The volatile components in Anhua and other dark teas were analyzed by headspace solid phase microextraction (HS-SPME) combined with gas chromatography-time of flight mass spectrometry (GC-TOF MS). About 41 volatile compounds were analyzed qualitatively and quantitatively. A classification model and predict the authenticity obtained from variance analysis, principal component analysis (PCA) and partial least squares discriminate analysis (PLSDA). In addition, the 26 compounds significant impacting on the classification were screened out from Anhua dark tea. The straight forward classification trend of Anhua dark tea and other samples was visualized through projection score plots obtained by PCA. Effective classification and identification of Anhua dark tea, other origin dark tea and other kinds were carried out. The 14 important components for classification were found. The results showed that the developed GC-TOF MS method combined with chemometrics based on the volatile components in tea could be used to discriminate Anhua dark tea.