Background: Comorbid depression/anxiety in type 2 diabetes mellitus (DM) patients is highly prevalent, affecting both diabetes control and quality of life. However, the best treating method for depression/anxiety in type 2 DM patients is still unclear. This study was conducted to compare the efficacy of paroxetine and agomelatine on depression/anxiety and metabolic control of type 2 DM patients. Methods: A total of 116 depressed, type 2 DM patients were recruited for 12 weeks treatment. Patients were randomly assigned to receive either paroxetine or agomelatine. Hamilton Depression Rating Scale and Hamilton Anxiety Rating Scale were used to assess depression and anxiety, respectively. Hemoglobin A1c, fasting plasma glucose, and body mass index were assessed at baseline and at the end of the trial. Results: At the end of the trial, there were 34 (60.7%) responders and 22 (39.3%) remissions in paroxetine group; and 38 (63.3%) responders and 26 (43.3%) remissions in agomelatine group. Compared to paroxetine group, lower depression scores were observed in agomelatine group. Fasting plasma glucose and body mass index were not significantly different after 12 weeks treatment between the two groups, but agomelatine group had a significantly lower final hemoglobin A1c level compared to paroxetine group. The two antidepressants had comparable acceptability. Conclusion: These results showed that compared to paroxetine, agomelatine might have some advantages in treating symptoms of depression/anxiety and glycemic control in depressed type 2 DM patients. The clinical applicability of agomelatine shows greater promise and should be explored further. Limited by the relatively small samples, future studies are needed to verify and support our findings.