# Multi-track Music Generation (Mixture Subjective Evaluation) on Slakh2100 (test)

Source: [Multi-track Music Generation (Mixture Subjective Evaluation) on Slakh2100 (test)](<https://www.sota2.com/research/sota/multi-track-music-generation-mixture-subjective-evaluation-on-slakh2100-test>)

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

Data updated: 2026-03-04T13:14:05.843Z

Subjective evaluation of multi-track music generation models using human assessors on the test split of the Slakh2100 dataset, reporting scores across different listener groups.

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 | Multi-track Music Generation (Mixture Subjective Evaluation) |
| Dataset (including any stated split) | Slakh2100 (test) |
| Metric | Subjective Score (Group 1) |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [Subjective Score (Group 1)](<https://www.sota2.com/research/sota/multi-track-music-generation-mixture-subjective-evaluation-on-slakh2100-test.md?metric=Subjective%20Score%20(Group%201)>): Higher is better; unit: SCALAR.

- [Subjective Score (Group 2)](<https://www.sota2.com/research/sota/multi-track-music-generation-mixture-subjective-evaluation-on-slakh2100-test.md?metric=Subjective%20Score%20(Group%202)>): Higher is better; unit: SCALAR.

- [Subjective Score (Group 3)](<https://www.sota2.com/research/sota/multi-track-music-generation-mixture-subjective-evaluation-on-slakh2100-test.md?metric=Subjective%20Score%20(Group%203)>): Higher is better; unit: SCALAR.

- [Subjective Score (Group 4)](<https://www.sota2.com/research/sota/multi-track-music-generation-mixture-subjective-evaluation-on-slakh2100-test.md?metric=Subjective%20Score%20(Group%204)>): Higher is better; unit: SCALAR.

- [Average Subjective Score](<https://www.sota2.com/research/sota/multi-track-music-generation-mixture-subjective-evaluation-on-slakh2100-test.md?metric=Average%20Subjective%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Subjective Score (Group 1) | Result date | Report paper |
| --- | --- | --- | --- |
| Ground Truth | 4.2 | Not recorded | 69a66c142d603e6de3e3cdaa |
| SyncTrack | 3.3 | Not recorded | 69a66c142d603e6de3e3cdaa |
| Ground Truth | 2.9 | Not recorded | 69a66c142d603e6de3e3cdaa |
| SyncTrack | 1.9 | Not recorded | 69a66c142d603e6de3e3cdaa |
| MSG-LD | 1.5 | Not recorded | 69a66c142d603e6de3e3cdaa |
| MSG-LD | 1.2 | Not recorded | 69a66c142d603e6de3e3cdaa |

### Ground Truth

Subjective Score (Group 1): 4.2. Result ID: 69a830066dbb7075b94e96bc.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c142d603e6de3e3cdaa.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### SyncTrack

Subjective Score (Group 1): 3.3. Result ID: 69a830066dbb7075b94e96bd.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c142d603e6de3e3cdaa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a66c142d603e6de3e3cdaa.md>)

Recorded evaluation configuration: {"Generation Mode":"Unconditional"}. This record does not assert independent reproduction.

### Ground Truth

Subjective Score (Group 1): 2.9. Result ID: 69a830066dbb7075b94e96c2.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c142d603e6de3e3cdaa.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### SyncTrack

Subjective Score (Group 1): 1.9. Result ID: 69a830066dbb7075b94e96c3.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c142d603e6de3e3cdaa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a66c142d603e6de3e3cdaa.md>)

Recorded evaluation configuration: {"Generation Mode":"Unconditional"}. This record does not assert independent reproduction.

### MSG-LD

Subjective Score (Group 1): 1.5. Result ID: 69a830066dbb7075b94e96be.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c142d603e6de3e3cdaa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76731e209131cea6d141.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### MSG-LD

Subjective Score (Group 1): 1.2. Result ID: 69a830066dbb7075b94e96c4.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c142d603e6de3e3cdaa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76731e209131cea6d141.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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