Audio-to-Text Retrieval on MusicBench
39.09Recall@1FIGMA
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| FIGMA2026.06 | 39.09 | 68.02 | 80.71 | 88.83 | |
| M2D-CLAP2026.06 | 36.55 | 63.96 | 75.63 | 84.77 | |
| LAION-CLAPTraining Data=General Audio2026.06 | 27.92 | 53.81 | 76.65 | 86.8 | |
| LAION-CLAPTraining Data=Music, Speech and General Audio2026.06 | 26.9 | 59.39 | 71.57 | 83.76 | |
| LAION-CLAPTraining Data=Music2026.06 | 25.38 | 61.93 | 76.14 | 89.34 | |
| MS-CLAP 20232026.06 | 23.86 | 55.84 | 70.56 | 83.25 | |
| LAION-CLAPTraining Data=General audio, Feature=variable-length2026.06 | 23.35 | 52.79 | 62.94 | 78.17 | |
| LAION-CLAPTraining Data=Music and Speech2026.06 | 19.8 | 48.22 | 65.48 | 80.2 | |
| MuQ-MuLaN2026.06 | 17.76 | 43.65 | 57.86 | 78.68 | |
| LAION-CLAPTraining=Continued Training on FGMCaps2026.06 | 13.71 | 36.55 | 52.79 | 70.05 | |
| MS-CLAP 20222026.06 | 8.63 | 22.34 | 34.52 | 49.24 | |
| CLAMP 32026.06 | 5.08 | 24.37 | 34.01 | 52.28 |