Although mentoring programs for female STEM students are often carried out with a great deal of passion on the part of program managers and mentors, robust results on their effects are often missing. However, regular evaluations are indispensable for an efficient allocation of resources towards gender balances in STEM. To accomplish this requirement, empirically valid and easy-to-use evaluation concepts are needed. We therefore develop an evaluation concept which corresponds to a Logic Chart, capturing three levels of expected effects (output—outcome—impact). On each level of impact, we derive a set of success indicators that can be measured by qualitative methods. A major advantage of our evaluation design is that the effect of a mentoring program can be observed directly after the end of the program. Furthermore, the results provide information about different channels of impact (e.g., reduced stereotypes or increased self-efficacy) and hence offer concrete indications for the further development of the program.