Correct estimation of sediment volume carried by a river is important with respect to pollution, channel navigability, reservoir filling, hydroelectric-equipment longevity, fish habitat, river aesthetics and scientific interests. Conventional sediment rating curves, however, are not able to provide sufficiently accurate results. In this study, some models based on fuzzy logic is developed as a superior alternative to the sediment rating curve technique for determining suspended sediment concentration for a given river cross-section. This study provides forecasting benchmarks for sediment concentration prediction in the form of a numerical and graphical comparison between fuzzy and rating curve models. Benchmarking was based on five-year period of continuous stream/low and sediment concentration data of Quebrada Blance Station and four-year period of data of Rio Valenciano Station operated by the United States Geological Survey (USGS). Nine different fuzzy models were established for each station to estimate sediment concentration from stream/low. Each fuzzy model had different number of membership functions. Parameters of membership functions are found using differential evolution algorithm. The benchmark results show fuzzy models produce much better results than rating curve models.