Objective: Recent reports have shown that C-X-C chemokine receptor 4 (CXCR4) is expressed in ovarian cancer and plays an important role in metastasis. However, the prognostic value of CXCR4 in ovarian cancer remains controversial and has not been emphasized. The aim of this study is to evaluate the prognostic significance of CXCR4 in ovarian cancer by performing a meta-analysis. Methods: We systematically searched for studies evaluating the relationship between CXCR4 expression and the outcome of ovarian cancer patients. Only articles in which CXCR4 expression was detected by immunohistochemical staining were included. Hazard ratios (HRs) and relative risk (RR) with 95% confidence intervals (CIs) were pooled as effect size (ES) across studies for overall survival (OS) and progression-free survival (PFS). Results: A total of 729 patients from 7 studies (6 articles) were included in this meta-analysis. Our results showed that high CXCR4 expression was significantly associated with poor prognosis in terms of OS (ES, 2.81; 95% CI, 1.16–6.80; p = 0.022) and PFS (ES, 8.48; 95% CI, 2.13–33.70; p = 0.002) in ovarian cancer patients. The association between high CXCR4 expression and poor ovarian cancer prognosis in OS was also statistically significant in subgroups of Asian and III-IV patients constituting 70%. Conclusions: The present meta-analysis indicated that high CXCR4 expression was associated with poor prognosis in ovarian cancer. More studies, especially larger scale and well-matched researches, are warranted to clarify the prognostic effect of CXCR4 on the outcome of ovarian cancer.