[Objective] The simulation effects and land use prediction accuracy of three land use transition models (LogReg, MLP, and SimWeight) for multi-land change analysis were compared and analyzed in order to provide a reference for land space planning, soil and water conservation, and ecological restoration in the Yunnan-Guizhou Plateau. [Methods] Three models were used to simulate land use changes for Kunming City from 2000 to 2020. Various methods such as ROC curve, AUC coefficient, and kappa coefficient were used to evaluate model performance. [Results] The simulations of change trends for most land use classes by MLP and SimWeight were better than the simulations by LogReg, especially with regard to the change analysis of unused land where the AUC values for MLP and SimWeight were greater than 0.9. The kappa values for LogReg, MLP, and SimWeight were 0.906 6, 0.904 1, and 0.925 3, respectively. The overall prediction results for the three models were similar, and SimWeight was slightly better than the two other models. [Conclusion] For LUCC modeling of Kunming City, SimWeight is recommended when the user desires higher accuracy, MLP is recommended when the user cares more about calculation speed, and LogReg is recommended when the user wants to further analyze the relationship between driving factors and land use changes.