The Internet of Things (IoT) is a rapidly growing technology that is constantly changing over time. Due to the widespread of Internet of Things devices in diverse application domains, it has become crucial to ensure the security of IoT networks. Intrusion Detection Systems (IDS) are the first line of defense against IoT-related threats. This paper presents a rigorous analysis of classifier performance in the context of IoT IDS, encompassing a comparison of Machine Learning (ML) methodologies which includes Support Vector Machines (SVM), Decision Trees (DT), Random Forest (RF), and Extreme Gradient Boosting (XGBoost). The study leverages a diverse dataset encompassing a wide range of network intrusion scenarios, allowing for a thorough evaluation of classifier efficacy under realistic conditions. Performance evaluation measures like accuracy, recall, precision, and F1-score assess the effectiveness of each classifier in identifying malicious activities and minimizing false positives. The computed results highlight the superior performance of XGBoost with an intrusion detection accuracy of 83.2% when compared to DT, SVM, and RF across various dimensions. Moreover, XGBoost consistently exhibits higher accuracy rates, increased precision in detecting intrusions, and superior recall for identifying true positives.