Accurate determination of pressure-volume-temperature (PVT) properties of petroleum reservoirs is essential in material balance calculations, inflow performance, well-test analysis, reservoir simulation, etc. Ideally, those data should be obtained experimentally; however, experimental measurements require accurate and enough sampling, and are time consuming, expensive and tedious. Therefore, seeking for a simple, reliable and accurate model for prediction of PVT properties of petroleum systems is of a vital importance. In this communication, a large PVT data bank, covering a wide range of thermodynamic conditions was collected from variety of geographical locations around the world. Afterward, gene expression programming (GEP) was employed to develop a universal model for solution gas: oil ratio. The proposed model is a function of bubble point pressure, gas specific gravity, and oil API gravity, and has a very simple format with only one tuning parameter. The proposed model was compared to both explicit and implicit models available in literature for prediction of solution gas: oil ratio, using statistical and graphical error analyses. The results of this study indicate that the proposed model is more accurate, reliable and efficient compared to all other published correlations.