| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| ESC-50 | CALM | Accuracy99.25 | 461 | 1mo ago | |
| AudioSet 20K | CAT | mAP47.8 | 151 | 1mo ago | |
| Urbansound8K | ConformerXL-P Non-RA | Accuracy97.5 | 126 | 3mo ago | |
| ESC-50 (test) | M2D2 | Accuracy98.5 | 111 | 1mo ago | |
| AudioSet 2M | MiCo | mAP50.5 | 102 | 1mo ago | |
| VGG-Sound | CALM | Top-1 Accuracy88.15 | 83 | 1mo ago | |
| ESC50 | PALM + ASPL* | Top-1 Acc96.58 | 73 | 1mo ago | |
| Speech Commands (test) | Chimera | Accuracy98.4 | 65 | 23d ago | |
| SPC V2 | SupMAM-CLAP | Accuracy98.7 | 65 | 4mo ago | |
| GTZAN | Nystromformer | Accuracy94.66 | 65 | 1mo ago | |
| AudioSet | mAP49.6 | 60 | 2mo ago | ||
| Speech Commands V2 (test) | ASiT | Accuracy98.9 | 59 | 1mo ago | |
| US8K (test) | EAT (LoRA) + Joint Training | R@1 Accuracy0.9807 | 56 | 1mo ago | |
| Beijing-Opera | CoCoOp | Base Accuracy100 | 48 | 24d ago | |
| SHD (test) | DelRec* | Accuracy91.72 | 41 | 3mo ago | |
| UrbanSound8K single-label | DAS | Accuracy77 | 35 | 1mo ago | |
| VocalSound | F3-Tokenizer | Accuracy91.6 | 32 | 24d ago | |
| AudioSet-2M (full) | BEATSiter3+ | mAP48.6 | 32 | 4mo ago | |
| US8K | MATPAC++ | Top-1 Accuracy89.7 | 30 | 1mo ago | |
| ESC50 (test) | MUKA | R@1 Accuracy0.9803 | 28 | 4mo ago | |
| TUT 2017 | SubT | Base Accuracy93.69 | 27 | 24d ago | |
| GT-Music-Genre | SubT | Base Accuracy91.09 | 27 | 24d ago | |
| RAVDESS | SubT | Base Accuracy72.85 | 27 | 24d ago | |
| ESC50 Actions | SubT | Accuracy (Base)100 | 27 | 24d ago | |
| NS-Instruments | COOP + ZEBRA | Base Accuracy70.78 | 27 | 24d ago |