The aim of this study was to assess the efficiency and safety of combination therapy of ursodeoxycholic acid (UDCA) and bezafibrate for primary biliary cirrhosis. A meta-analysis of all long-term randomized controlled trials comparing the combination of UDCA and bezafibrate with UDCA monotherapy was performed via electronic searches. Seven trials, which included 177 patients, were assessed. Combination therapy with UDCA and bezafibrate was more effective than UDCA monotherapy in improving liver biochemistry, alkaline phosphatase (mean difference [MD], −146.15 IU/L; 95% confidence interval [CI], −193.58 to −98.72; P < 0.00001), γ-glutamyltransferase (MD, −20.64 IU/L; 95% CI, −30.86 to −10.43; P < 0.0001), immunoglobulin M (MD, −90.96 mg/dL; 95% CI, −137.36 to −44.56; P = 0.0001) and triglycerides (MD, −15.49 mg/dL; 95% CI, −30.25 to −0.74; P = 0.04). However, their effects on pruritus (odds ratio [OR], 0.82; 95% CI, 0.30–2.24; P = 0.70) and alanine aminotransferase (MD, −8.41 IU/L; 95% CI, −22.57 to 5.75; P = 0.24) did not differ significantly. This meta-analysis revealed no significant differences in the incidence of all-cause mortality (OR, 0.72; 95% CI, 0.10–5.49; P = 0.75) and adverse events (OR, 0.35; 95% CI, 0.07–1.84; P = 0.22) between patients treated with combination therapy and those treated with monotherapy. In this meta-analysis, combination therapy with UDCA and bezafibrate was more effective than UDCA monotherapy. Combination therapy improved liver biochemistry, but did not improve clinical symptoms, incidence of death or adverse events more effectively than monotherapy.