Nutritional issues in toddlers are a crucial issue that significantly impacts the health and development of children in Indonesia. Malnutrition can lead to various long-term health problems. Therefore, detecting and classifying the nutritional status of toddlers is very important. This study aims to analyze and compare boosting techniques to classify the nutritional status of toddlers, focusing on three boosting techniques: AdaBoost, Gradient Boosting, and XGBoost. This is done because boosting techniques work by sequentially building models, where each new model attempts to correct the prediction errors of the previous model. The results show that the XGBoost model provides the best performance with a precision of 0.9849, recall of 0.9848, accuracy of 0.9848, F1 score of 0.9848, and ROC-AUC of 0.9994 at an 80:20 data split ratio. Conversely, the AdaBoost model shows the lowest results with a precision of 0.6294, recall of 0.6292, accuracy of 0.6292, F1 score of 0.6291, and ROC-AUC of 0.7581 at a 90:10 data split ratio, caused by its sensitivity to outliers and noise in the data. These findings indicate that XGBoost is the best boosting model for classifying the nutritional status of toddlers, followed by Gradient Boosting, with AdaBoost in the last position. The outstanding performance of XGBoost is due to the use of regularization techniques, effective handling of missing values, and efficient and fast boosting algorithms through parallel processing techniques.