Text-to-audio retrieval on AudioCaps (test)
66.59Recall@1KCL
Evaluation Results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| KCLLanguage=eng2025.02 | 66.59 | 91.34 | — | — | — | 40.52 | — | — | |
| CACLLanguage=eng2025.02 | 66.31 | 91.49 | — | — | — | 39.41 | — | — | |
| ML-CLAPLanguage=eng2025.02 | 64.91 | 90.54 | — | — | — | 38.62 | — | — | |
| KCLLanguage=spa2025.02 | 63.76 | 89.39 | — | — | — | 38.73 | — | — | |
| KCLLanguage=nld2025.02 | 63.55 | 90.52 | — | — | — | 39.14 | — | — | |
| KCLLanguage=fra2025.02 | 63.41 | 89.57 | — | — | — | 39.21 | — | — | |
| KCLLanguage=deu2025.02 | 63.34 | 89.28 | — | — | — | 39.02 | — | — | |
| CACLLanguage=fra2025.02 | 63.23 | 89.48 | — | — | — | 37.92 | — | — | |
| CACLLanguage=spa2025.02 | 63.23 | 90.12 | — | — | — | 37.45 | — | — | |
| CACLLanguage=nld2025.02 | 63.23 | 90.86 | — | — | — | 37.95 | — | — | |
| CACLLanguage=deu2025.02 | 63.13 | 89.91 | — | — | — | 38.14 | — | — | |
| ML-CLAPLanguage=spa2025.02 | 63.04 | 88.86 | — | — | — | 37.38 | — | — | |
| KCLLanguage=avg2025.02 | 62.91 | 89.5 | — | — | — | 38.23 | — | — | |
| KCLLanguage=cat2025.02 | 62.71 | 89.49 | — | — | — | 37.65 | — | — | |
| ML-CLAPLanguage=deu2025.02 | 62.65 | 88.76 | — | — | — | 37.88 | — | — | |
| ML-CLAPLanguage=nld2025.02 | 62.5 | 90.33 | — | — | — | 37.72 | — | — | |
| CACLLanguage=avg2025.02 | 62.28 | 89.45 | — | — | — | 37.02 | — | — | |
| KCLLanguage=jpn2025.02 | 62.28 | 89.16 | — | — | — | 36.81 | — | — | |
| ML-CLAPLanguage=fra2025.02 | 61.65 | 89.39 | — | — | — | 37.9 | — | — | |
| ML-CLAPLanguage=cat2025.02 | 61.65 | 87.6 | — | — | — | 36.43 | — | — | |
| CACLLanguage=jpn2025.02 | 61.55 | 88.67 | — | — | — | 34.91 | — | — | |
| CACLLanguage=cat2025.02 | 61.23 | 88.44 | — | — | — | 36.49 | — | — | |
| ML-CLAPLanguage=avg2025.02 | 61.19 | 88.5 | — | — | — | 36.81 | — | — | |
| ML-CLAPLanguage=jpn2025.02 | 59.45 | 87.81 | — | — | — | 35.2 | — | — | |
| Adversarial HubsBase Model=AudioCLIP, Gallery=Poisoned, Retrieved=Adv. Hub2024.12 | 58 | 77.6 | 85.8 | — | 1.5 | — | — | — | |
| KCLLanguage=zho2025.02 | 57.66 | 87.28 | — | — | — | 34.79 | — | — | |
| CACLLanguage=zho2025.02 | 56.4 | 86.65 | — | — | — | 33.93 | — | — | |
| ML-CLAPLanguage=zho2025.02 | 53.67 | 84.76 | — | — | — | 33.38 | — | — | |
| Adversarial HubsBase Model=ImageBind, Gallery=Poisoned, Retrieved=Adv. Hub2024.12 | 52.2 | 71.2 | 81.3 | — | 1.5 | — | — | — | |
| ONE-PEACERetrieval Direction=Audio -> Text2023.05 | 51 | 81.9 | 92 | — | — | — | — | — | |
| AuroLARe-ranking=true2026.02 | 51 | 80.6 | 89.6 | — | — | — | — | — | |
| AuroLARe-ranking=true2026.02 | 51 | — | — | — | — | — | — | — | |
| KCLLanguage=eng2025.02 | 49.68 | 82.44 | — | — | — | 63.34 | — | — | |
| CACLLanguage=eng2025.02 | 49.05 | 82.14 | — | — | — | 63.07 | — | — | |
| KCLLanguage=nld2025.02 | 47.92 | 80.76 | — | — | — | 61.7 | — | — | |
| KCLLanguage=deu2025.02 | 47.81 | 80.81 | — | — | — | 61.78 | — | — | |
| KCLLanguage=fra2025.02 | 47.79 | 80.52 | — | — | — | 61.53 | — | — | |
| SLAPEvaluation Protocol=Supervised2026.01 | 47.5 | 79.8 | 89.2 | — | — | — | — | — | |
| CACLLanguage=nld2025.02 | 47.41 | 80.23 | — | — | — | 61.22 | — | — | |
| KCLLanguage=spa2025.02 | 47.33 | 80.67 | — | — | — | 61.49 | — | — | |
| ML-CLAPLanguage=eng2025.02 | 47.31 | 80.65 | — | — | — | 61.44 | — | — | |
| CACLLanguage=fra2025.02 | 46.86 | 79.97 | — | — | — | 60.83 | — | — | |
| KCLLanguage=avg2025.02 | 46.81 | 80 | — | — | — | 60.81 | — | — | |
| AuroLA2026.02 | 46.8 | 78.4 | 88.3 | — | — | — | — | — | |
| AuroLA2026.02 | 46.8 | — | — | — | — | — | — | — | |
| AuroLAPre-training (PT)=true, Re-ranking=true2026.02 | 46.7 | 76.8 | 85.7 | — | — | — | — | — | |
| AuroLAPre-training (PT)=true, Re-ranking=true2026.02 | 46.7 | — | — | — | — | — | — | — | |
| CACLLanguage=spa2025.02 | 46.68 | 80.52 | — | — | — | 60.9 | — | — | |
| KCLLanguage=cat2025.02 | 46.44 | 79.62 | — | — | — | 60.42 | — | — | |
| CACLLanguage=deu2025.02 | 46.21 | 80.08 | — | — | — | 60.62 | — | — | |
| CACLLanguage=avg2025.02 | 46.03 | 79.5 | — | — | — | 60.15 | — | — | |
| ML-CLAPLanguage=fra2025.02 | 45.88 | 78.92 | — | — | — | 60.01 | — | — | |
| ML-CLAPLanguage=nld2025.02 | 45.88 | 79.64 | — | — | — | 59.92 | — | — | |
| LAION-CLAPRetrieval Direction=Audio -> Text2023.05 | 45.8 | 80.9 | 91.6 | — | — | — | — | — | |
| PE-AV2026.02 | 45.8 | — | — | — | — | — | — | — | |
| PE-AV2026.02 | 45.8 | — | — | — | — | — | — | — | |
| FineLAP2026.04 | 45.7 | 79.5 | 90 | — | — | — | — | — | |
| ML-CLAPLanguage=deu2025.02 | 45.6 | 79.49 | — | — | — | 59.93 | — | — | |
| CED-LEEvaluation Protocol=Supervised2026.01 | 45.6 | 81.3 | 90.2 | — | — | — | — | — | |
| CACLLanguage=cat2025.02 | 45.27 | 78.61 | — | — | — | 59.43 | — | — | |
| KCLLanguage=jpn2025.02 | 45.27 | 78.86 | — | — | — | 59.49 | — | — | |
| ML-CLAPLanguage=spa2025.02 | 45 | 79.32 | — | — | — | 59.62 | — | — | |
| ML-CLAPLanguage=avg2025.02 | 44.84 | 78.43 | — | — | — | 59.09 | — | — | |
| CACLLanguage=jpn2025.02 | 44.76 | 78.5 | — | — | — | 58.97 | — | — | |
| ML-CLAPLanguage=cat2025.02 | 44.36 | 77.89 | — | — | — | 58.58 | — | — | |
| ALM2VecStage=FT2026.06 | 43.2 | 78 | 87.8 | — | — | — | — | — | |
| ML-CLAPLanguage=jpn2025.02 | 43.04 | 76.86 | — | — | — | 57.54 | — | — | |
| ONE-PEACERetrieval Direction=Text -> Audio2023.05 | 42.5 | 77.5 | 88.4 | — | — | — | — | — | |
| OnePeace2026.02 | 42.5 | 77.5 | 88.4 | — | — | — | — | — | |
| OnePeace2026.02 | 42.5 | — | — | — | — | — | — | — | |
| AuroLAPre-training (PT)=true2026.02 | 42.4 | 75.3 | 85.3 | — | — | — | — | — | |
| AuroLAPre-training (PT)=true2026.02 | 42.4 | — | — | — | — | — | — | — | |
| KCLLanguage=zho2025.02 | 42.25 | 76.38 | — | — | — | 56.75 | — | — | |
| WavCapsEvaluation Protocol=Supervised2026.01 | 42.2 | 76.5 | 87.1 | — | — | — | — | — | |
| MGA-CLAP2026.04 | 42.2 | 74.9 | — | — | — | — | — | — | |
| WavCaps-CLAPStage=FT2026.06 | 42.2 | 76.5 | 87.1 | — | — | — | — | — | |
| CACLLanguage=zho2025.02 | 42.01 | 76.02 | — | — | — | 56.23 | — | — | |
| CLAP-HTSATRetrieval Direction=Audio -> Text2023.05 | 41.9 | 73.1 | 84.6 | — | — | — | — | — | |
| M2D2Evaluation Protocol=Supervised2026.01 | 41.9 | 77 | 88.5 | — | — | — | — | — | |
| M2D-CLAP2026.04 | 41.9 | 77.1 | 88.5 | — | — | — | — | — | |
| ML-CLAPLanguage=zho2025.02 | 41.7 | 74.72 | — | — | — | 55.74 | — | — | |
| FLAPmode=fusion2026.02 | 41.5 | 75.5 | 86 | — | — | — | — | — | |
| FLAPFusion=true2026.02 | 41.5 | — | — | — | — | — | — | — | |
| M2D-CLAPModel Type=CLAP Models2026.04 | 41.39 | 77.13 | 88.27 | — | — | — | — | — | |
| TAPRetrieval Direction=Audio -> Text2023.05 | 41.3 | 75.5 | 86.1 | — | — | — | — | — | |
| CacophonyEvaluation Protocol=Supervised2026.01 | 41 | 75.3 | 86.4 | — | — | — | — | — | |
| Cacophony2026.02 | 41 | 75.3 | 86.4 | — | — | — | — | — | |
| Cacophony2026.02 | 41 | — | — | — | — | — | — | — | |
| Cacophony2026.04 | 41 | 75.3 | 86.4 | — | — | — | — | — | |
| ML-CLAP2026.02 | 40.4 | 75.4 | 87.1 | — | — | — | — | — | |
| ML-CLAP2026.02 | 40.4 | — | — | — | — | — | — | — | |
| ALM2VecStage=PT2026.06 | 40 | 74.5 | 85.9 | — | — | — | — | — | |
| WavCaps2026.02 | 39.7 | 74.5 | 86.1 | — | — | — | — | — | |
| WavCaps2026.02 | 39.7 | — | — | — | — | — | — | — | |
| HTSAT-BERT2026.04 | 39.7 | 74.5 | 86.1 | — | — | — | — | — | |
| WavCaps-CLAPStage=PT2026.06 | 39.7 | 74.5 | 86.1 | — | — | — | — | — | |
| MMTRetrieval Direction=Audio -> Text2023.05 | 39.6 | 76.8 | 86.7 | — | — | — | — | — | |
| ML-ACTRetrieval Direction=Audio -> Text2023.05 | 39.4 | 72 | 83.9 | — | — | — | — | — | |
| M-LTM2026.02 | 39.1 | 74.1 | 85.8 | — | — | — | — | — | |
| M-LTM2026.02 | 39.1 | — | — | — | — | — | — | — |