Comparative molecular field analysis (CoMFA), comparative molecular field analysis region focusing (CoMFA-RF) for optimizing the region for the final partial least square analysis, and comparative molecular similarity indices analysis (CoMSIA) methods were employed to develop three-dimensional quantitative structure–activity relationship (3D-QSAR) models of 1H NMR chemical shift of NH proton of diaryl triazene derivatives. The best orientation was searched by all-orientation search (AOS) strategy to minimize the effect of the initial orientation of the structures. The predictive abilities of CoMFA-RF and CoMSIA models were determined using a test set of ten compounds affording predictive correlation coefficients of 0.721 and 0.754, respectively, indicating good predictive power. For further model validation, cross validation (leave one out), progressive scrambling, and bootstrapping were also applied. The accuracy and speed of obtained 3D-QSAR models for the prediction of 1H NMR chemical shifts of NH group of diaryl triazene derivatives were greater compared to some computational well-known procedures. Copyright © 2013 John Wiley & Sons, Ltd.