Glioblastoma is the most common intracranial malignancy and constitutes about 50 % of all gliomas. Both inter-tumor and intra-tumor histological heterogeneity had been recognized by the early 1980-ies. Recent works using novel molecular platforms provided molecular definitions of these tumors. Based on comprehensive genomic sequence analyses, The Cancer Genome Atlas Research Network (TCGA) cataloged somatic mutations and recurrent copy number alterations in glioblastoma. Robust transcriptome and epigenome studies also revealed inter-tumor heterogeneity. Integration and cluster analyses of multi-dimensional genomic data lead to a new classification of glioblastoma tumors into subtypes with distinct biological features and clinical correlates. However, multiple observations also revealed tumor area-specific patterns of genomic imbalance. In addition, genetic alterations have been identified that were common to all areas analyzed and other alterations that were area specific. Analyses of intra-tumor transcriptome variations revealed that in more than half of the examined cases, fragments from the same tumor mass could be classified into at least two different glioblastoma molecular subgroups. Intra-tumor heterogeneity of molecular genetic profiles in glioblastoma may explain the difficulties encountered in the validation of oncologic biomarkers, and contribute to a biased selection of patients for single target therapies, treatment failure or drug resistance. In this paper, we summarize the currently available literature concerning inter- and intra-tumor molecular heterogeneity of glioblastomas, and call attention to the importance of this topic in relation to the growing efforts in routine molecular diagnostics and personalized therapy.