People often perform visual tasks together, for example, when looking for a misplaced key. When performing such tasks jointly, people tend to coordinate their actions to divide the labor, for example, by looking for the misplaced key in different rooms. This way, they tend to perform better together than individually — they attain a group benefit. In this talk, I will present a series of studies, in which we investigated interpersonal coordination in a joint multiple object tracking task. I will address how group benefits can be quantified, whether group benefits are attained or not, how labor divisions come about, and which factors influence group performance.