This comprehensive investigation investigated two well-known machine learning models, the Adaptive Neuro-Fuzzy Inference System (ANFIS) and the Artificial Neural Network (ANN). Basic characteristics of cars, such as the number of cylinders, displacement, horsepower, weight, and rate of acceleration, will be used to classify them. The main goal of this research is to give auto dealers practical information that will help them identify and assess the various traits of the vehicles in their inventory. In addition to categorization, our research also looks into the field of predictive modelling. We conducted research to determine the city-specific MPG (miles per gallon) that a car can achieve. This was accomplished by projecting this crucial metric using both models and directly comparing the predictive abilities of the ANFIS and ANN models. Our analysis yielded clear-cut conclusions. The ANN model emerges as the undisputed leader in the prediction of MPG City with an astounding accuracy rate of 93.79%. Contrarily, the ANFIS model only manages to achieve an accuracy rate of 49.27% despite having some advantages. This distinction emphasizes how effective the ANN model is at generating accurate and consistent predictions of city fuel efficiency.