Advancements in construction technology have led to the modification of traditional materials to enhance their strength and durability. These demands were the driving force behind the development of high-strength concrete (HSC). Due to its increasing use in numerous construction projects, researchers are motivated to study the behavior of HSC at elevated temperatures. In general, concrete's mechanical and durability characteristics degrade when subjected to elevated temperatures. The current study employs computational intelligence models, specifically Artificial Neural Networks (ANN) and gene expression programming, to assess the residual compressive strength of concrete after exposure to elevated temperatures. This study aims to estimate the residual compressive strength of concrete, which is the output variable, by considering the several input variables including (a) elevated temperature and (b) concrete constituents. A database containing 479 concrete specimens tested at elevated temperatures is established. Using this database, a prediction model based on linear regression, non-linear regression and ANN is developed to compute the residual compressive strength. The ANN model shows a significant correlation between the observed and estimated values when compared to the experimental data, undertaken as part of this study. Artificial neural network (ANN) constructed employing the Bayesian regularisation function demonstrates the highest correlation coefficient.