Aurora kinases (AURKs) have been identified as promising biological targets for the treatment of cancer. In this study, molecular dynamics simulations were employed to investigate the binding selectivity of three inhibitors (HPM, MPY, and VX6) towards AURKA and AURKB by predicting their binding free energies. The results show that the inhibitors HPM, MPY, and VX6 have more favorable interactions with AURKB as compared to AURKA. The binding energy decomposition analysis revealed that four common residue pairs (L139, L83), (V147, V91), (L210, L154), and (L263, L207) showed significant binding energies with HPM, MPY, and VX6, hence responsible for the binding selectivity of AURKA and AURKB to the inhibitors. The MD trajectory analysis also revealed that the inhibitors affect the dynamic flexibility of protein structure, which is also responsible for the partial selectivity of HPM, MPY, and VX6 towards AURKA and AURKB. As expected, this study provides useful insights for the design of potential inhibitors with high selectivity for AURKA and AURKB.