ResearchBenchmarksCross-modal Retrieval (Audio to Text) on iNaturalist Species-level Retrieval seenCross-modal Retrieval (Audio to Text) on iNaturalist Species-level Retrieval seenFollow63.7Top-1 AccuracyBioVITA-2.537614.658731.85549.0513Mar 25, 2026Evaluation resultsMethodMethodLinksTop-1 AccuracyTop-5 AccuracyBioVITATraining Stage=Stage2Training Stage=Stage22026.0363.783.8BioVITATraining Stage=Stage1Training Stage=Stage12026.0360.380TaxaBind2026.039.628.1ImageBind2026.0328.9CLAP2026.030.74.7Random2026.030.010.05