Genetic polymorphisms of RAD51 135 G>C and XRCC2 G>A (rs3218536) have been reported to change the risk of ovarian cancer, but the results are controversial. To get a more precise result, a meta-analysis was performed. A comprehensive literature search in PubMed, Excerpta Medica Database, and China National Knowledge Infrastructure was carried out to get case-control studies published up to November 2013. The pooled odds ratio (OR) and its corresponding 95 % confidence interval (CI) were conducted to estimate the effect of RAD51 135 G>C and XRCC2 G>A (rs3218536) polymorphisms on ovarian cancer risk. A total of 13 independent case-control studies with 5,927 cases and 10,303 controls were included in this meta-analysis. There was no significant association between RAD51 135 G>C polymorphism and risk of ovarian cancer. However, the result of total studies indicated the XRCC2 G>A (rs3218536) polymorphism could reduce the risk of ovarian cancer (heterozygote model AG vs. GG: OR=0.877, 95 % CI=0.770-0.999, P=0.048; dominant model AA/AG vs. GG: OR=0.864, 95 % CI=0.763-0.979, P=0.022). The result was still significant after Hardy-Weinberg equilibrium-violating studies were excluded (allele contrast A vs. G: OR=0.836, 95 % CI=0.74-0.943, P=0.004; homozygote model AA vs. GG: OR=0.562, 95 % CI=0.317-0.994, P=0.048; heterozygote model AG vs. GG: OR=0.859, 95 % CI=0.753-0.98, P=0.023; dominant model AA/AG vs. GG: OR=0.842, 95 % CI=0.74-0.958, P=0.009). In the stratified analysis by ethnicity, significantly reduced risk was observed among Caucasians in dominant model (AA/AG vs. GG: OR=0.867, 95 % CI=0.764-0.984, P=0.027). No significant association was found between the RAD51 135G>C polymorphism and the risk of ovarian cancer. Interestingly, XRCC2 G>A (rs3218536) polymorphism might reduce the risk of ovarian cancer. Larger-scale and well-designed studies are needed to further clarify the association.