High-performance concrete is defined as concrete that meets special combinations of performance and uniformity requirements that cannot always be achieved routinely using conventional constituents and normal mixing, placing, and curing practices. A large number of trial mixes are required to select the desired combination of materials that meets special performance. Therefore, in this paper, using Harmony Search (HS) meta-heuristic algorithms optimization method imitating the music improvisation process where musicians improvise their instruments' pitches searching for a perfect state of harmony. There are three type of Harmony search (Local (LHS), Improved (IHS) and Global (GHS) which were successfully used in different branches of engineering. So, these algorithms are used to predict the quantity of contents of the mixes at different known compressive strength and slump. The results of this research show that, Harmony Search Algorithms is an effective method in prediction of concrete mixes, while comparing the results of the three types of Harmony Search algorithms, it was be found that GHS results is better than IHS better than LHS whither according to min. cost or min. average error.