The aim of this study was to test for dimensional variations between plaster models recorded with alginate impression and printed 3D physical replicas from an .stl file digitized with an intra-oral scanner. Eighty arches (maxillary and mandibular) from 40 different patients were analyzed. Classic alginate impressions and digital recordings with an intraoral scanner were taken on the same day, for both arches of each patient. Digital recordings were then printed into resin models. The linear intercanine (IC) and intermolar (IM) distances were measured with a manual electronic caliper and then compared. The measurements were repeated twice for each distance to verify repeatability with the intraclass correlation coefficient (ICC). The Student’s t test for paired data was used to compare the two sets of impressions. The repeatability of the measures was assessed as ICC values were higher than 0.98. The values of the IC and IM lengths showed a statistically significant difference, but not clinically significant as it was less than 0.1 mm, between the two techniques.