This study presents a new approach based on Genetic Expression Programming (GEP) for modeling of variation of heat of hydration of Portland and blended cements. For that purpose, two different GEP models were developed to generate two mathematical equations. In the GEP Model 1, six input parameters such as the ground blast furnace slag replacement ratio (GBFS), ground basaltic pumice replacement ratio (GBP), clinker and gypsum ratio (CG), cement fineness (CF), grinding type (GT) and time (T) were used. In GEP Model 2, three input parameters such as cement fineness (CF), grinding type (GT) and time (T) were used. The results were highly promising in terms of training performances and prediction accuracies and revealed that the proposed GEP models can be used in the prediction of heat of hydration of blended cements. © 2009 Academic Journals.