Introduction: Hepatocellular carcinoma (HCC), the most common type of liver cancer, is a major global health problem, ranking as the third leading cause of cancer-related death worldwide. Early identification and diagnosis of HCC requires the discovery of reliable biomarkers. Therefore, the study aimed to assess the diagnostic accuracy of miRNAs for HCC. The protocol was registered on PROSPERO website with the registration number CRD42023417494.Method: A literature search was conducted in PubMed, Scopus, Embase, Wiley Online Library, and Science Direct databases to identify pertinent articles published between 2018 and 30 July 2023. Stata 17.0 software was employed to determine the pooled sensitivity, specificity, positive likelihood ratio (PLR), negative likelihood ratio (NLR), diagnostic ratio (DOR), and area under the curve (AUC) for evaluating the accuracy of miRNAs in diagnosing HCC. The assessment of heterogeneity among studies involved the use of the Cochran-Q test and I2 statistic tests. Due to the observed significant heterogeneity, the random-effect model was chosen. Subgroup analysis and meta-regression analysis were also undertaken to explore potential sources contributing to heterogeneity. Deeks’ funnel plot was used to assess publication bias. In addition, Fagan’s nomogram and likelihood ratio scattergram were utilized to assess the clinical validity of miRNAs for HCC.Result: Twenty-four articles were included, involving 1,668 individuals diagnosed with HCC and 1,236 healthy individuals. The findings revealed pooled sensitivity of 0.84 (95% CI: 0.80–0.88), specificity of 0.81 (95% CI: 0.77–0.84), PLR of 4.36 (95% CI: 3.59–5.30), NLR of 0.19 (95% CI: 0.15–0.25), DOR of 22.47 (95% CI: 14.47–32.64), and an AUC of 0.89 (95% CI: 0.86–0.91) for the diagnosis of HCC using miRNAs. Furthermore, results from the subgroup analysis demonstrated that superior diagnostic performance was observed when utilizing plasma miRNAs, a large sample size (≥100), and miRNA panels.Conclusion: Hence, circulating miRNAs demonstrate substantial diagnostic utility for HCC and can serve as effective non-invasive biomarkers for the condition. Additionally, miRNA panels, miRNAs derived from plasma, and miRNAs evaluated in larger sample sizes (≥100) demonstrate enhanced diagnostic efficacy for HCC diagnosis. Nevertheless, a large pool of prospective studies and multi-center research will be required to confirm our findings in the near future.