<p>Travertine is a chemical sedimentary rock widely used as a building stone in many regions of the world. Uniaxial compressive strength (UCS) is one of the key technical criteria in assessing the quality of a building stone. For a preliminary assessment of stone quality based on UCS, indirect methods, including regression analysis and soft computing approaches, can serve as fast and inexpensive tools. Due to the porous nature of travertine, it exhibits highly variable UCS behavior, which affects the performance of regression analysis and soft computing approaches in assessing the UCS of travertines. In the present study, based on a comprehensive literature review of the previous studies, UCS, density (ρ), porosity (n), and P-wave velocity (Vp) of the travertines were collected. Data of the UCS were categorized into three groups, namely all data, UCS &lt; 40 MPa, and UCS &gt; 40 MPa. The UCS was assessed using regression analysis and soft computing approaches based on the ρ, n, and Vp. The performance of regression analysis and soft computing approaches was examined through the statistical indicators of the coefficient of correlation (R), root mean squared error (RMSE), variance accounted for (VAF), mean absolute percentage error (MAPE), and performance index (PI), and fivefold cross-validation. Comparing the values ​​of statistical indicators shows that soft computing approaches have higher performance than regression analysis in assessing the UCS. Also, it was found that regression analysis and soft computing approaches have a better performance for travertines with UCS &gt; 40 MPa, followed by all data and UCS &lt; 40 MPa, respectively. Finally, the findings indicated that due to the highly heterogeneous nature of travertine in terms of its porous media, a performance loss in the regression analysis and some soft computing approaches for assessing the UCS of travertines were observed compared to compact building stones such as limestone, granite, and marble.</p>