Sound levels from occupied classrooms have been gathered from 220 classrooms across four grade levels (3, 5, 8 and 11) over six school days each and processed with k-means clustering into speech and non-speech clusters. Three metrics describing the classroom acoustics, including the average daily A-weighted equivalent level for non-speech, the average daily difference between the A-weighted equivalent levels for speech and non-speech (a signal to noise ratio), and the mid-frequency averaged reverberation time, were analyzed against classroom-aggregated standardized reading and math achievement test scores, while controlling for classroom demographics including socioeconomic status. Interactions between the metrics and demographics were also tested. A statistically significant relationship was found between the average daily non-speech levels in classrooms and math test scores; higher daily non-speech levels were correlated with lower math test scores ($p<0.05$). No statistically significant main effects of acoustic metrics were found on reading achievement. There were some significant differences and an interaction found between grades, but these may be due to uneven sample distributions as there were fewer grade 8 and 11 classrooms measured. Children learn in occupied classrooms, and the findings from this investigation based on data from occupied conditions suggest that designing for lower unoccupied sound levels can lead to occupied environments that are conducive to better student learning outcomes.