Objective HMG CoA reductase inhibitors (statins) are used to control blood cholesterol levels and reduce cardiovascular disease. It has been repeatedly reported that statins may cause new onset diabetes mellitus (DM). However, there is controversy whether the risk of DM differs among statins. We investigated the risk of new onset diabetes development in subjects treated with different statins. Methods Our study enrolled 1,172 patients without DM who were receiving statin treatment for cholesterol control. We evaluated the incidence of new-onset diabetes according to the type of statin. Results The mean duration of follow up was 56.4 ± 7.9 months. The incidence of DM was significantly higher in the pitavastatin group (11.64%) compared to the other statin groups (atorvastatin (4.76%), rosuvastatin (6.02%), simvastatin (4.08%), and pravastatin (3.64%), P = 0.003). The risk of diabetes was the highest in the pitavastatin group compared with the atorvastatin group (HR = 2.43, P = 0.005). Other statins showed no significant differences compared to atorvastatin. An older age was associated with the development of diabetes (HR=1.03, P = 0.030). Other factors including sex, body mass index, duration of statin use, and total cholesterol level at baseline showed no association with the development of DM. Conclusion Among the five statins, pitavastatin showed the strongest effect on the development of diabetes.