| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Audio-to-Text Retrieval | FMACaps Eval | R@113.2 | 19 | |
| Text-to-Audio Retrieval | FMACaps Eval | Recall@113 | 19 | |
| Controllable Music Generation | FMACaps full-control variant (test) | TB68.46 | 9 | |
| Music Generation | FMACaps | FD19.99 | 9 | |
| Text-to-Music Retrieval | FMACaps zero-shot | MRR0.075 | 4 |