Mesophyll conductance ( g m ) describes the efficiency with which CO 2 moves from substomatal cavities to chloroplasts. Despite the stipulated importance of leaf architecture in affecting g m , there remains a considerable ambiguity about how and whether anatomy influences g m . This is, in part, because studies exploring the relationship between leaf architecture and g m have often relied on simple linear or exponential models to identify correlations. Here, we employed non-linear machine learning models to more comprehensively assess the relationship between ten leaf architecture traits and g m . These models achieved excellent predictability of g m , which depended on the leaf architecture traits considered as predictors. Dissection of the importance of leaf architecture traits in the models indicated that cell wall thickness and chloroplast area exposed to internal airspace have a large impact on interspecific variation in g m . Additionally, other leaf architecture traits, such as: leaf thickness, leaf density, and chloroplast thickness emerged as important predictors of g m . We found significant differences in the predictability between models trained on different plant functional types (PFTs): those trained on woody species could predict g m by anatomical traits on other woody PFTs, ferns, and C 3 herbaceous plants, whereas the converse did not hold in general. By moving beyond simple linear and exponential models, our analyses demonstrated that a larger suite of leaf architecture traits drive differences in g m than has been previously acknowledged. These findings pave the way for modulating g m by strategies that modify its leaf architecture determinants.