The test treatment in confirmatory clinical trials is often assessed using multiple primary endpoints. We considered that trial efficacy is confirmed only when there is superiority of at least one endpoint and non-inferiority of the remaining endpoints. Some researchers proposed testing procedures for multiple primary endpoints that are continuous variables. However, there has not yet been discussion of the case in which a trial has multiple binary endpoints in the above framework. In this study, we consider a testing procedure for multiple primary endpoints that are binary, and evaluate the performance of the proposed method through simulations.