The aroma components of two grades of Huangjincha tea 2 were investigated by using headspace solid-phase microextraction (HS-SPME) coupled with gas chromatography-mass spectrometry (GC-MS) to establish their aroma fingerprints. The results were analyzed using chemometrics. Totally 81 aroma components were identified, 41 of which were common to both. Based on these common aroma components, the two grades could be discriminated by orthogonal partial least squares-discrimination analysis (OPLS-DA), and nine differential aroma components between them were identified including heptanal, limonene, trans-β-ocimene, 1-octanol, (E)-4,8-dimethylnona-1,3,7-triene, trans-nerolidol, 1,10-diepicubenol, epicubenol, and methyl hexadecanoate. A linear discriminant model to distinguish the two grades was established using the differential aroma components as independent variables. The self-validation and cross-validation accuracy of this model were 100%. These results may provide an objective and quantitative reference for the classification of Huangjincha 2.