Modeling is an important tool in understanding physical processes in the solar system. Metrics analysis evaluates model performance by comparing model output to a measurable parameter of interest. In this paper we studied the performance of the coupled Block Adaptive‐Tree Solar Wind Roe‐Type Upwind Scheme (BATSRUS) global magnetosphere MHD code and the Fok ring current model (FRC) by examining in detail the geosynchronous proton fluxes during the injection event on 21–22 January 2005. The output of BATSRUS code, calculated ionospheric potential and magnetic field, as well as proton temperature and density distribution, is used as an input boundary condition for the FRC model. We also discuss another event, on 10–11 August 2000, and speculate about the reasons of an apparent difference in the performance of the coupled models for these two events. The results of the simulation are compared with two LANL satellite observations, LANL‐97A and 1994‐084. The comparison of the simulation results for strongly varying solar wind and for prolonged interval of steady solar wind with southward IMF Bz, demonstrates that coupled BATSRUS and FRC models perform fairly for the magnetosphere driven by strong solar wind disturbances and probably are missing some internal magnetosphere dynamics in the second case.