Abstract: The city of Duyun is located in a frequent geohazard zone with urban landslides in Guizhou Province. The Shabaobao town is chosen as the study area to assess the landslide susceptibility in the paper. Nine factors, including elevation, slope angle, lithology, water system, etc. are extracted by using raster units. Three models are adopted to evaluate the landslide geohazard susceptibility in Duyun. The binary logistic regression model and information value model are quantitative methods, based on mathematical models when the analytical hierarchy process (AHP) is a qualitative model, depending on the statistical model. The results show that the accuracy and effect of the binary logistic model are the best, whose AUC value under the ROC curve can reach 0.873, and the landslide areas ratio accounts for 95.41% within the high and moderate susceptibility zones according to the model prediction, which corresponds mostly to the field investigation result. The assessment method and results can provide a reference for the evaluation and prevention of geological hazards in urban areas of Guizhou Province.