Collective intelligence–the ability of groups to solve diverse problems–has been explored using laboratory experiments, computer simulations, and questionnaires. These instruments, however, suffer from limitations, such as external validity in the case of laboratory experiments and self-reporting bias in the case of questionnaires. Here we investigate the exploration-exploitation dynamics of small teams using high-frequency, observational data from escape rooms: a non-interventional yet controlled environment where naturally occurring teams solve exploration and exploitation tasks. We find that more effective teams tend to coordinate throughout problem-solving, exhibit balanced communication patterns, and are more responsive, addressing tasks promptly as they become solvable rather than accumulating them. In contrast, members of less effective teams often work in isolation, participate in problem-solving unequally, and tend to accumulate tasks rather than addressing them as they become solvable. Importantly, we show that no single collaborative structure works for every task: exploitation is faster under team-wide communication and may even benefit from the dominance of key members, while efficient exploration aligns with balanced participation. Additionally, positive exchanges are associated with faster exploitation but slower exploration. These findings expand the external validity of experimental work on collective intelligence to an organic non-interventional setting and highlight the importance of understanding team performance through behavior instead of team demographics.