With the development of web-based science inquiry learning, behavioral engagement in such learning contexts received more and more attention. Combined with specific science inquiry stages: comparative experiment design, implementation with computer simulation, and reflection on results, the current study explored a series of features from log data to conceptualize students' behavioral engagement. The features were divided into three categories: general engagement features including time, game the system, submission frequency, and revisiting behavior; learning content related features including context consistency, comparative experimental design, and experiment design consistency; and instruction related features consisting of revision behavior and revision improvement. 220 sixth graders from four classes in China participated in the study. Correlation and regression analysis were used to analyze the relationship between engagement features and learning performance. The results showed that time spend in experimental implementation, gaming the system in experimental design and reflection, the number of trials and materials tried in experimental implementation, comparative experimental design and context consistency, and revision behavior in all stages was significantly correlated with the outcome variables. The regression analysis further indicated that revision behavior in experimental design was the most prominent predictor for the performance outcomes. The three kinds of features and the importance of feedback were further discussed.