A task-based search system is described. The computing system can receive, from a user device, a first user query associated with a task. The system can determine, using one or more machine-learned models, a first subtask having a first interaction score and a second subtask having a second user interaction score. Additionally, the system can perform a first query search for the first subtask to obtain a first content item associated with the first subtask. Moreover, the system can perform a second query search for the second subtask to obtain a second content item associated with the second subtask. Furthermore, the system can cause a presentation, on a display of the user device, of the first content item and the second content item. The first content item can be displayed above the second content item based on the first user interaction score being higher than the second user interaction score.