Our goal is to answer the question: compared with experimental structures, how useful are predicted models for functional annotation? We assessed the predicted models’ functional utility by comparing the performances of functional characterization methods on predicted and experimental structures. We identified 28 sites in 25 protein targets on which to perform functional assessment.  These 28 sites included nine sites with known ligand binding (holo-sites), nine sites that were expected or suggested by experimental authors to have small molecule binding (apo-sites), and ten sites containing motifs, loops, or key residues with important disease-associated mutations. We evaluated the functional utility of the predictions by comparing their microenvironments to the experimental structures. Overall structural quality correlates with functional utility. However, the best-ranked predictions (global) may not have the best functional quality (local). Our assessment provides the ability to discriminate between predictions with high structural quality.  When assessing ligand-binding sites, most prediction methods have higher performance on apo-sites than holo-sites. Some servers show consistently high performance for certain types of functional sites. Finally, many functional sites are associated with protein-protein interaction. We also analyzed biologically relevant features from the protein assemblies of two targets where the active site spanned the protein-protein interface. For the assembly targets, we found that the features in the models were mainly determined by the choice of template.