<p>In this study, an enhanced version of the recently developed Zebra Optimization Algorithm (ZOA) is introduced, which takes inspiration from the foraging and defensive behaviors of zebras. ZOA is an efficient metaheuristic algorithm that has been used to solve various complex optimization problems. However, there is potential for further enhancement in preventing premature convergence, addressing local optima stagnation, and improving solution quality. To address these issues, two key strategies are integrated into the Enhanced Zebra Optimization Algorithm (EZOA): Levy flight and lens opposition-based learning. The Levy flight strategy promotes effective exploration in the initial foraging stage, thus preventing premature convergence to sub-optimal solutions. Next, the lens opposition-based learning strategy is introduced to improve diversity and ensure convergence towards higher-quality solutions. The proposed approach is evaluated on three test cases of optimization problems, including twenty-three classical benchmark functions, a set of CEC-2019 functions, four mixed-integer reliability optimization benchmark problems, and four constrained engineering design optimization problems. The results of EZOA are compared against several well-performing metaheuristic algorithms from the literature, along with some champion algorithms of IEEE CEC competitions. Additionally, Friedman’s rank, Wilcoxon signed-rank test, and Mann–Whitney <i>U</i> test are employed to analyze the simulation results, providing statistical validation of the robustness and significance of the proposed EZOA, which ranks first across all test cases. Furthermore, a comprehensive evaluation of time complexity, along with boxplot and convergence analysis, conducted provides insights into the effectiveness and stability of EZOA.</p>