Objectives: To test the hypotheses that mechanobehavior scores (MBS) were correlated with mandibular ramus lengths (Co-Go) and differed between facial phenotypes. Materials and Methods: Subjects gave informed consent to participate. Co-Go (mm), mandibular plane angles (SN-GoGn, °), and three-dimensional anatomy were derived from cephalometric radiography or cone beam computed tomography. Temporomandibular joint (TMJ) energy densities (ED) (mJ/mm3) were measured using dynamic stereometry and duty factors (DF) (%) were measured from electromyography, to calculate MBS (= ED2 3 DF, (mmmJ3)2%) for each TMJ. Polynomial regressions, K-means cluster analysis, and analysis of variance (ANOVA) with Tukey post-hoc tests were employed. Results: Fifty females and 23 males produced replete data. Polynomial regressions showed MBS were correlated with Co-Go (females, R2 = 0.57; males, R2 = 0.81). Cluster analysis identified three groups (P<.001). Dolichofacial subjects, with shorter normalized Co-Go, clustered into two subgroups with low and high MBS compared to brachyfacial subjects with longer Co-Go. SN-GoGn was significantly larger (P<.03) in the dolichofacial subgroups combined (33.0 ± 5.98) compared to the brachyfacial group (29.8 ± 5.58). Conclusions: MBS correlated with Co-Go within sexes and differed significantly between brachyfacial and dolichofacial subjects.