There is a long history of research efforts aimed at understanding the relationship between homework activity and academic achievement. While some self-report inventories involving homework activity have been useful for predicting academic performance, self-reported measures may be limited or even problematic. Here, we employ a novel method for accurately measuring students' homework activity using smartpen technology. Three cohorts of engineering students in an undergraduate statics course used smartpens to complete their homework problems, thus producing records of their work in the form of timestamped digitized pen strokes. Consistent with the time-on-task hypothesis, there was a strong and consistent positive correlation between course grade and time doing homework as measured by smartpen technology (r = 0.44), but not between course grade and self-reported time doing homework (r = -0.16). Consistent with an updated version of the time-on-task hypothesis, there was a strong correlation between measures of the quality of time spent on homework problems (such as the proportion of ink produced for homework within 24 hr of the deadline) and course grade (r = -0.32), and between writing activity (such as the total number of pen strokes on homework) and course grade (r = 0.49). Overall, smartpen technology allowed a fine-grained test of the idea that productive use of homework time is related to course grade.