Learning weariness is a common issue among adolescents in China. However, little is known about its developmental stability and changes over time. This study involved 1,857 participants (52.6% girls) who were assessed at two time points, approximately six months apart. Latent profile analysis was conducted to identify subgroups of learning weariness, and latent transition analysis was then used to examine the transition probabilities between these subgroups. Logistic regression analyses examined associations between the identified classes and related factors. Three distinct subgroups of learning weariness were identified: low learning weariness group, transition group, and high learning weariness group. The transition group showed the highest stability (53.9%). Both the low and high learning weariness groups tend to shift toward the transition group, with shift probabilities of 39.8% and 38.2%, respectively. Poorer family functioning increased the likelihood of shifting from low to transition group, while positive classmate relationships served as a protective factor against learning weariness.