Evaluating the performance and efficiency of similar units of an organization with the DEA (Data Envelopment Analysis) model has been a hot debate among researchers in recent decades. In this research, for evaluation of the performance and efficiency of Provincial Gas Companies in Iran, first CCR (Charnes, Cooper, and Rhodes) Input-Oriented Multiple Model and AP (Anderson-Peterson) Model was analyzed for ranking efficient units in the formant of DEA; But weakness of models was determined in terms of separating efficiency of companies. In DEA model, units whose efficiency score is equal to "1" may not be ranked through classical DEA methods; In other words, DEA does not differentiate between such units. To solve this problem, the AP approach is proposed to classify efficient units. This problem is generalizable because of the lower quantity of units in comparison with the ‌input and output quantities of the model. In the continuation of this study, for to solve this problem and analysis and evaluation of the efficiency of companies, attitudes including Performance Calculator Neural Networks were used with the units clustering attitude in the format of synthetic models of DEA and ANNs (Artificial Neural Networks) as called Neuro-DEA. Analytical results of calculating efficiency of these models indicated the higher power of calculation and separability of the model for companies in terms of efficiency. The superiority of neural data envelopment analysis model (Neuro-DEA) compared to other models is in minimizing the inputs to the desired output level. In order to measure the efficiency of the..