The importance of the path loss in millimeter wave channel propagation cannot be taken for granted in terms of deployment, design, performance assessment, and planning. The path loss helps to determine the network’s geographic coverage. Although many path loss models, including statistical and empirical models based on measurement and linear regression, have been proposed by various researchers, high fidelity is required to determine the performance of the wireless network’s channel. This research validates the improved version of the well-known close in (CI) and floating intercept (FI) path loss models at frequency bands of 28 and 38 GHz. The measurement surroundings comprised of an enclosed passageway with vertical-horizontal (V-H) and vertical-vertical (V-V) antenna polarizations. One of the key findings of this study is that the enhanced versions of these models typically perform better in terms of consistency than the standard models thereby justifying their high accuracy level. The improved versions of the CI and the FI models demonstrate a significant improvement for various antenna polarizations. The mean prediction error (MPE) and standard deviation error (SDE) also show how precisely and accurately the improved models predict the path loss. Additionally, the improved models provide the reasonable responsiveness and uniformity of the parameters with the change in the antenna polarization and lower the shadow fading’s standard deviation in LOS as well as NLOS situations. The results confirm that the modified versions of CI and FI models predict path loss better in an enclosed environment for 5G networks.