The aim of this study is to investigate the prognostic significance of geriatric nutritional risk index (GNRI) at the time of recurrence in patients with recurrent pancreatic cancer, and the relationship between GNRI and skeletal muscle mass for survival outcomes after recurrence. This study enrolled 77 patients who developed postoperative recurrence. The skeletal muscle mass index (SMI) was used in this study. The patients were divided into a high-GNRI group (n = 36) and a low-GNRI group (n = 41) for the GNRI, and were divided into a high-SMI group (n = 38) and a low-SMI group (n = 39) for SMI. The 2-year post-recurrence overall survival of patients in the high-GNRI group was significantly longer than that of patients in the low-GNRI group (P = 0.001). No significant difference for the 2-year post-recurrence OS curves between the high-SMI group and the low-SMI group was observed (P = 0.125). Upon stratifying the patients with high GNRI or low GNRI according to SMI, There was no significant difference in the 2-year post-recurrence OS curves between the patients with both high GNRI and high SMI and the patients with high GNRI and low SMI (P = 0.399). Similarly, There was no significant difference in the 2-year post-recurrence OS curves between the patients with low GNRI and high SMI and the patients with both low GNRI and low SMI (P = 0.256). Multivariate analysis revealed that the GNRI at the time of recurrence was an independent prognostic risk factor in patients with recurrent pancreatic cancer (P = 0.019). The GNRI at the time of recurrence is useful for predicting the prognosis in patients with recurrence pancreatic cancer. Skeletal muscle mass at the time of recurrence is not contributed to predict post-recurrence survival of patients with recurrent pancreatic cancer.