The purpose of this study was to investigate the relationships between students’ different extent of completion of modeling activity and the students’ modeling competences and learning engagement. Research participants were 76 11-th grade students in Taiwan. The students participated in modeling-based computer simulation activities (MBCSA). We designed and learning patterns was analyzed through lag sequential analysis (LSA). Research instruments included pre- and post-modeling competence tests, engagement questionnaires, and online students’ worksheets. Students’ activity logs were also recorded by the computers. The students’ online worksheets were scored and used for grouping the students into three levels of completion of MBCSA: the Low-Score Group (LSG), Middle-Score Group (MSG) and High-Score Group (HSG). The results showed that, first, in analyzing the students’ pre- and post-modeling competences test, ANCOVA results showed HSG and MSG were significantly higher than LSG on model representation (MR). Second, in analyzing the engagement questionnaires, ANOVA results showed HSG was significantly higher than MSG on positive behavioral engagement and positive social engagement, and LSG was significantly higher than HSG on negative cognitive engagement, negative behavioral engagement and negative social engagement. Third, by using the LSA, six activity patterns were identified in this study. Students in the three groups showed different tendencies of the sequences of completing the modeling activities.