Accurate liquid-vapor pressure prediction is fundamental to develop equations of state to simulate, evaluate and optimize chemical processes. The accuracy of vapor pressure calculations is essential because it is used as a basis to calculate the acentric factor, thermal and equilibrium properties. In this study, a new accurate equation for calculate the vapor pressure of pure substances as a function of reduced temperature and critical pressure is presented by using Marquardt-Levenberg algorithm which minimize the sum of the squared differences between the values of the observed and predicted values of the dependent variables. Vapor pressures have been calculated with presented substance-dependent equation and compared with the data reported in data compilation for 75 pure substances for more than 15,000 data points, and the overall average absolute percentage deviation is only 0.091%. The accuracy of obtained model has been compared to the mostly used equations and the comparison indicates that the proposed method provide more accurate results than other methods used in this work. (C) 2013 Elsevier B.V. All rights reserved.