ResearchBenchmarksCross-modal Retrieval (Text to Image) on iNaturalist Species-level Retrieval seenCross-modal Retrieval (Text to Image) on iNaturalist Species-level Retrieval seenFollow91.2Top-1 AccuracyBioVITA-3.637620.983745.60570.2263Mar 25, 2026Evaluation resultsMethodMethodLinksTop-1 AccuracyTop-5 AccuracyBioVITATraining Stage=Stage2Training Stage=Stage22026.0391.297.5BioCLIP 22026.0384.895.3BioVITATraining Stage=Stage1Training Stage=Stage12026.0384.895.3ImageBind2026.0367.986.7TaxaBind2026.0366.986.9CLIP2026.0363.872.5Random2026.030.010.05