 |
| Real Motion | 0.511 | Not recorded | 69535c8353fdd5c36173d923 |
| Real | 0.511 | Not recorded | 699bdedf09c33900fcd8035c |
| Light-T2M | 0.511 | Not recorded | 699bdedf09c33900fcd8035c |
| GenM3 | 0.511 | Not recorded | 699bdedf09c33900fcd8035c |
| CoMo Recons. | 0.508 | Not recorded | 69535c8353fdd5c36173d923 |
| Momask | 0.508 | Not recorded | 699bdedf09c33900fcd8035c |
| GraphMotion | 0.504 | Not recorded | 69535c8353fdd5c36173d923 |
| FineMoGen | 0.504 | Not recorded | 69535c8353fdd5c36173d923 |
| MMM | 0.504 | Not recorded | 699bdedf09c33900fcd8035c |
| CoMo | 0.502 | Not recorded | 69535c8353fdd5c36173d923 |
| MotionLCM | 0.502 | Not recorded | 699bdedf09c33900fcd8035c |
| Mo.Mamba | 0.502 | Not recorded | 699bdedf09c33900fcd8035c |
| CoMo | 0.502 | Not recorded | 699bdedf09c33900fcd8035c |
| MotionGPT | 0.492 | Not recorded | 69535c8353fdd5c36173d923 |
| T2M-GPT | 0.492 | Not recorded | 699bdedf09c33900fcd8035c |
| MotionGPT | 0.492 | Not recorded | 699bdedf09c33900fcd8035c |
| T2M-GPT | 0.491 | Not recorded | 69535c8353fdd5c36173d923 |
| Mo.Diffuse | 0.491 | Not recorded | 699bdedf09c33900fcd8035c |
| PGR2M (Base) | 0.489 | Not recorded | 69535c8353fdd5c36173d923 |
| PGR2M | 0.488 | Not recorded | 69535c8353fdd5c36173d923 |
| MLD | 0.481 | Not recorded | 69535c8353fdd5c36173d923 |
| MLD | 0.481 | Not recorded | 699bdedf09c33900fcd8035c |
| Guo et al. | 0.457 | Not recorded | 69535c8353fdd5c36173d923 |
| T2M | 0.455 | Not recorded | 699bdedf09c33900fcd8035c |
| TM2T | 0.424 | Not recorded | 69535c8353fdd5c36173d923 |
| TM2T | 0.424 | Not recorded | 699bdedf09c33900fcd8035c |
| MotionGPT | 0.364 | Not recorded | 699bdedf09c33900fcd8035c |
| MDM | 0.32 | Not recorded | 69535c8353fdd5c36173d923 |
| MDM | 0.32 | Not recorded | 699bdedf09c33900fcd8035c |

### TCA-T2M

R-Precision (Top 1): 0.517. Result ID: 699ce0145698665ec480d103.

[Reporting paper](<https://www.sota2.com/research/paper/699bdedf09c33900fcd8035c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/699bdedf09c33900fcd8035c.md>)

Recorded evaluation configuration: {"Year":"2025"}. This record does not assert independent reproduction.

### MG-MotionLLM

R-Precision (Top 1): 0.516. Result ID: 699ce0145698665ec480d101.

[Reporting paper](<https://www.sota2.com/research/paper/699bdedf09c33900fcd8035c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77cc1e209131cea7567e.md>)

Recorded evaluation configuration: {"Year":"2025"}. This record does not assert independent reproduction.

### PGR2M Recons.

R-Precision (Top 1): 0.514. Result ID: 699807c25698665ec4614af6.

[Reporting paper](<https://www.sota2.com/research/paper/69535c8353fdd5c36173d923.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69535c8353fdd5c36173d923.md>)

Recorded evaluation configuration: {"Editable":"Yes"}. This record does not assert independent reproduction.

### Real Motion

R-Precision (Top 1): 0.511. Result ID: 699807c25698665ec4614af4.

[Reporting paper](<https://www.sota2.com/research/paper/69535c8353fdd5c36173d923.md>)

Recorded evaluation configuration: {"Editable":"-"}. This record does not assert independent reproduction.

### Real

R-Precision (Top 1): 0.511. Result ID: 699ce0145698665ec480d0f2.

[Reporting paper](<https://www.sota2.com/research/paper/699bdedf09c33900fcd8035c.md>)

Recorded evaluation configuration: {"Year":"–"}. This record does not assert independent reproduction.

### Light-T2M

R-Precision (Top 1): 0.511. Result ID: 699ce0145698665ec480d100.

[Reporting paper](<https://www.sota2.com/research/paper/699bdedf09c33900fcd8035c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa763c1e209131cea6c04c.md>)

Recorded evaluation configuration: {"Year":"2025"}. This record does not assert independent reproduction.

### GenM3

R-Precision (Top 1): 0.511. Result ID: 699ce0145698665ec480d102.

[Reporting paper](<https://www.sota2.com/research/paper/699bdedf09c33900fcd8035c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a441e209131cea820d5.md>)

Recorded evaluation configuration: {"Year":"2025"}. This record does not assert independent reproduction.

### CoMo Recons.

R-Precision (Top 1): 0.508. Result ID: 699807c25698665ec4614af5.

[Reporting paper](<https://www.sota2.com/research/paper/69535c8353fdd5c36173d923.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74d91e209131cea64207.md>)

Recorded evaluation configuration: {"Editable":"Yes"}. This record does not assert independent reproduction.

### Momask

R-Precision (Top 1): 0.508. Result ID: 699ce0145698665ec480d0fc.

[Reporting paper](<https://www.sota2.com/research/paper/699bdedf09c33900fcd8035c.md>)

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

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

Recorded evaluation configuration: {"Year":"2024","reproduced":true}. This record does not assert independent reproduction.

### GraphMotion

R-Precision (Top 1): 0.504. Result ID: 699807c25698665ec4614afc.

[Reporting paper](<https://www.sota2.com/research/paper/69535c8353fdd5c36173d923.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71141e209131cea4f27a.md>)

[Implementation](<https://github.com/jpthu17/GraphMotion>)

Recorded evaluation configuration: {"Editable":"No"}. This record does not assert independent reproduction.

### FineMoGen

R-Precision (Top 1): 0.504. Result ID: 699807c25698665ec4614afe.

[Reporting paper](<https://www.sota2.com/research/paper/69535c8353fdd5c36173d923.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71ac1e209131cea527a6.md>)

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

Recorded evaluation configuration: {"Editable":"Yes"}. This record does not assert independent reproduction.

### MMM

R-Precision (Top 1): 0.504. Result ID: 699ce0145698665ec480d0fb.

[Reporting paper](<https://www.sota2.com/research/paper/699bdedf09c33900fcd8035c.md>)

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

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

Recorded evaluation configuration: {"Year":"2024"}. This record does not assert independent reproduction.

### CoMo

R-Precision (Top 1): 0.502. Result ID: 699807c25698665ec4614aff.

[Reporting paper](<https://www.sota2.com/research/paper/69535c8353fdd5c36173d923.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74d91e209131cea64207.md>)

Recorded evaluation configuration: {"Editable":"Yes"}. This record does not assert independent reproduction.

### MotionLCM

R-Precision (Top 1): 0.502. Result ID: 699ce0145698665ec480d0fd.

[Reporting paper](<https://www.sota2.com/research/paper/699bdedf09c33900fcd8035c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76731e209131cea6d0f5.md>)

[Implementation](<https://dai-wenxun.github.io/MotionLCM-page>)

Recorded evaluation configuration: {"Year":"2024"}. This record does not assert independent reproduction.

### Mo.Mamba

R-Precision (Top 1): 0.502. Result ID: 699ce0145698665ec480d0fe.

[Reporting paper](<https://www.sota2.com/research/paper/699bdedf09c33900fcd8035c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74651e209131cea61753.md>)

[Implementation](<https://steve-zeyu-zhang.github.io/MotionMamba>)

Recorded evaluation configuration: {"Year":"2024"}. This record does not assert independent reproduction.

### CoMo

R-Precision (Top 1): 0.502. Result ID: 699ce0145698665ec480d0ff.

[Reporting paper](<https://www.sota2.com/research/paper/699bdedf09c33900fcd8035c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74d91e209131cea64207.md>)

Recorded evaluation configuration: {"Year":"2024"}. This record does not assert independent reproduction.

### MotionGPT

R-Precision (Top 1): 0.492. Result ID: 699807c25698665ec4614afb.

[Reporting paper](<https://www.sota2.com/research/paper/69535c8353fdd5c36173d923.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70201e209131cea493fc.md>)

[Implementation](<https://github.com/OpenMotionLab/MotionGPT>)

Recorded evaluation configuration: {"Editable":"No"}. This record does not assert independent reproduction.

### T2M-GPT

R-Precision (Top 1): 0.492. Result ID: 699ce0145698665ec480d0f3.

[Reporting paper](<https://www.sota2.com/research/paper/699bdedf09c33900fcd8035c.md>)

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

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

Recorded evaluation configuration: {"Year":"2023"}. This record does not assert independent reproduction.

### MotionGPT

R-Precision (Top 1): 0.492. Result ID: 699ce0145698665ec480d0f4.

[Reporting paper](<https://www.sota2.com/research/paper/699bdedf09c33900fcd8035c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70201e209131cea493fc.md>)

[Implementation](<https://github.com/OpenMotionLab/MotionGPT>)

Recorded evaluation configuration: {"Year":"2023","Reference":"\[45\]"}. This record does not assert independent reproduction.

### T2M-GPT

R-Precision (Top 1): 0.491. Result ID: 699807c25698665ec4614afa.

[Reporting paper](<https://www.sota2.com/research/paper/69535c8353fdd5c36173d923.md>)

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

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

Recorded evaluation configuration: {"Editable":"No"}. This record does not assert independent reproduction.

### Mo.Diffuse

R-Precision (Top 1): 0.491. Result ID: 699ce0145698665ec480d0fa.

[Reporting paper](<https://www.sota2.com/research/paper/699bdedf09c33900fcd8035c.md>)

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

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

Recorded evaluation configuration: {"Year":"2024"}. This record does not assert independent reproduction.

### PGR2M (Base)

R-Precision (Top 1): 0.489. Result ID: 699807c25698665ec4614b00.

[Reporting paper](<https://www.sota2.com/research/paper/69535c8353fdd5c36173d923.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69535c8353fdd5c36173d923.md>)

Recorded evaluation configuration: {"Editable":"Yes","Transformer":"Base Only"}. This record does not assert independent reproduction.

### PGR2M

R-Precision (Top 1): 0.488. Result ID: 699807c25698665ec4614b01.

[Reporting paper](<https://www.sota2.com/research/paper/69535c8353fdd5c36173d923.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69535c8353fdd5c36173d923.md>)

Recorded evaluation configuration: {"Editable":"Yes","Transformer":"Base and Refine"}. This record does not assert independent reproduction.

### MLD

R-Precision (Top 1): 0.481. Result ID: 699807c25698665ec4614af9.

[Reporting paper](<https://www.sota2.com/research/paper/69535c8353fdd5c36173d923.md>)

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

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

Recorded evaluation configuration: {"Editable":"No"}. This record does not assert independent reproduction.

### MLD

R-Precision (Top 1): 0.481. Result ID: 699ce0145698665ec480d0f9.

[Reporting paper](<https://www.sota2.com/research/paper/699bdedf09c33900fcd8035c.md>)

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

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

Recorded evaluation configuration: {"Year":"2023"}. This record does not assert independent reproduction.

### Guo et al.

R-Precision (Top 1): 0.457. Result ID: 699807c25698665ec4614af7.

[Reporting paper](<https://www.sota2.com/research/paper/69535c8353fdd5c36173d923.md>)

Recorded evaluation configuration: {"Editable":"No"}. This record does not assert independent reproduction.

### T2M

R-Precision (Top 1): 0.455. Result ID: 699ce0145698665ec480d0f7.

[Reporting paper](<https://www.sota2.com/research/paper/699bdedf09c33900fcd8035c.md>)

Recorded evaluation configuration: {"Year":"2022"}. This record does not assert independent reproduction.

### TM2T

R-Precision (Top 1): 0.424. Result ID: 699807c25698665ec4614af8.

[Reporting paper](<https://www.sota2.com/research/paper/69535c8353fdd5c36173d923.md>)

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

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

Recorded evaluation configuration: {"Editable":"No"}. This record does not assert independent reproduction.

### TM2T

R-Precision (Top 1): 0.424. Result ID: 699ce0145698665ec480d0f6.

[Reporting paper](<https://www.sota2.com/research/paper/699bdedf09c33900fcd8035c.md>)

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

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

Recorded evaluation configuration: {"Year":"2022"}. This record does not assert independent reproduction.

### MotionGPT

R-Precision (Top 1): 0.364. Result ID: 699ce0145698665ec480d0f5.

[Reporting paper](<https://www.sota2.com/research/paper/699bdedf09c33900fcd8035c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70201e209131cea493fc.md>)

[Implementation](<https://github.com/OpenMotionLab/MotionGPT>)

Recorded evaluation configuration: {"Year":"2024","Reference":"\[46\]"}. This record does not assert independent reproduction.

### MDM

R-Precision (Top 1): 0.32. Result ID: 699807c25698665ec4614afd.

[Reporting paper](<https://www.sota2.com/research/paper/69535c8353fdd5c36173d923.md>)

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

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

Recorded evaluation configuration: {"Editable":"Yes"}. This record does not assert independent reproduction.

### MDM

R-Precision (Top 1): 0.32. Result ID: 699ce0145698665ec480d0f8.

[Reporting paper](<https://www.sota2.com/research/paper/699bdedf09c33900fcd8035c.md>)

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

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

Recorded evaluation configuration: {"Year":"2023"}. This record does not assert independent reproduction.

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