The Sodium-cooled Fast Reactor (SFR) core predesign process is commonly realized on the basis of expert advices and local parametric studies. As such, in-deep knowledge of physical phenomena avoids an important number of expensive simulations. However, the study space is explored only partially. To ease the computational burden metamodels, or surrogate models, can be used, to quickly evaluate the performances of a wide set of different cores, individually defined by a set of parameters (pellet diameter, fissile height...), in the study space. This paper presents the development of a simplified neutronics ERANOS reference core calculation scheme that is then implemented in the construction of the Design of Experiment (DOE) database. The surrogate models for SFR CFV-like cores performances are developed, biases and uncertainties are quantified against the CFV-v1 version. Global Sensitivity Analysis also allowed highlighting antagonist performances for the design and to propose two alternative core configurations. A broadened application of the method with an optimization of a CFV-like core is also detailed. The Pareto front of the seven selected performance parameters has been studied using eleven surrogate models, based on Artificial Neural Network (ANN). The optimization demonstrates that the CFV-v1, designed using Best Estimate codes, under given performance constraints, is Pareto optimal: no other configuration is highlighted from the Multi-Objective Optimization (MOO) study. Further MOO analysis, including a specific study on impact of new degrees of freedom, such as five Pu enrichments compared to two, or different pellet diameters have been performed. Additional configurations are then found by the surrogate models, improving simultaneously all performances of the CFV-v1 configuration. (C) 2016 Elsevier B.V. All rights reserved.