Objective: To determine whether there was a seasonal variation in the incidence of gestational diabetes mellitus (GDM) by using two-step approach for GDM diagnosis. Methods: A total of 6,396 pregnant Taiwanese women were enrolled in this retrospective cohort study between 2012 and 2014. Two-step approach was used for GDM diagnosis in all study participants. The results of all pregnancy glucose challenge test (GCT) and oral glucose tolerance test (OGTT) were collected. A modified Poisson regression approach was used to model seasonal trends. Results: During the study period, 418 (6.5%) women were diagnosed with GDM. Seasonal modeling showed a strong relation between season and GDM (p<0.001). Unadjusted and adjusted models (adjusted for maternal age, body mass index (BMI), parity) demonstrated the presence of a peak incidence occurring among pregnancies with GDM in Spring (March, April, May) and Summer (June, July, August) (RR:1.50, 95% CI:1.11-2.03; RR:1.50, 95% CI:1.12-2.00), compared to Winter (January, February, December). As this was a retrospective study, we could only use variables that been collected as part of the hospital information system. Conclusion: Our findings suggested a seasonal variation for GDM in Taiwan. Further mechanistic studies are warranted.