Determining pressure loss for cuttings-liquid system is very complicated task since drillstring is usually rotating during drilling operations and cuttings are present inside wells. While pipe rotation is increasing the pressure loss of Newtonian fluids without cuttings in an eccentric annulus, a reduction in the pressure loss for cuttings-liquid system is observed due to the bed erosion. In this study, cuttings transport experiments for different flow rates, pipe rotation speeds, and rate of penetrations (ROPs) are conducted. Pressure loss within the test section and stationary and/or moving bed thickness are recorded. This study aims to predict frictional pressure loss for solid (cuttings)–liquid flow inside horizontal wells using computational fluid dynamics (CFD) and artificial neural networks (ANNs). For this purpose, numerous ANN structures and CFD models are developed and tested using experimental data. Among the ANN structures, TrainGdx–Tansig structure gave more accurate results. The results show that the ANN showed better performance than the CFD. However, both could be used to estimate solid–liquid two-phase pressure drop in horizontal wellbores with pipe rotation.