<p>Determination of the constitutive model and its parameters is essential to the design, stability analysis, and safety construction of geotechnical engineering. Due to the complexity of geomaterials and the variability of geological conditions, uncertainty significantly affects the accurate determination of constitutive models and parameters, posing potential risks to geotechnical engineering safety. This study developed an uncertainty quantification (UQ) framework to address uncertainty by combining Bayesian theory and laboratory tests. A laboratory test was used to characterize the mechanical behavior and failure mechanism of geomaterials and generate data. Bayesian theory was adopted to describe the uncertainty of constitutive model parameters based on Markov Chain Monte Carlo (MCMC) and test data. The developed framework was validated by a synthetic example based on the HS model of soil. The results show that the developed framework effectively characterizes and quantifies uncertainty, which is an inherent property of geomaterials. Then, the developed framework was further validated and demonstrated by an actual soil triaxial compression test. The results proved that uncertainty is essential for characterizing the geomaterial’s mechanical behavior, and the developed framework provides a scientific and feasible approach to quantify uncertainty. The developed framework provides a scientific, reasonable, and promising tool to quantify the uncertainty of the constitutive model and its parameters for geomaterials.</p>