Recently, novel machine-learning algorithms have shown potential for predicting undiscovered links in biomedical knowledge networks. However, dedicated benchmarks for measuring algorithmic progress have not yet emerged. With OpenBioLink, we introduce a large-scale, high-quality and highly challenging biomedical link prediction benchmark to transparently and reproducibly evaluate such algorithms. Furthermore, we present preliminary baseline evaluation results.Source code and data are openly available at https://github.com/OpenBioLink/OpenBioLink.Supplementary data are available at Bioinformatics online.