This paper investigates the application of artificial intelligence methods to evaluate the construction history of a three-dimensional model, with a focus on online education and skill assessment. The study examines the input data required for analyzing the modeling workflow and identifies key operations indicative of construction method quality. A textual description of the modeling process is incorporated as an additional evaluation criterion. The paper also outlines the preprocessing of textual data for AI-based analysis. For the experimental validation, three approaches were implemented: linear regression, random forest, and neural networks. The hybrid combination of linear regression and neural networks yielded the highest accuracy. The results demonstrate the feasibility of employing these techniques for assessing the procedural logic of 3D model construction.