Text-to-Audio Retrieval on MusicBench
34.52Recall@1FIGMA
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| FIGMA2026.06 | 34.52 | 65.99 | 81.73 | 91.37 | |
| CLAMP 32026.06 | 28.43 | 57.87 | 74.62 | 89.85 | |
| LAION-CLAPTraining Data=Music2026.06 | 25.38 | 55.84 | 68.53 | 79.7 | |
| M2D-CLAP2026.06 | 25.38 | 55.33 | 70.05 | 78.17 | |
| LAION-CLAPTraining Data=General Audio2026.06 | 23.86 | 48.73 | 62.94 | 77.16 | |
| MuQ-MuLaN2026.06 | 20.81 | 47.71 | 62.94 | 74.62 | |
| MS-CLAP 20232026.06 | 20.3 | 44.67 | 57.87 | 70.05 | |
| LAION-CLAPTraining Data=General audio, Feature=variable-length2026.06 | 19.8 | 44.67 | 57.87 | 73.1 | |
| LAION-CLAPTraining Data=Music, Speech and General Audio2026.06 | 19.8 | 54.82 | 65.99 | 77.16 | |
| LAION-CLAPTraining Data=Music and Speech2026.06 | 19.29 | 46.19 | 64.47 | 77.66 | |
| LAION-CLAPTraining=Continued Training on FGMCaps2026.06 | 10.66 | 36.55 | 48.73 | 68.53 | |
| MS-CLAP 20222026.06 | 6.09 | 17.26 | 27.41 | 41.62 |