Computational Fluid Dynamics (CFD) simulations of oxy-coal combustion experiments conducted at the IFRF at the semi-industrial scale with two different burners, i.e. the Aerodynamically Air Staged Burner (AASB) and the low-NOx TEA-C burner, were performed in order to investigate the performance of different sub-models for oxy–fired conditions. Special attention was devoted to the reduction of computational cost by using proper modelling strategies based on reduced and complete computational domains. The uncertainties due to the choice of different sub-models and boundary conditions are discussed, highlighting the need for accurate and comprehensive experimental datasets to validate computational models. Discussion is made of the use of proper validation metrics to quantify the level of agreement between predictions and experiments.