Passwords are the crucial component for authentication. Strong passwords are complex in structure for protecting online accounts and safeguarding personal and sensitive information from unauthorized access. The passwords employed by the user can be quickly predicted through various techniques, such as analyzing input patterns and utilizing brute force strategies by the cybercriminals. This work analyses the various password strength prediction models developed by baseline and ensemble-based classifiers. The current study primarily focuses on various classifiers, namely decision tree, random forest, boosting, gradient descent classifier (GDClassifier), perceptron, Logistic Regression, Logistic Regression with cross-validation, passive-aggressive classifier, extreme gradient boosting (XGBoost), and light gradient boosting method (Light GBM). However, the experimental results showed that XGBoost gave an accuracy of 98.73% compared to other methods and outperformed the existing state-of-the-art techniques.