The pursuit of cement-based materials with enhanced mechanical performance in the construction industry involves formulating numerous mixtures with varied contents of raw materials. However, the scarcity or contamination of these materials demands optimization methods to minimize the number of trials required. Response Surface Methodology (RSM) is a statistical experimental optimization method with which relations between sets of factors and responses can be established. This systematic review aims to analyze the existing literature on RSM models developed to achieve optimum levels in cementitious mixes. Over 100 papers were analyzed in accordance with the Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) format. A comprehensive review of the RSM analyses in those studies and their effectiveness is conducted, through the evaluation of their optimized factors and responses, the selection of their design models, their use of ANalysis Of VAriance (ANOVA), and the determination of their coefficients of determination (R2). Factors such as water/ cement ratio and binder content prevailed in most models, the predominant responses of which were, respectively, compressive strength and workability. Although the use of ANOVA is commonly used to demonstrate the validity of the models, the studies replicating the mix with optimal levels of all factors are necessary to validate the results. On the basis of this review and depending on the responses that need to be maximized or minimized, the application of RSM can clearly be very crucial when quantifying the effects of new raw materials, whether recovered waste or natural resources, on mix behaviour.
