In this paper, an analytical behavioral model is proposed to describe the dependence of the mutual inductance on the real trajectory of an electrical vehicle, recharged by a dynamic Wireless Power Transfer (WPT) system. The model is derived by means of a multi-objective genetic programming algorithm, which uses a training data set provided by a 3D magneto quasi-static numerical solver. The model is herein applied to a real WPT system working at 85 kHz and successfully validated.