| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Clotho (test) | AuroLA | R@138.6 | 85 | 16d ago | |
| AudioCaps (test) | AuroLA | R@165.6 | 69 | 16d ago | |
| DiDeMo (test) | LoRS | R@15.3 | 19 | 5d ago | |
| VCTK A→T | PEAV S | Recall@196.1 | 15 | 1mo ago | |
| Clotho V2 (test) | WavCaps | Recall@118.78 | 13 | 1mo ago | |
| Auto-ACD (test) | AuroLA | R@141.8 | 10 | 1mo ago | |
| VALOR | PE-AV | Recall@135.1 | 9 | 1mo ago | |
| EPIC-Sounds | AuroLA | mAP50.3 | 8 | 1mo ago | |
| HD-EPIC | AuroLA | mAP32.2 | 8 | 1mo ago | |
| VGGSounder | AuroLA | mAP48.9 | 8 | 1mo ago | |
| Clotho 1K 1.0 (test) | ONE-PEACE | R@127.1 | 8 | 1mo ago | |
| AudioCaps 1K 1.0 (test) | FuseMix(W&H,B) | R@152.4 | 8 | 1mo ago | |
| Taxonomic Retrieval Family level | BioVITA | Top 1 Accuracy19.2 | 4 | 23d ago | |
| Taxonomic Retrieval Genus level | BioVITA | Top-1 Accuracy53.6 | 4 | 23d ago | |
| Clotho | ASK+ | R@10.195 | 4 | 1mo ago | |
| InternalSFX (test) | Woosh-CLAP-Private | R@569.4 | 3 | 16d ago | |
| Unseen species-level | BioVITA | Top-1 Accuracy36.6 | 3 | 23d ago | |
| AVE | BrokenBind | Accuracy33.1 | 3 | 1mo ago | |
| MSRVTT | BrokenBind | Accuracy36.4 | 3 | 1mo ago | |
| Sound (test) | Speech-CLAP | R@111.27 | 3 | 1mo ago | |
| Speech (test) | CLAP | R@10.51 | 3 | 1mo ago | |
| OpenImages 5K (test) | OPT | R@180.3 | 1 | 1mo ago |