With the help of Visual Learning Analytics (VLA) tools, teachers can construct meaningful groups of students that can, for example, collaborate and be engaged in productive discussions. However, finding similar samples in large educational databases requires effective similarity measures that capture the teacher’s intent. In this paper we propose a web-based VLA tool called Similarity-Based Grouping (SBGTool), to assist teachers in categorizing students into different groups based on their similar learning outcomes and activities. By using SBGTool, teachers may compare individual students by considering the number of answers (correct and incorrect) in different question categories and time ranges, find the most difficult question categories considering the percentage of similarity to the correct answers, determine the degree of similarity and dissimilarity across students, and find the relationship between students’ activity and success. To demonstrate the tool’s efficacy, we used 10,000 random samples from the EdNet dataset, a large-scale hierarchical educational dataset consisting of student-system interactions from multiple platforms, at university level, collected over a period of two years. The results point to the conclusion that the tool is efficient, can be adapted to different learning domains, and has the potential to assist teachers in maximizing the collaborative learning potential in their classrooms.