Abstract Understanding differences between substellar spectral data and models has proven to be a major challenge, especially for self-consistent model grids that are necessary for a thorough investigation of brown dwarf atmospheres. Using the random forest supervised machine-learning method, we study the information content of 14 previously published model grids of brown dwarfs (from 1997 to 2021). The random forest method allows us to analyze the predictive power of these model grids, as well as interpret data within the framework of Approximate Bayesian Computation. Our curated data set includes three benchmark brown dwarfs (Gl 570D, ϵ Indi Ba, and Bb) as well as a sample of 19 L and T dwarfs; this sample was previously analyzed by Lueber et al. using traditional Bayesian methods (nested sampling). We find that the effective temperature of a brown dwarf can be robustly predicted independent of the model grid chosen for the interpretation. However, inference of the surface gravity is model-dependent. Specifically, the BT-Settl, Sonora Bobcat, and Sonora Cholla model grids tend to predict log g ∼ 3 –4 (cgs units) even after data blueward of 1.2 μm have been disregarded to mitigate for our incomplete knowledge of the shapes of alkali lines. Two major, longstanding challenges associated with understanding the influence of clouds in brown dwarf atmospheres remain: our inability to model them from first principles and also to robustly validate these models.