Abstract: Traditional efficiency modeling is difficult to reflect the actual situation of thetransmission system under complex working conditions, so the GA-BP neural network is used to establish the transmissionefficiency model of electric vehicle reducer. Compared with traditional efficiency models, this model can comprehensivelysearch for the optimal solution using a genetic algorithm, leveraging the nonlinear capability of neural networks, establishes the complex relationship between the reducer's transmission efficiency and multiple variables, including lubricanttemperature, input torque, and rotational speed. The simulation results show that the RMSE of the model is 0.243 54 and 0.332 29, respectively, and the maximum relative error percentage is less than 4%, which verifies the accuracy of the model. Therefore, the model can well reveal the variation law of the transmission efficiency of the reducer with working conditions.