Reaching the global minimum cost value without getting stuck in local minima is a challenging task. The contribution of metaheuristic techniques in the last few decades has been significant, providing algorithms capable of finding good approximations of unknown solutions. These approximations are sufficiently accurate and acceptable in engineering applications. In these algorithms, we seek the solution intelligently, considering a specific indicator which is the cost function value of agents at their positions. Swarm intelligence (SI) algorithms, like particle swarm optimization (PSO), ant colony optimization (ACO) and some other algorithms, are bio-inspired metaheuristic methods. Although such algorithms are powerful tools in optimization, they have not been deeply studied from a mean-field perspective, as most studies focus on numerical results and cost reduction. The Consensus-Based Optimization (CBO) was introduced as a novel approach to trace convergence behavior.