Background: Meningiomas exhibit considerable heterogeneity. We previously identified four distinct molecular groups (immunogenic, NF2-wildtype, hypermetabolic, proliferative) which address much of this heterogeneity. Despite their utility, the stochasticity of clustering methods and the requirement of multi-omics data limits the potential for classifying cases in the clinical setting. Methods: Using an international cohort of 1698 meningiomas, we constructed and validated a machine learning-based molecular classifier using DNA methylation alone. Original and newly-predicted molecular groups were compared using DNA methylation, RNA sequencing, whole exome sequencing, and clinical outcomes. Results: Group-specific outcomes in the validation cohort were nearly identical to those originally described, with median PFS of 7.4 (4.9-Inf) years in hypermetabolic tumors and 2.5 (2.3-5.3) years in proliferative tumors (not reached in the other groups). Predicted NF2-wildtype cases had no NF2 mutations, and 51.4% had others mutations previously described in this group. RNA pathway analysis revealed upregulation of immune-related pathways in the immunogenic group, metabolic pathways in the hypermetabolic group and cell-cycle programs in the proliferative group. Bulk deconvolution similarly revealed enrichment of macrophages in immunogenic tumours and neoplastic cells in hypermetabolic/proliferative tumours. Conclusions: Our DNA methylation-based classifier faithfully recapitulates the biology and outcomes of the original molecular groups allowing for their widespread clinical implementation.