Staging fibrosis is crucial for the prognosis and to determine the rapid need of treatment in patients with chronic hepatitis B (CHB) and C (CHC). The expression of 13 fibrosis-related microRNAs (miRNAs) (miR-20a, miR-21, miR-27a, miR-27b, miR-29a, miR-29c, miR-92a, miR-122, miR-146a, miR-155, miR-221, miR-222, and miR-224) was analyzed in 194 serums and 177 liver biopsies of patients with either CHB or CHC to develop models to diagnose advanced fibrosis and cirrhosis (Metavir F3-F4). In CHB patients, the model (serum miR-122, serum miR-222, platelet count and alkaline phosphatase) was more accurate than APRI and FIB-4 to discriminate in between mild and moderate fibrosis (F1-F2) and F3-F4 (AUC of CHB model: 0.85 vs APRI: 0.70 and FIB-4: 0.81). In CHC patients, the model (hepatic miR-122, hepatic miR-224, platelet count, albumin and alanine aminotransferase) was more accurate than both APRI and FIB-4 to discriminate in between patients with F3-F4 and F1-F2 (AUC of the CHC model = 0.93 vs APRI: 0.86 and FIB-4: 0.79). Most of the miRNAs tested were differentially expressed in patients with CHB and CHC. In particular, serum miR-122 was 28-fold higher in patients with CHB than in those with CHC. Both CHB and CHC models may help for the diagnosis of advanced fibrosis and cirrhosis (F3-F4).