The aim of this study was to evaluate the efficacy and safety of neo-adjuvant chemotherapy (NACT) versus radical surgery (RS) for patients with cervical cancer. A meta-analysis of randomized controlled trials (RCT) of NACT + RS versus RS alone for patients with cervical cancer was performed according to the guidelines of the Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) statement. The following electronic databases were searched from their inception to April 2015: PUBMED, EMBASE and Cochrane Library. Statistical analysis was done using REVIEW MANAGER 5.3. Five RCT involving 739 patients were studied. There were significant differences between the NACT + RS and the RS-alone groups for positive lymph nodes (OR, 0.45; 95%CI: 0.29–0.70) and parametrial infiltration (OR, 0.48; 95%CI: 0.25–0.92), while treatment efficacy did not differ significantly for 5-year overall survival rate (OR, 1.17; 95%CI: 0.85–1.61), 5-year disease-free survival rate (OR, 1.09; 95%CI: 0.77–1.56) or recurrence rate (OR, 1.17; 95%CI: 0.85–1.61). The results also indicated that chemotherapy-related toxicity was well tolerated. For patients with cervical cancer, NACT could significantly reduce the number of positive lymph nodes and the level of parametrial infiltration compared with RS alone, and be well tolerated.