This meta-analysis aimed to obtain a comprehensive and reliable assessment of the relationships between XRCC1 Arg399Gln and XPD Lys751Gln polymorphisms and the clinical outcomes of gastric cancer (GC) patients treated with oxaliplatin-based chemotherapy. The PubMed, CINAHL, Web of Science, CISCOM, EBSCO, Google Scholar, Cochrane Library, and CBM databases were searched for relevant articles published before September 1, 2013 without language restrictions. Crude odd ratios (ORs) or hazard risk (HR) [95 % confidence intervals (CI)] were calculated. Twelve clinical cohort studies were assessed with a total 1,024 GC patients treated with oxaliplatin-based chemotherapy. Our meta-analysis findings revealed that GC patients with the GA+AA (A carrier) genotypes of XRCC1 Arg399Gln showed a lower effective clinical response (CR+PR) than those with the GG (A non-carrier) genotype (OR=0.41, 95 % CI 0.20∼0.82, P=0.012). However, there was no statistically significant difference in effective clinical response between those with XPD AC+CC (C carrier) genotypes and CC (C non-carrier) genotype (OR=0.55, 95 % CI 0.28∼1.07, P=0.076). Furthermore, the GA+AA genotypes of XRCC1 Arg399Gln was associated with a worse progression-free survival (PFS) and overall survival (OS) compared with the CC genotype (PFS, HR=1.90, 95 % CI 1.12∼2.69, P<0.001; OS, HR=2.13, 95 % CI 0.79∼3.47, P=0.002, respectively). No relationships were found between XPD Lys751Gln polymorphism and both PFS and OS (all P>0.05). No publication bias was detected in this meta-analysis. Results from the current meta-analysis indicate that XRCC1 Arg399Gln polymorphism may be associated with poor clinical outcomes in GC patients treated with oxaliplatin-based chemotherapy.