The Nanling belt in South China has considerable resources of tungsten polymetallic commodities and is one of the most important metallogenic belts in the world. Data-driven weights-of-evidence(WofE) and fuzzy logic models are used to evaluate the tungsten polymetallic potential of the Nanling belt. Initially, seven ore-controlling factors derived from multi-source geospatial datasets(e.g., geological, geochemical, and geophysical) are used for data integration in the two models. Two mineral potential maps are generated that efficiently predicate the locations of the deposits. The WofE map predicate 81% of the deposits within 13.6% of the study area, whereas the fuzzy logic map predicate 81.5% of the deposits within 13% of the area. The predictive maps are syntheses of spatial association rules, which provide better understanding of those factors that control the distribution of mineralization and trigger eventual exploration work in new areas. Subsequently, in order to evaluate the success rate accuracy, the receiver operating characteristic curves and area under the curves(AUCs) for the two potential maps are constructed. The results show that the AUCs for the WofE and fuzzy logic models are 0.775 7 and 0.840 6, respectively. The higher AUC value for the fuzzy logic model implies that it delineate a greater number of favorable areas compared with the WofE model. Overall, the capabilities of both models for correctly classifying areas with existing mineral deposits are satisfactory. The Nanling belt in South China has been resources of tungsten polymetallic commodities and is one of the most important metallogenic belts in the world. Data-driven weights-of-evidence (WofE) and fuzzy logic models are used to evaluate the tungsten polymetallic potential of the Nanling belt. Initially, seven ore-controlling factors derived from multi-source geospatial datasets (eg, geological, geochemical, and geophysical) are used for data integration in the two models. Two mineral potential maps are generated that efficiently predicate the locations of the deposits. The WofE map predicate 81% of the deposits within 13.6% of the study area, while the fuzzy logic map predicate 81.5% of the deposits within 13% of the area. The predictive maps are syntheses of spatial association rules, where provide better understanding of those factors that control the distribution of mineralization and trigger eventual exploration work in new areas. ccess rate accuracy, the receiver operating characteristic curves and area under the curves (AUCs) for the two potential maps are constructed. The results show that the AUCs for the WofE and fuzzy logic models are 0.775 7 and 0.840 6, respectively. The higher AUC value for the fuzzy logic model implies that it delineate a greater number of favorable areas than with the WofE model. Overall, the capabilities of both models for correctly classifying areas with existing mineral deposits are satisfactory.