Heavy metals are among the most persistent of pollutants in aquatic systems due to their resistance to decomposition in nature. Four assessment methods (two pollution indexes and two fuzzy mathematical models - single-factor deciding and weighted average models) were used to check the level and characteristics of heavy metal pollution in the Karasu stream water. Several heavy metals such as Copper (Cu), Zinc (Zn), Manganese (Mn), Lead (Pb), Nickel (Ni), Cadmium (Cd) and Iron (Fe) were tested with these methods. A data set (12 months, total 180 measurements) was collected from 5 sampling points (A-E) of the River. The used criteria were classes, I-IV represents from clear to polluted one. Water quality was assessed as class IV from all water samples collected from the each station with single-factor index method. It was identified to be class IV from the samples of A, B, C and D stations, and class Ill from the sample of E station with the comprehensive index model. By using the fuzzy mathematical methods, the water quality were determined as classes of IV, IV, IV, II and II from the water samples of A, B, C, D and E stations respectively. Introduction of membership degree and weight of each factor to fuzzy mathematical models made the methods more reasonable in the field of water quality assessment. Therefore, these fuzzy mathematical methods might be quite convenient in evaluation of water pollution and classification considering the results of the present study.