Abstract: Natural deep eutectic solvents (NADES) are mixtures of naturally derived compounds with a significantly decreased melting point due to the specific interactions among the constituents. NADES have benign properties (low volatility, flammability, toxicity, cost) and tailorable physicochemical properties (by altering the type and molar ratio of constituents), hence they are often considered as a green alternative to common organic solvents. Modeling the relation between their composition and properties is crucial though, both for understanding and predicting their behavior. Several efforts were done to this end, yet this review aims at structuring the present knowledge as an outline for future research. First, we reviewed the key properties of NADES and relate them to their structure based on the available experimental data. Second, we reviewed available modeling methods applicable to NADES. At the molecular level, density functional theory and molecular dynamics allow interpreting density differences and vibrational spectra, and computation of interaction energies. Additionally, properties at the level of the bulk media can be explained and predicted by semi-empirical methods based on ab initio methods (COSMO-RS) and equation of state models (PC-SAFT). Finally, methods based on large datasets are discussed; models based on group contribution methods and machine learning. A combination of bulk media and dataset modeling allows qualitative prediction and interpretation of phase equilibria properties on the one hand, and quantitative prediction of melting point, density, viscosity, surface tension and refractive indices on the other hand. In our view, multiscale modeling, combining the molecular and macroscale methods, will strongly enhance the predictability of NADES properties and their interaction with solutes, yielding truly tailorable solvents to accommodate (bio)chemical reactions.