Although serious games are more and more used for learning goals, high-quality empirical studies to prove the effectiveness of serious games are relatively scarce. In this paper, three empirical studies are presented that investigate the effectiveness of serious games as opposed to traditional classroom instruction on learning features as well as learning outcomes. All three studies used a similar longitudinal case-control study design and measured the same set of learning features (control, challenge, feedback, engagement and social interaction). Learning outcomes were measured by self-report and knowledge tests. Results of the three studies show that students that played the serious games scored higher on features associated with high-quality learning. Furthermore, the studies show that serious gaming is more effective on self-reported learning outcomes than traditional classroom instruction. Effects of serious gaming on the knowledge tests were not found. The studies serve as a first step to the development of a generic evaluation framework for serious gaming.