Object: Type 2 Diabetes is related with an increased risk of dementia. Dipeptidyl peptidase-4 inhibitors (DPP-4i) have shown promising results for its use in dementia in preclinical studies. Therefore, we investigated the risk of developing dementia in elderly patients initiated on DPP-4i versus sulfonylurea (SU). Methods: A population-based cohort study using claims database named the Korean National Health Insurance Service Senior cohort (ver. 3.0, 1 January 2002 to 31 December 2015) was performed. DPP-4i-treated patients and SU-treated patients were matched by 1:1 propensity score matching which was calculated with 49 confounding variables. Kaplan-Meier curves and Cox proportional hazards regression analysis were performed to estimate the risk of dementia among patients who were prescribed DPP-4i compared with patients who were prescribed SU. Results: In total, 7,561 patients on each group were paired using propensity score matching. The risk of dementia was lower in the DPP-4i group compared to the DPP-4i group (hazard ratio [HR] 0.66; 95% confidence interval [CI] 0.56-0.79; P < 0.001). Also, HR of Alzheimer’s dementia, and vascular dementia were lower in DPP-4i-treated patients compared with SU-treated patients (HR 0.71; 95% CI 0.57-0.89); P = 0.002 for Alzheimer’s dementia, HR 0.50; 95% CI 0.30-0.85); P = 0.01 for vascular dementia). Conclusion: Our findings suggest that DPP-4i use decrease the risk of dementia compared with SU.