Abstarct: Drillability is one of the most critical parameters in drilling oil and gas wells, significantly influencing bit selection. Choosing an appropriate drill bit can lead to reduced drilling time and increased efficiency. Since the drillability of rocks depends on numerous parameters that are intricately interrelated, achieving a comprehensive method to evaluate and assess rock drillability has been a key objective for drilling researchers. In the present study, inspired by previous methods and studies, efforts were made to predict the bit penetration rate in various formations by collecting, preparing, and constructing a suitable databaxse. Subsequently, the drillability of formations, which reflects the impact of geomechanical parameters on rocks, was analyzed. The analyses revealed that some parameters positively enhance drillability, while others negatively affect it. In this study, a one-dimensional geomechanical model was developed for six wellbores in the South Azadegan Field. Geomechanical parameters, as well as petrophysical and operational data, were utilized to analyze their impact on the bit penetration rate. Bivariate linear regression methods were employed to evaluate the relationship between these characteristics and the drilling penetration rate. Furthermore, multiple linear regression was applied to the selected parameters, yielding appropriate correlations between independent variables and the dependent parameter (bit penetration rate) in different formations. Due to insufficient and unreliable data, multiple linear regression could not be performed for the Aghajari, Gachsaran, Asmari, Pabdeh, Jahrum, and Fahliyan formations. Additionally, due to the limited thickness of the Laffan formation, it was preferred to analyze it in conjunction with the Ilam formation. For validation, the regression analysis results were compared with the actual penetration rates of the wells, yielding acceptable outcomes. Moreover, the bit penetration rate for the Gurpi to Kazhdumi formations was estimated using multivariate nonlinear regression via SPSS software and validated in wells 86 and 103. This approach resulted in significant correlations between bit penetration rates and independent parameters for the Gurpi, Ilam/Laffan, Sarvak, Kazhdumi, and Dariyan formations. The estimated penetration rate was plotted against the measured penetration rate for the aforementioned wells, with favorable results. Nonlinear regression results for the Aghajari, Gachsaran, Asmari, Pabdeh, Jahrum, Gadvan, and Fahliyan formations were not satisfactory due to limited and unreliable data. In addition to regression methods, the penetration rate was also predicted using the multilxayer perceptron neural network method for various formations. This method yielded acceptable results for the Laffan, Sarvak, Kazhdumi, and Dariyan formations. Among the applied methods for estimating bit penetration rates, the multilxayer perceptron neural network performed better for the Sarvak and Kazhdumi formations, while the multiple linear regression method was more suitable for the Ilam/Laffan formations. Meanwhile, multivariate nonlinear regression showed better performance for the Dariyan formation. However, this method lacked efficiency for other formations due to data limitations and drilling challenges. For instance, the Jahrum formation was absent in certain wells due to geological factors and experienced complete fluid loss in others. This research demonstrated that geomechanical parameters such as compressive strength, Young's modulus, density, internal friction angle, and porosity play essential roles in determining drillability. These parameters influence the hardness, brittleness, and stability of formations, directly affecting bit selection, weight on bit, rotational speed, and drilling fluid type. For instance, rocks with high compressive strength and density usually require stronger equipment and higher force, resulting in lower penetration rates. Conversely, rocks with lower density and strength drill faster but have higher instability risks. Optimizing drilling operations requires an accurate understanding of these parameters and adapting equipment and drilling conditions accordingly. The models developed in this study can be employed during drilling operations to prevent penetration rate reductions, optimize drilling processes, enhance efficiency, and reduce operational costs. Keywords: Rock Drillability, One-Dimensional Geomechanical Modeling, Penetration Rate, Rock Geomechanical Properties, Linear Regression, Nonlinear Regression, Neural Networks