The identification of gasoline adulteration by organic solvents is not an easy task, because compounds that constitute the solvents are already in gasoline composition. In this work, the use of hydrogen nuclear magnetic resonance (H-1 NMR) with a statistical approach for identifying gasoline adulteration by organic solvents is described. Both principal component analysis (PCA) and hierarchical cluster analysis (HCA) from NMR data of 47 commercial samples allowed the distinction between conform and nonconform samples. The 1H NMR-PCA and H-1 NMR-HCA models were evaluated through the analyses of 21 intentionally adulterated samples, which showed a tendency to meet in the nonconform group with the increase of the solvent concentration.