Music educators assess the progress made by their students between lessons. This assessment process is error prone, relying on skills and memory. An objective ear is a tool that takes as input a pair of performances of a piece of music and returns an accurate and reliable assessment of the progress between the performances. The tool evaluates performances using domain knowledge to generate a vector of metrics. The vectors for a pair of performances are subtracted from each other and the differences are used as input to a machine-learning classifier which maps the differences to an assessment. The implementation demonstrates that an objective ear tool is a feasible and practical solution to the problem of assessment.