Inputs to various applications and models, current global land cover (GLC) maps are based on different data sources and methods. Therefore, comparing GLC maps is challenging. Statistical comparison of GLC maps is further complicated by the lack of a reference dataset that is suitable for validating multiple maps. This study utilizes the existing Globcover-2005 reference dataset to compare thematic accuracies of three GLC maps for the year 2005 (Globcover, LC-CCI and MODIS). We translated and reinterpreted the LCCS (land cover classification system) classifier information of the reference dataset into the different map legends. The three maps were evaluated for a variety of applications, i.e., general circulation models, dynamic global vegetation models, agriculture assessments, carbon estimation and biodiversity assessments, using weighted accuracy assessment. Based on the impact of land cover confusions on the overall weighted accuracy of the GLC maps, we identified map improvement priorities. Overall accuracies were 70.8 ± 1.4%, 71.4 ± 1.3%, and 61.3 ± 1.5% for LC-CCI, MODIS, and Globcover, respectively. Weighted accuracy assessments produced increased overall accuracies (80–93%) since not all class confusion errors are important for specific applications. As a common denominator for all applications, the classes mixed trees, shrubs, grasses, and cropland were identified as improvement priorities. The results demonstrate the necessity of accounting for dissimilarities in the importance of map classification errors for different user application. To determine the fitness of use of GLC maps, accuracy of GLC maps should be assessed per application; there is no single-figure accuracy estimate expressing map fitness for all purposes.