Reviews and meta-analyses have proved to be fundamental to establish neuroscientific theories on intelligence. The prediction of intelligence using invivo neuroimaging data and machine learning has become a widely accepted and replicated result. We present a systematic review of this growing area of research, based on studies that employ structural, functional, and/or diffusion MRI to predict intelligence in cognitively normal subjects using machine learning. We systematically assessed methodological and reporting quality using the PROBAST and TRIPOD in 37 studies. We observed that fMRI is the most employed modality, resting-state functional connectivity is the most studied predictor. A meta-analysis revealed a significant difference between the performance obtained in the prediction of general and fluid intelligence from fMRI data, confirming that the quality of measurement moderates this association. Studies predicting general intelligence from Human Connectome Project fMRI averaged r = 0.42 (CI95% = [0.35, 0.50]) while studies predicting fluid intelligence averaged r = 0.15 (CI95% = [0.13, 0.17]). We identified virtues and pitfalls in the methods for the assessment of intelligence and machine learning. The lack of treatment of confounder variables and small sample sizes were two common occurrences in the literature which increased risk of bias. Reporting quality was fair across studies, although reporting of results and discussion could be vastly improved. We conclude that the current literature on the prediction of intelligence from neuroimaging data is reaching maturity. Performance has been reliably demonstrated, although extending findings to new populations is imperative. Current results could be used by future works to foment new theories on the biological basis of intelligence differences.