Unknown
musiccaps is a state-of-the-art machine learning benchmark indexed on Codesota. This page tracks published model results, top scores per metric, and the SOTA timeline for musiccaps.
Higher is better
| Rank | Model | Source | Score | Year | Paper |
|---|---|---|---|---|---|
| 1 | MusicGen-Medium MusicGen-Medium (Copet et al., Meta AI, NeurIPS 2023). FAD on MusicCaps. Reproduced result in AudioLDM 2 Table III. | Community | 4.89 | 2023 | Source |
| 2 | AudioLDM 2-MSD AudioLDM 2-MSD (MagnaTagATune/Million Song Dataset variant). FAD on MusicCaps. Table III in paper. | Community | 4.47 | 2024 | Source |
| 3 | MusicLM MusicLM (Agostinelli et al., Google, 2023). FAD on MusicCaps. Reported in AudioLDM 2 Table III (not reproduced). | Community | 4 | 2023 | Source |
| 4 | AudioLDM-M AudioLDM medium (Liu et al., ICML 2023). FAD on MusicCaps. Reproduced in AudioLDM 2 Table III. | Community | 3.2 | 2023 | Source |
| 5 | AudioLDM 2-Full AudioLDM 2-Full (Liu et al., IEEE/ACM TASLP 2024). Best FAD on MusicCaps evaluation set. Table III in paper. | Community | 3.13 | 2024 | Source |