This study aims to examine the impact of reduced in-person learning during COVID-19 on students' academic achievement gaps focusing on rural--urban and in-school disparities. To this end, first, we investigated the regional disparity of student performance between Seoul and Gangwon, representative areas of urban and rural regions in South Korea, using t test analysis. Second, we conducted a regression analysis to analyze how the number of in-school days is associated with the student performance gap by controlling the regions. Our findings from the two analyses can be summarized as follows: First, we observed a difference in patterns between the two regions. In Seoul, student performance was polarized at the two ends of the grade spectrum, whereas in Gangwon Province, achievement declined overall between pre- and post-COVID-19. Second, in the case of Seoul, the proportion of mid-range achievement students decreased after COVID-19, whereas in Gangwon Province, COVID-19 did not have a significant effect on students' B, C, and D grades. Third, regardless of region, more in-person learning was associated with a higher portion of mid-range grades. Based on the findings, we suggested several policy implementations to cope with student performance gaps, which can facilitate the governmental response to nationwide crises that may emerge in the future.