Introduction: We aimed to identify objective factors associated with failure of nonoperative management (NOM) of gastroduodenal peptic ulcer perforation (GDUP) and establish a scoring model for early identification of patients in whom NOM of GDUP may fail. Methods: A total of 71 patients with GDUP were divided into NOM (cases of NOM success) and operation groups (cases requiring emergency operation or conversion from NOM to operation). Using logistic regression analysis, a scoring model was established based on the independent factors. The patients were stratified into low-risk and high-risk groups according to the scores. Results: Of the 71 patients, 18 and 53 were in the NOM and operation groups, respectively. Ascites in the pelvic cavity on computed tomography (CT) and sequential organ failure assessment (SOFA) score at admission were identified as independent factors for NOM failure. The scoring model was established based on the presence of ascites in the pelvic cavity on CT and SOFA score ≥2 at admission. The operation rates for GDUP were 28.6% and 86.0% in the low-risk (score, 0) and high-risk groups (scores, 2 and 4), respectively. Conclusion: Our scoring model may help determine NOM failure or success in patients with GDUP and make decisions regarding initial treatment.