The casualties due to traffic accidents in Iran are very shocking, which necessitates further investigations into safety measures. The purpose of this study is to evaluate the performance of provinces in road transport safety. The present research data is from the statistical yearbook of Roads and Transportation Organization. The method used in this study was data envelopment analysis (BCC) with weighted input variables in two stages of provincial classification without considering inter-provincial class. Finally, efficient units were compared with Anderson Patterson method. Research data were analyzed using DEA Solver software. In the first stage, 31 provinces without any classification were compared with each other in terms of safety performance indicators presented in the statistical yearbook of the National Road Administration, which included East Azarbaijan, Alborz, Khuzestan, Sistan Baluchestan, Qazvin, Golestan, Gilan, Lorestan, Markazi and Hamadan were found to be ineffective. In the second stage, the provinces were categorized into three categories according to the number of freight and passenger trips, and then each province was compared in terms of performance status with each other. At this stage, Golestan, Sistan and Baluchestan, Markazi, Hamedan, Gilan, Alborz and Lorestan provinces were ineffective. The results of implementation of Anderson Patterson method announced the top three provinces, respectively, Tehran, Isfahan and Khorasan Razavi, respectively.