# Controllable Music Generation on FMACaps (full-control variant, test)

Source: [Controllable Music Generation on FMACaps (full-control variant, test)](<https://www.sota2.com/research/sota/controllable-music-generation-on-fmacaps-full-control-variant-test>)

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

Data updated: 2026-02-26T06:05:51.259Z

Evaluation of Controllable Music Generation performance using the specific full-control variant test split of the FMACaps dataset, assessed using metrics like TB, TBT, CK, and PCM.

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 | Controllable Music Generation |
| Dataset (including any stated split) | FMACaps full-control variant (test) |
| Metric | TB |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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

- [TB](<https://www.sota2.com/research/sota/controllable-music-generation-on-fmacaps-full-control-variant-test.md?metric=TB>): Higher is better; unit: PERCENT.

- [TBT](<https://www.sota2.com/research/sota/controllable-music-generation-on-fmacaps-full-control-variant-test.md?metric=TBT>): Higher is better; unit: PERCENT.

- [CK](<https://www.sota2.com/research/sota/controllable-music-generation-on-fmacaps-full-control-variant-test.md?metric=CK>): Higher is better; unit: PERCENT.

- [CKD](<https://www.sota2.com/research/sota/controllable-music-generation-on-fmacaps-full-control-variant-test.md?metric=CKD>): Higher is better; unit: PERCENT.

- [PCM](<https://www.sota2.com/research/sota/controllable-music-generation-on-fmacaps-full-control-variant-test.md?metric=PCM>): Higher is better; unit: PERCENT.

- [ECM](<https://www.sota2.com/research/sota/controllable-music-generation-on-fmacaps-full-control-variant-test.md?metric=ECM>): Higher is better; unit: PERCENT.

- [CMO](<https://www.sota2.com/research/sota/controllable-music-generation-on-fmacaps-full-control-variant-test.md?metric=CMO>): Higher is better; unit: PERCENT.

- [CMOT](<https://www.sota2.com/research/sota/controllable-music-generation-on-fmacaps-full-control-variant-test.md?metric=CMOT>): Higher is better; unit: PERCENT.

- [BM](<https://www.sota2.com/research/sota/controllable-music-generation-on-fmacaps-full-control-variant-test.md?metric=BM>): Higher is better; unit: PERCENT.

## Recorded results

| Method | TB | Result date | Report paper |
| --- | --- | --- | --- |
| Mustango | 68.46 | Not recorded | 68fa805b1e209131cea9cc5d |
| Mustango | 50.56 | Not recorded | 68fa805b1e209131cea9cc5d |
| Tango | 39.31 | Not recorded | 68fa805b1e209131cea9cc5d |
| Tango | 32.21 | Not recorded | 68fa805b1e209131cea9cc5d |
| MusicGen-M | 26.76 | Not recorded | 68fa805b1e209131cea9cc5d |
| MusicGen-S | 21.74 | Not recorded | 68fa805b1e209131cea9cc5d |
| Tango | 13.99 | Not recorded | 68fa805b1e209131cea9cc5d |
| Tango | 11.13 | Not recorded | 68fa805b1e209131cea9cc5d |
| AudioLDM2 | 10.55 | Not recorded | 68fa805b1e209131cea9cc5d |

### Mustango

TB: 68.46. Result ID: 698b95bc7a967eddb76fcc21.

[Reporting paper](<https://www.sota2.com/research/paper/68fa805b1e209131cea9cc5d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa805b1e209131cea9cc5d.md>)

[Implementation](<https://github.com/amaai-lab/mustango>)

Recorded evaluation configuration: {"training\_datasets":"MusicBench","pre-trained":false}. This record does not assert independent reproduction.

### Mustango

TB: 50.56. Result ID: 698b95bc7a967eddb76fcc22.

[Reporting paper](<https://www.sota2.com/research/paper/68fa805b1e209131cea9cc5d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa805b1e209131cea9cc5d.md>)

[Implementation](<https://github.com/amaai-lab/mustango>)

Recorded evaluation configuration: {"training\_datasets":"MusicBench","pre-trained":true}. This record does not assert independent reproduction.

### Tango

TB: 39.31. Result ID: 698b95bc7a967eddb76fcc20.

[Reporting paper](<https://www.sota2.com/research/paper/68fa805b1e209131cea9cc5d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f771e209131cea45c2c.md>)

[Implementation](<https://github.com/declare-lab/tango>)

Recorded evaluation configuration: {"training\_datasets":"MusicBench","pre-trained":true}. This record does not assert independent reproduction.

### Tango

TB: 32.21. Result ID: 698b95bc7a967eddb76fcc1f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa805b1e209131cea9cc5d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f771e209131cea45c2c.md>)

[Implementation](<https://github.com/declare-lab/tango>)

Recorded evaluation configuration: {"training\_datasets":"MusicBench","pre-trained":false}. This record does not assert independent reproduction.

### MusicGen-M

TB: 26.76. Result ID: 698b95bc7a967eddb76fcc1b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa805b1e209131cea9cc5d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72031e209131cea5421d.md>)

[Implementation](<https://www.sota2.com/github.com/facebookresearch/audiocraft>)

Recorded evaluation configuration: {"training\_datasets":"-","pre-trained":false}. This record does not assert independent reproduction.

### MusicGen-S

TB: 21.74. Result ID: 698b95bc7a967eddb76fcc1a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa805b1e209131cea9cc5d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72031e209131cea5421d.md>)

[Implementation](<https://www.sota2.com/github.com/facebookresearch/audiocraft>)

Recorded evaluation configuration: {"training\_datasets":"-","pre-trained":false}. This record does not assert independent reproduction.

### Tango

TB: 13.99. Result ID: 698b95bc7a967eddb76fcc1e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa805b1e209131cea9cc5d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f771e209131cea45c2c.md>)

[Implementation](<https://github.com/declare-lab/tango>)

Recorded evaluation configuration: {"training\_datasets":"MusicCaps","pre-trained":true}. This record does not assert independent reproduction.

### Tango

TB: 11.13. Result ID: 698b95bc7a967eddb76fcc1d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa805b1e209131cea9cc5d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f771e209131cea45c2c.md>)

[Implementation](<https://github.com/declare-lab/tango>)

Recorded evaluation configuration: {"training\_datasets":"MusicCaps","pre-trained":false}. This record does not assert independent reproduction.

### AudioLDM2

TB: 10.55. Result ID: 698b95bc7a967eddb76fcc1c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa805b1e209131cea9cc5d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73261e209131cea5ab21.md>)

[Implementation](<https://audioldm.github.io/audioldm2>)

Recorded evaluation configuration: {"training\_datasets":"-","pre-trained":false}. This record does not assert independent reproduction.

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