This paper introduces a new method for estimating the absolute quality of individual protein structure models, called QMEAN Z-score. The QMEAN Z-score is a normalized score that measures the 'degree of nativeness' of a protein model compared to high-resolution experimental structures. It is calculated by comparing the model's structural features to those of similar-sized experimental structures. The QMEAN Z-score is independent of protein size and can be used to assess both monomers and oligomeric assemblies. The method was validated using a comprehensive analysis of all experimental structures in the PDB, where membrane proteins and thermostable proteins were found to accumulate on opposite sides of the score spectrum. The QMEAN Z-score was also shown to detect experimentally solved protein structures with significant errors and to evaluate theoretical protein models. The results indicate that the QMEAN Z-score is a reliable measure of protein stability and can be used to assess the absolute quality of both experimental and theoretical models. The QMEAN Z-score calculation has been integrated into the QMEAN server, which is available online. The method was tested on a variety of datasets, including the PDB reference set and CASP8 server models, and was shown to perform well in comparison to other scoring functions. The QMEAN Z-score is a valuable tool for assessing the quality of protein models and can be used to identify models with significant errors.This paper introduces a new method for estimating the absolute quality of individual protein structure models, called QMEAN Z-score. The QMEAN Z-score is a normalized score that measures the 'degree of nativeness' of a protein model compared to high-resolution experimental structures. It is calculated by comparing the model's structural features to those of similar-sized experimental structures. The QMEAN Z-score is independent of protein size and can be used to assess both monomers and oligomeric assemblies. The method was validated using a comprehensive analysis of all experimental structures in the PDB, where membrane proteins and thermostable proteins were found to accumulate on opposite sides of the score spectrum. The QMEAN Z-score was also shown to detect experimentally solved protein structures with significant errors and to evaluate theoretical protein models. The results indicate that the QMEAN Z-score is a reliable measure of protein stability and can be used to assess the absolute quality of both experimental and theoretical models. The QMEAN Z-score calculation has been integrated into the QMEAN server, which is available online. The method was tested on a variety of datasets, including the PDB reference set and CASP8 server models, and was shown to perform well in comparison to other scoring functions. The QMEAN Z-score is a valuable tool for assessing the quality of protein models and can be used to identify models with significant errors.