The combined bivariate performance measure (CBPM) introduces a novel performance metric for evaluating a system or process that encompasses two conflicting performance measures. While machine learning (ML) research often deals with training time, it is not typically included as a performance metric due to the challenge of simultaneously presenting these conflicting performances. The article proposes a simple but groundbreaking performance measurement framework that reconciles the compromised value of system performance from these two conflicting performances. This framework can be readily adapted for choosing the highest performing systems among the candidates. The CBPM represents the most advanced integrated performance measure, offering a single value for easy comparison across different ML systems.