Protify: A Benchmarking Platform Revealing Task Dependence and Homology Leakage in Protein Language Model Evaluation
Nikolaos Rafailidis, Logan P Hallee, Tamar Peleg, Colin Horger, Luck Haviland, Jason P Gleghorn
Protify benchmarks protein language models across tasks and evaluation settings, revealing task dependence and homology leakage in model performance.
bioRxiv · Nov 5, 2026 · PreprintBioinformatics