In this meta-analysis, all relative literature was retrieved through the Embase and PubMed databases. Moreover, the Stata 12.0 software package was applied to calculate the pooled odds ratio (OR) of the 95% confidence interval (CI). A total of seven studies was identified to analyze the relation between ERCC1 and ERCC2 gene polymorphisms and pancreatic cancer risk. The results showed that ERCC2 rs13181 polymorphism was associated with pancreatic cancer (CC vs. AA: OR = 1.53, 95% CI = 1.24-1.90; AC vs. AA: OR = 1.06, 95% CI = 0.92-1.22; dominant model: OR = 1.16, 95% CI = 1.02-1.32; recessive model: OR = 1.39, 95% CI = 0.13-1.70). For ERCC1 rs3212986 polymorphism, a significant correlation with pancreatic cancer risk was found (TT vs. GG: OR = 2.33, 95% CI = 1.73-3.14; GT vs. GG: OR = 1.34, 95% CI = 1.11-1.63; dominant model: OR = 1.50, 95% CI = 1.25-1.80; recessive model: OR = 1.98, 95% CI = 1.50-2.62). A lack of association was found for ERCC1 rs11615 polymorphism (TT vs. CC: OR = 1.21, 95% CI = 0.93-1.56; CT vs. CC: OR = 1.02, 95% CI = 0.87-1.21; dominant model: OR = 1.43, 95% CI = 0.80-2.50; recessive model: OR = 0.99, 95% CI = 0.65-1.51).