Hemorrhage of arteriovenous malformation (AVM) is a rare condition during pregnancy. This study was proposed to pool the proportion of AVM hemorrhage per pregnancy. A systematic review and meta-analysis with three databases were performed to review the studies published until April 2022. The Newcastle Ottawa Scale was used for risk assessment of data quality. The meta-analysis was conducted by a generic inverse variance of double arcsine transformation with a random model using Stata software. Twelve studies were included in this review. The pooled proportion of AVM hemorrhage per pregnancy was 0.16 (95% CI: 0.08, 0.26). The subgroup analyses were carried out based on world regions and study designs, and the study duration with the highest proportion of each subgroup was Europe [0.35 (95% CI: 0.02, 0.79)], with retrospective review [0.18 (95% CI: 007, 0.32)] and 10 to 20 years of study duration [0.37 (95% CI: 0.06, 0.77)]. The AVM hemorrhage per pregnancy in this review was considered low. However, the conclusion must be carefully interpreted since this review had a small study limitation.