The packed bed extraction of spearmint oil using supercritical carbon dioxide was studied by a two-phase mass transfer model on the basis of desorption and diffusion. Unsteady-state mass balance for solute in supercritical and in solid phases led to two partial differential equations that were solved numerically using a linear equilibrium relationship. The model has four parameters, axial dispersion, mass transfer, and diffusion and desorption coefficients. Diffusion and desorption coefficients were used as the model tuning parameters and the others were predicted applying existing experimental correlations. The tuning parameters were calculated by the fitting error between 5 and 15% by the genetic algorithm method. In addition, this model was compared with a model that did not account for the desorption rate, according to the model suggested by Goodarznia and Eikani (G&E). Moreover, the effects of operational parameters such as pressures, temperatures, CO2 flow rates, and mean particle sizes on the extraction yield were evaluated. In order to obtain experimental data for spearmint oil, a facility was designed and constructed to conduct the experimental part of this study. The two models were also applied to the literature's experimental data for rosemary leaves, grape seeds, peanuts, and tomato seeds. Comparison of the results of the proposed model with results from the G&E model indicated that the proposed model had better predictability. Also, good agreement of the proposed model results and the experimental data confirmed the basic hypothesis of the model and the importance of the desorption rate.