The main objective of this event is to bring relevant subcommunities of computational biology together and shine a light on the many details of method evaluation, as opposed to the standard focus on "novel" computational approaches, their applications and biological discovery. The conference thus provides attendees with a platform to focus primarily on how we as a community set the standards for collecting evidence to support the use of computational methods. In particular, a primary objective of the conference will be to establish minimum standards of benchmarks and/or best practice, in terms of defining what makes a relevant reference dataset, suitable “metrics of success”, “good” simulations, and what are the outputs (e.g., what set of artifacts) of a good benchmark. A further objective is to facilitate uptake of modern systematic benchmarking frameworks.