The study investigated opportunities for improved geometallurgical practices at the Jerritt Canyon Smith gold deposit. The sequential Gaussian simulation (SGS) method was used to characterize the geological variability within the deposit domains. Sensor-based bulk ore sorting was introduced as the enabling technology that can classify mined materials based on their geometallurgical properties in real time. The impact of the simulation-based modelling and bulk ore sorting was evaluated in terms of metallurgical results and mine economics. Compared to the ordinary Kriging interpolation approach, the SGS simulation method more accurately captured the grade variability allowing improved understanding of the orebody geometallurgy. For different domains of the Smith deposit, the metallurgy and economic benefits of bulk ore sorting vary, representing different geometallurgical classification potentials across the deposit. High-resolution sortability mapping was established to guide the geometallurgical classification of the mined material. In conclusion, the study demonstrated the integration of simulation-based modelling and sensor-based bulk ore sorting for improved geometallurgical practices.