The prognostic value of programmed death-ligand 1 (PD-L1) in gastric cancer (GC) remains controversial. To clarify this problem, we performed a meta-analysis of research studies identified in the PubMed, EMBASE and the Cochrane Library databases. A total of 1,901 patients in 10 studies were enrolled in this meta-analysis, and the pooled hazard ratio (HR) of 1.64 (95% CI 1.11 to 2.43; P = 0.01) indicated that PD-L1 expression is associated with a shorter overall survival (OS). The pooled odds ratios (ORs) indicated that PD-L1 expression was associated with tumour size (OR = 1.87, 95% CI 1.25 to 2.78; P = 0.002) and lymph node status (OR = 2.17, 95% CI 1.04 to 4.52; P = 0.04). However, PD-L1 had no correlation with gender, age, cancer location, differentiation, depth of invasion, and tumour stage. This meta-analysis indicates that PD-L1 expression is a valuable predictor of the prognosis of patients with GC. PD-L1 expression could be used for identifying a subgroup of patients, who would potentially benefit from targeted therapy against PD-1 or PD-L1. Well-designed large-cohort studies are needed to confirm these findings.