Arterial ischemia and hemorrhage are associated with bevacizumab, an inhibitor of vascular endothelial growth factor that is widely used to treat many types of cancers. As specific types of arterial ischemia and hemorrhage, cerebrovascular events such as central nervous system (CNS) ischemic events and CNS hemorrhage are serious adverse events. However, increased cerebrovascular events have not been uniformly reported by previous studies. New randomized controlled trials (RCTs) have been reported in recent years and we therefore conducted an up-to-date meta-analysis of RCTs to fully characterize the risk of cerebrovascular events with bevacizumab. We searched the databases of PubMed, Web of Science, and the American Society of Clinical Oncology conferences to identify relevant clinical trials up to February 2014. Eligible studies included prospective RCTs that directly compared patients with cancer treated with and without bevacizumab. A total of 12,917 patients from 17 RCTs were included in our analysis. Patients treated with bevacizumab had a significantly increased risk of cerebrovascular events compared with patients treated with control medication, with a relative risk of 3.28 (95% CI, 1.97-5.48). The risks of CNS ischemic events and CNS hemorrhage were increased compared with control, with RRs of 3.22 (95% CI, 1.71-6.07) and 3.09 (95% CI, 1.36-6.99), respectively. Risk varied with the bevacizumab dose, with RRs of 3.97 (95% CI, 2.15-7.36) and 1.96 (95% CI, 0.76-5.06) at 5 and 2.5 mg/kg/week, respectively. Higher risks were observed in patients with metastatic colorectal cancer (RR, 6.42; 95% CI, 1.76-35.57), and no significant risk was observed in other types of tumors. In conclusion, the addition of bevacizumab significantly increased the risk of cerebrovascular events compared with controls, including CNS ischemic events and CNS hemorrhage. The risk may vary with bevacizumab dose and tumor type.