List your company

Text-to-audio retrieval on AudioCaps (test)

66.59Recall@1KCL
38.000445.422752.84560.2673May 18, 2023Nov 23, 2023May 30, 2024Dec 6, 2024Jun 13, 2025Dec 19, 2025Jun 27, 2026

Evaluation results

MethodLinks
KCLLanguage=eng2025.0266.5991.34———40.52——
CACLLanguage=eng2025.0266.3191.49———39.41——
ML-CLAPLanguage=eng2025.0264.9190.54———38.62——
KCLLanguage=spa2025.0263.7689.39———38.73——
KCLLanguage=nld2025.0263.5590.52———39.14——
KCLLanguage=fra2025.0263.4189.57———39.21——
KCLLanguage=deu2025.0263.3489.28———39.02——
CACLLanguage=fra2025.0263.2389.48———37.92——
CACLLanguage=spa2025.0263.2390.12———37.45——
CACLLanguage=nld2025.0263.2390.86———37.95——
CACLLanguage=deu2025.0263.1389.91———38.14——
ML-CLAPLanguage=spa2025.0263.0488.86———37.38——
KCLLanguage=avg2025.0262.9189.5———38.23——
KCLLanguage=cat2025.0262.7189.49———37.65——
ML-CLAPLanguage=deu2025.0262.6588.76———37.88——
ML-CLAPLanguage=nld2025.0262.590.33———37.72——
CACLLanguage=avg2025.0262.2889.45———37.02——
KCLLanguage=jpn2025.0262.2889.16———36.81——
ML-CLAPLanguage=fra2025.0261.6589.39———37.9——
ML-CLAPLanguage=cat2025.0261.6587.6———36.43——
CACLLanguage=jpn2025.0261.5588.67———34.91——
CACLLanguage=cat2025.0261.2388.44———36.49——
ML-CLAPLanguage=avg2025.0261.1988.5———36.81——
ML-CLAPLanguage=jpn2025.0259.4587.81———35.2——
Adversarial HubsBase Model=AudioCLIP, Gallery=Poisoned, Retrieved=Adv. Hub2024.125877.685.8—1.5———
KCLLanguage=zho2025.0257.6687.28———34.79——
CACLLanguage=zho2025.0256.486.65———33.93——
ML-CLAPLanguage=zho2025.0253.6784.76———33.38——
Adversarial HubsBase Model=ImageBind, Gallery=Poisoned, Retrieved=Adv. Hub2024.1252.271.281.3—1.5———
ONE-PEACERetrieval Direction=Audio -> Text2023.055181.992—————
AuroLARe-ranking=true2026.025180.689.6—————
AuroLARe-ranking=true2026.0251———————
KCLLanguage=eng2025.0249.6882.44———63.34——
CACLLanguage=eng2025.0249.0582.14———63.07——
KCLLanguage=nld2025.0247.9280.76———61.7——
KCLLanguage=deu2025.0247.8180.81———61.78——
KCLLanguage=fra2025.0247.7980.52———61.53——
SLAPEvaluation Protocol=Supervised2026.0147.579.889.2—————
CACLLanguage=nld2025.0247.4180.23———61.22——
KCLLanguage=spa2025.0247.3380.67———61.49——
ML-CLAPLanguage=eng2025.0247.3180.65———61.44——
CACLLanguage=fra2025.0246.8679.97———60.83——
KCLLanguage=avg2025.0246.8180———60.81——
AuroLA2026.0246.878.488.3—————
AuroLA2026.0246.8———————
AuroLAPre-training (PT)=true, Re-ranking=true2026.0246.776.885.7—————
AuroLAPre-training (PT)=true, Re-ranking=true2026.0246.7———————
CACLLanguage=spa2025.0246.6880.52———60.9——
KCLLanguage=cat2025.0246.4479.62———60.42——
CACLLanguage=deu2025.0246.2180.08———60.62——
CACLLanguage=avg2025.0246.0379.5———60.15——
ML-CLAPLanguage=fra2025.0245.8878.92———60.01——
ML-CLAPLanguage=nld2025.0245.8879.64———59.92——
LAION-CLAPRetrieval Direction=Audio -> Text2023.0545.880.991.6—————
PE-AV2026.0245.8———————
PE-AV2026.0245.8———————
FineLAP2026.0445.779.590—————
ML-CLAPLanguage=deu2025.0245.679.49———59.93——
CED-LEEvaluation Protocol=Supervised2026.0145.681.390.2—————
CACLLanguage=cat2025.0245.2778.61———59.43——
KCLLanguage=jpn2025.0245.2778.86———59.49——
ML-CLAPLanguage=spa2025.024579.32———59.62——
ML-CLAPLanguage=avg2025.0244.8478.43———59.09——
CACLLanguage=jpn2025.0244.7678.5———58.97——
ML-CLAPLanguage=cat2025.0244.3677.89———58.58——
ALM2VecStage=FT2026.0643.27887.8—————
ML-CLAPLanguage=jpn2025.0243.0476.86———57.54——
ONE-PEACERetrieval Direction=Text -> Audio2023.0542.577.588.4—————
OnePeace2026.0242.577.588.4—————
OnePeace2026.0242.5———————
AuroLAPre-training (PT)=true2026.0242.475.385.3—————
AuroLAPre-training (PT)=true2026.0242.4———————
KCLLanguage=zho2025.0242.2576.38———56.75——
WavCapsEvaluation Protocol=Supervised2026.0142.276.587.1—————
MGA-CLAP2026.0442.274.9——————
WavCaps-CLAPStage=FT2026.0642.276.587.1—————
CACLLanguage=zho2025.0242.0176.02———56.23——
CLAP-HTSATRetrieval Direction=Audio -> Text2023.0541.973.184.6—————
M2D2Evaluation Protocol=Supervised2026.0141.97788.5—————
M2D-CLAP2026.0441.977.188.5—————
ML-CLAPLanguage=zho2025.0241.774.72———55.74——
FLAPmode=fusion2026.0241.575.586—————
FLAPFusion=true2026.0241.5———————
M2D-CLAPModel Type=CLAP Models2026.0441.3977.1388.27—————
TAPRetrieval Direction=Audio -> Text2023.0541.375.586.1—————
CacophonyEvaluation Protocol=Supervised2026.014175.386.4—————
Cacophony2026.024175.386.4—————
Cacophony2026.0241———————
Cacophony2026.044175.386.4—————
ML-CLAP2026.0240.475.487.1—————
ML-CLAP2026.0240.4———————
ALM2VecStage=PT2026.064074.585.9—————
WavCaps2026.0239.774.586.1—————
WavCaps2026.0239.7———————
HTSAT-BERT2026.0439.774.586.1—————
WavCaps-CLAPStage=PT2026.0639.774.586.1—————
MMTRetrieval Direction=Audio -> Text2023.0539.676.886.7—————
ML-ACTRetrieval Direction=Audio -> Text2023.0539.47283.9—————
M-LTM2026.0239.174.185.8—————
M-LTM2026.0239.1———————