Abstract: To improve the loading rate of two-dimensional variable-sized bin packing problem, the tabu search whale optimization algorithm (TSWOA) and improved best-fit algorithm (IBF) are proposed. Tabu search strategy was used to help the whale optimization algorithm jump out of the local optimal solution during the search process of the algorithm. Best-fit algorithm was improved based on the principle of minimum drop to reduce the generation of wasted space when placing the items. The results show that the TSWOA-IBF algorithm has higher solution accuracy compared with algorithms in existing literature and has better convergence than genetic algorithm, gray wolf optimization algorithm and whale optimization algorithm. TSWOA-IBF algorithm can effectively solve two-dimensional variable-sized bin packing problem.