As non-nucleoside reverse transcriptase inhibitors, tetrahydroimidazo [4,5,1-jk][1, 4] benzodiazepinone (TIBO) derivatives play an important role in treating acquired immunodeficiency syndrome (AIDS). The activities (The 50% antiviral inhibitory concentration, pIC50) of a series of HIV reverse transcriptase inhibitor TIBO derivatives were modeled by the quantitative structure-activity relationship (QSAR) method. Based on the norm indexes proposed by our group, a multiple linear regression (MLR) model was developed to estimate the pIC 50 of anti HIV-1 activity of TIBO derivatives. The squared correlation coefficients for training set (R 2 train) and test set (R 2 test) are 0.911 and 0.913, respectively. The average absolute relative deviation (ARD) and overall average absolute error (AAE) are 5.78% and 0.330, respectively. Comparison results with other references demonstrated that this norm-based model was efficient and could provide satisfying prediction results.