Abstract | The reliable estimation of the seismic performance of structures requires quantifying the effect of aleatory and epistemic uncertainties of the system parameters. This is efficiently achieved for a case study of a steel moment-resisting frame through several important advances. First, a state-of-the-art numerical model is formed with full parameterization of its strength properties. Empirical relationships derived from experimental data are used to model the cyclic behavior of  steel sections using probabilistically distributed parameters that include intra- and inter-member correlation. Incremental dynamic analysis is employed to accurately assess the seismic performance of the model. Finally, an efficient Monte Carlo simulation algorithm is used, based on record-wise incremental Latin Hypercube Sampling to propagate the uncertainties from the numerous parameters to the actual system demand and capacity. Consequently, this modern steel frame is shown to be only mildly sensitive to parameter uncertainties when quality is tightly controlled.