Flood Early Warning Systems (FEWSs) using Machine Learning (ML) has gained worldwide popularity. However, determining the most efficient ML technique is still a bottleneck. We assessed FEWSs with three river states, No-alert, Pre-alert, and Alert for flooding, for lead times between 1 to 12 hours using the most common ML techniques, such as Multi-Layer Perceptron (MLP), Logistic Regression (LR), K-Nearest Neighbors (KNN), Naive Bayes (NB), and Random Forest (RF). The Tomebamba catchment in the tropical Andes of Ecuador was selected as case study. For all lead times, MLP models achieve the highest performance followed by LR, with f1-macro (log-loss) scores of 0.82 (0.09) and 0.46 (0.20) for the 1- and 12-hour cases, respectively. The ranking was highly variable for the remaining ML techniques. According to the g-mean, LR models correctly forecast and show more stability at all states, while the MLP models perform better in the Pre-alert and Alert states. Future efforts are recommended to enhance the input data representation and develop communication applications to boost the awareness of the society for floods.