This work aims to sort cocoa beans according to chocolate sensory quality and phenolic composition. Prior tothe study, cocoa samples were processed into chocolate in a standard manner, and then the chocolate was characterized bysensory analysis, allowing sorting of the samples into four sensory groups. Two objectives were set:first to use average massspectra as quick cocoa-polyphenol-extractfingerprints and second to use thosefingerprints and chemometrics to select themolecules that discriminate chocolate sensory groups. Sixteen cocoa polyphenol extracts were analyzed by liquidchromatography−low-resolution mass spectrometry. Averaging each mass spectrum provided polyphenolicfingerprints,which were combined into a matrix and processed with chemometrics to select the most meaningful molecules fordiscrimination of the chocolate sensory groups. Forty-four additional cocoa samples were used to validate the previous results.Thefingerprinting method proved to be quick and efficient, and the chemometrics highlighted 29m/zsignals of known andunknown molecules, mainlyflavan-3-ols, enabling sensory-group discrimination.