Aiming at the lack of objective feedback on programming ability and the difficulty in determining the weights of evaluation indexes in power system applications, we establish a programming ability evaluation model of genetic algorithm (GA) optimized back propagation (BP) neural network (GA-BP). By mining the data in power system applications, the programming ability assessment indexes are extracted, and the objective combination of the two-parameter balanced entropy weight method and the deviation maximization method is used to determine the weights of the indexes as well as the assessment value of the programming ability, which is taken as the desired output of the GA-BP neural network, and compared with the programming ability assessment results determined by a single BP neural network. The results of the study show that the model can be used to achieve a more accurate assessment of the programming capability of neural networks in power system applications.