[en] Three-dimensional deterministic core calculations are typically based on the classical two-step approach, where the homogenized cross sections of an assembly type are pre-calculated and then interpolated to the actual state in the reactor. The weighting flux used for cross-section homogenization is determined assuming the fundamental mode condition and using a critical-leakage model that does not account for the actual environment of an assembly. On the other hand, 3D direct transport calculations and the 2D/1D Fusion method, mostly based on the method of characteristics, have recently been applied showing excellent agreement with reference Monte-Carlo code, but still remaining computationally expensive for multiphysics applications and core depletion calculations. In the present work, we propose a method of Dynamic Homogenization as an alternative technique for 3D core calculations, in the framework of domain decomposition method that can be massively parallelized. It consists of an iterative process between core and assembly calculations that preserves assembly exchanges. The main features of this approach are: i) cross-sections homogenization takes into account the environment of each assembly in the core; ii) the reflector can be homogenized with its realistic 2D geometry and its environment; iii) the method avoids expensive 3D transport calculations; iv) no 'off-line' calculation and therefore v) no cross-section interpolation is required. The verification tests on 2D and 3D full core problems are presented applying several homogenization and equivalence techniques, comparing against direct 3D transport calculation. For this analysis, we solved the NEA 'PWR MOX/UO₂ Core Benchmark' problem, which is characterized by strong radial heterogeneities due to the presence of different types of UOx and MOx assemblies at different burnups. The obtained results show the advantages of the proposed method in terms of precision with respect to two-step and performances with respect to the direct approach. (author)