The artificial intelligence model Claude 3 Opus achieved a great milestone by securing the top spot in the list of large language models, surpassing its competitor GPT-4 from OpenAI for the first time.
In contrast to other artificial intelligence evaluation platforms that rely on complex technical criteria, the “Chatbot Arena” platform relies on user voting to determine the best model.
Individuals are presented with different products from two artificial intelligence models, and the person evaluates each based on their personal preferences, such as the quality of generated texts or the way they respond to questions asked.
Upon the release of the GPT-4 model, it claimed the top spot in the ranking list since its launch last year, to the extent that any model showing similar performance is considered part of the “GPT-4 class.” However, Claude 3 Opus managed to achieve an interesting and nearly convergent result with GPT-4, indicating intense competition in the field of large artificial intelligence models.
