Recently, phishing attacks have risen to the top of the social engineering assaults that affect organizations, governments, and the general public. A phishing assault cost roughly $1.5 billion in 2012, according to an internet analysis. As the worldwide impact of phishing attempts grows, more effective phishing detection systems will be required to combat this threat. This paper has examined six classifiers to identify the top machine learning classifiers for phishing attack detection from a dataset of 48 features from 5000 legitimate websites retrieved from the Kaggle repository. This work is implemented using CatBoostClassifier (CB)., light gradient-boostingmachineClassifier(LGBM)., eXtremeGradientBoosting (XGB), GradientBoostingClassifier (GBA), AdaBoostClassifier and RandomForestClassifier (RF) algorithms. The algorithms have achieved the XGBClassifier's accuracy result of 99.05% and the highest f1-core result of 99.0331%. The outcomes show that XGBClassifier is a reliable classifier for phishing attack detection.