Fig. 2: Benchmarking Results: Biomarker Prediction Tasks.
From: A clinical benchmark of public self-supervised pathology foundation models
Each box plots summarizes the distribution of validation performance across 20 MCCV splits (N = 20). Boxes show the quartiles of each distribution, while the whiskers extend 1.5 times the interquartile range. Source data are provided as a Source Data file.
