Background Androgen receptor (AR) is a potential therapeutic target in triple-negative breast cancer (TNBC). We aimed to elucidate the association of AR expression with glucose metabolic features in TNBC. Methods Two independent datasets were analyzed: FDG PET data of our institution and a public dataset of GSE135565. In PET analysis, patients with TNBC who underwent pretreatment PET between Jan 2013 and Dec 2017 were retrospectively enrolled. Clinicopathologic features and maximum standardized uptake value (SUVmax) of tumors were compared with AR expression. In GSE135565 dataset, glycolysis score was calculated by the pattern of glycolysis-related genes, and of which association with SUVmax and AR gene expression were analyzed. Results A total of 608 female patients were included in the PET data of our institution. SUVmax was lower in AR-positive tumors (P < 0.001) and correlated with lower AR expression (rho = - 0.26, P < 0.001). In multivariate analysis, AR was a deterministic factor for low SUVmax (P = 0.012), along with other key clinicopathologic features. In the GSE135565 dataset, AR expression also exhibited a negative correlation with SUVmax (r = -0.34, P = 0.001) and the glycolysis score (r = -0.27, P = 0.013). Conclusions Low glucose metabolism is a signature of AR expression in TNBC. It is suggested that evaluation of AR expression status needs to be considered in clinical practice particularly in TNBC with low glucose metabolism.