This pre-proof journal article assesses the performance of four AI chatbots—ChatGPT-4o, MedGebra GPT4o, Meta Llama 3, and Gemini Advanced—in answering 100 multiple-choice questions on endodontics. The study compares their accuracy and consistency across two rounds of testing, using statistical methods to analyze the results. MedGebra GPT4o initially exhibited the highest accuracy, but ChatGPT-4o showed greater consistency. The findings reveal varying levels of performance among the chatbots, highlighting the need for further development to enhance accuracy and reliability in medical applications. The research contributes to the understanding of AI's capabilities in the field of endodontics.