In this thesis, we review past studies of consensus-based optimization (CBO) and compare its performance with four other nature-inspired metaheuristics: GA, PSO, ACO, and SA. Consensus-based optimization is a relatively simple algorithm but shows superior performance, successfully optimizing complex test functions. Moreover, CBO allows for theoretical validation of its success in continuous optimization, as indicated in past literatures. To be specific, past studies proved that CBO without noise eventually arrives at a consensus but not necessarily at a global optimum. CBO with isotropic noise has been studied using the classical mean-field theory, which was successful only for constrained problems. Finally, studies proved the convergence of CBO with component-wise noise using a direct, unconventional method. Keywords: Consensus-based optimization, Nature-inspired metaheuristic, Swarm-intelligence, Optimization