Optimization is a process of making the system adjusting some characteristic to make it work effectively under some constraints or conditions. It is a field of research which is getting attention in many real-world problems. Optimization algorithms play an important role in the different areas, and they should find the good solution for given problems by minimizing or maximize the one or more objective function. For each optimization problems there are set of possible solutions called solution space (Neumüller, Wagner, Kronberger, & Affenzeller, 2012). The achievable solution founded by the algorithm may consider as a global optimum solution if it is the only better solution among other solutions. Computing global optimal solution for the large-space optimization problem is complex ;since, optimization problems appear in different fields including engineering, manufacture and the economic system there is a huge requirement for an efficient algorithm which could solve the high dimensional problem successfully (Baghel, Agrawal, & Silakari, 2012).High dimensional optimization problem considers being one of the challenges facing the optimization algorithm for obtaining an optimal solution. It has two main aspects one is that algorithm face difficulty to avoiding trap into local optimum, and the other is that the search space growing extensively ( Neumüller et al., 2012; Singh & Jana, 2017) which make a challenge to the algorithm to explore the search space in a suitable way. Although, optimization methods have been applied in the various large-scale space problems including designing large-scale electronic systems, scheduling problems with a large number of resources, and vehicle routing in large-scale traffic networks the need of efficient solution for these problem is highly required (Mahdavi, Shiri, & Rahnamayan, 2015) . With the advantages of technology, rapid evolution and increase of data among various fields the need to test an existing algorithm to find the suitable method that handle high dimensional optimization effectively is crucial. The main focus of this paper is to analyze, test and compare in detail two algorithms particle swarm optimization(PSO) and cuckoo search(CS) in terms of accuracy and runtime performance. Standard benchmark functions with up 150 parameters are used; additionally, all tests and analyzes are doing by MATLAB. The rest of this paper is organized as follows: Section II gives literature review about optimization methods. Section III shows an overview of (PSO)and (CS). Problem formulation and the standard function using in experiments are in section IV, while the results and conclusion are presented in section V and VI respectively. Global optimization methods can be classified into two types: deterministic and probabilistic (Weise,2009). Deterministic algorithm dealing with the problem by making a clear assumption of it, and explore the search in an efficient way to achieve a fixed solution within a finite amount of time.(Weise, 2009) . These algorithms could not use in such problems that have large search area such as high dimensional optimization problem. Due to time constraint, theses algorithm could not explore the large search space effectively (Nyarko & Cupec, 2014). This situation becomes more difficult especially in detecting the search space; however, metaheuristic algorithms show advanced in these issues (Yang,2013). Metaheuristic algorithms are taken its essences from nature, and they have been used commonly. These algorithms have two characteristics exploration and exploitation(Rajakumar, Dhavachelvan, & Vengattaraman, 2016; X. Yang, 2010) Exploration is seeking the search area while exploiting is utilization these searching information to check that the good solution within this area. These two characteristics help the metaheuristic to avoid the local optimum, and expand the search areas successfully. Consequently, metaheuristic algorithm within these features has good chance to achieve the global optimum solution(Berhad, 2014). Metaheuristic algorithms have been applied in many fields including computer science, Artificial Intelligence, machine learning and data mining(X. Yang et al., 2014).These algorithms show advanced in high dimensional optimization problem (Singh & Jana, 2017)by creating random solutions irritated for many times to able reaching to the good or optimal solution until stopped by some criteria such as elapsed time and number of irritation. Although, the metaheuristic algorithms share the same concept about taking their idea from the nature they have different source of inspiration. For example, genetic algorithms (GA) and differential evolution(DE) are bio-inspired while particle swarm optimization (PSO), Ant Colony Optimization (ACO) and cuckoo search (CS) are swarm intelligence ( Yang, 2014) .These algorithms have been well studied to resolve this problem global optimization for high dimensional problem (Abiyev & Tunay, 2015; Mahdavi et al., 2015; Singh & Jana, 2017) ,but these algorithms requiring comparison for choosing one algorithm over the others to handle the desired problem .In this paper our study will focus on swarm intelligence algorithms.x