A QSAR study was developed in order to model the antioxidant activity, specifically the radical scavenger activity (RSA), of 26 di(hetero)arylamines' derivatives of benzo[b]thiophenes. The QSAR model was constructed, using the partial least squares projection of latent structures (PLS) method, and its robustness and predictability were verified by internal and external cross-validation methods. A total of 4 molecular descriptors, belonging to RDF (Radial Distribution Function) descriptors (RDF020e and RDF045e) and 2D-autocorrelation descriptors (GATS8p and MATS5e) were selected to build the QSAR model. RDF descriptors seem to relate the presence of electronegative atoms at the inner atmosphere of the compounds to increase RSA. 2D-Autocorrelation descriptors associate the presence of polarizable and electronegative pairs of atoms, at specific topological distance, with the RSA of the compounds. Finally this QSAR model proved to be a useful tool in the prediction of radical scavenger activity of congeneric compounds and will be used to guide the synthesis of new diarylamines in our laboratory.