BACKGROUND Antibiotic prophylaxis seems to decrease the incidence of bacterial infections in patients with cirrhosis and upper gastrointestinal bleeding and is considered standard of care. However, there is no updated information regarding the effects of this intervention. OBJECTIVE To assess the benefits and harms of antibiotic prophylaxis in cirrhotic patients with gastrointestinal bleeding by performing a systematic review of randomised trials. METHODS We searched The Cochrane Hepato-Biliary Group Controlled Trials Register, The Cochrane Central Register of Controlled Trials in The Cochrane Library, MEDLINE, EMBASE and Science Citation Index EXPANDED until June 2010. We statistically combined data calculating relative risk (RR) for dichotomous outcomes and mean difference (MD) for continuous outcomes. RESULTS Twelve trials (1241 patients) evaluating antibiotic prophylaxis against placebo or no antibiotic prophylaxis were included. Antibiotic prophylaxis was associated with reduced mortality (RR 0.79, 95% CI 0.63-0.98), mortality from bacterial infections (RR 0.43, 95% CI 0.19-0.97), bacterial infections (RR 0.35, 95% CI 0.26-0.47), rebleeding (RR 0.53, 95% CI 0.38-0.74) and days of hospitalisation (MD -1.91, 95% CI -3.80-0.02). Trials analysing rebleeding rate and hospitalisation length are still scarce, thus, caution should be exerted when interpreting the results. CONCLUSIONS Antibiotic prophylaxis in patients with cirrhosis and upper gastrointestinal bleeding significantly reduced bacterial infections, and reduce all-cause mortality, bacterial infection mortality, rebleeding events and hospitalisation length. Novel clinically significant outcomes were included in this meta-analysis. Some benefits are biased and the risks are not yet properly assessed, this encourages future research in this field.