Ophthalmology is a specialty that depends on image-based and data-rich diagnosis, so artificial intelligence (AI) has a lot of potential for this field [1], [2]. Artificial intelligence applications have surfaced due to technological advancements, opening the door for its application in all fields of medicine [3], [4], [5]. Large deep learning models, known as baseline models, have recently been introduced and brought natural language processing to the attention of the media. A new approach to the development of AI systems is represented by baseline models, where models are pre-trained on a large scale using enormous volumes of undisclosed multimodal data in a self-policing system [6].

The field of education and knowledge accessibility has undergone a significant transformation with the advent of artificial intelligence large language models (LLMs) in recent times. LLMs have proven to be extremely skilled at synthesizing information from a wide range of sources. Due to their relative novelty, the role of these LLMs in medicine remains unclear. Large deep learning models has recently started to be the subject of research. Whether such systems can replace the knowledge and experience of specialized physicians is extremely controversial [7]. Despite the limitation of experience-based medical decision-making, which allows doctors to make complex diagnoses, there is new interest in evaluating the performance of LLMs in routine doctor examinations [8].

The most well-known and frequently used LLM models today are Microsoft Copilot (Microsoft Corporation, Washington, ABD), Google Gemini (Alphabet Inc., California, ABD) and ChatGPT (OpenAI Incorporated, San Francisco, ABD). LLMs can be trained by exposing them to large volumes of training data [9], [10], [11]. Most research has focused on the use of ChatGPT in ophthalmology. A thorough assessment of Google Gemini and Microsoft Copilot's diagnostic capabilities in cases involving uveitis and ocular inflammation is still required [12], [13].

The aim of the study was to determine the level of knowledge of ChatGPT-4o, Microsoft Copilot Pro and Google Gemini 1.5 Pro (Google Gemini Advanced), which are LLMs from three different companies that can be used by patients and ophthalmologists to obtain information in the diagnosis and treatment of uveitis and ocular inflammation, and to compare their performance with each other and ophthalmologists and to compare their strengths and weaknesses.