<p>To verify the rationality of different mathematical models for susceptibility assessment of post-earthquake disasters, taking the hazard statistics of Lushan County in Ya’an City, China as an example, this study preliminarily selected 12 evaluation factors closely related to geological disasters, such as elevation, slope, and aspect, as well as 159 actual disaster sites based on Geographic Information System (GIS). Traditional susceptibility assessment models—including the information value (I) model, certain factor (CF) model, informative–logistic regression (I-LR) model, and certain factor–logistic regression (CF-LR) model—were applied, alongside the machine learning-based random forest (RF) model, to evaluate the susceptibility of local disasters. Thirty disaster sites that were not included in the models were selected as test samples, and the rationality and accuracy of the four mathematical models were evaluated and tested using the frequency ratio method and Receiver Operating Characteristic (ROC) curve method, respectively. The results showed that all four traditional models indicated that the extremely high and high susceptibility areas of Lushan County are mainly concentrated in the low-altitude and valley areas in the south and central parts, while the low and extremely low susceptibility areas are distributed in the high mountainous and canyon areas in the north, which is basically consistent with the actual investigation. The AUC values for the four traditional models’ evaluation accuracy, from high to low, are CF-LR (0.825), I-LR (0.822), I (0.816), and CF (0.815). The first two coupled models, which consider the weight coefficients of influencing factors, show slightly improved results compared to single models. However, the Random Forest model based on machine learning has an AUC value of 0.920 for evaluation accuracy, demonstrating the best performance. The research findings offer valuable insights for selecting regional susceptibility assessment models for post-earthquake disasters.</p>