GPT-4 is recognized as the best AI model for chatbots
LMSYS Chatbot Arena service has updated the rating of large language models of artificial intelligence. It allows you to assess which models are currently doing the best job.
LMSYS Chatbot Arena is a crowdsourced open platform for evaluating large language models (LLMs). To compile the rating, more than 300 thousand people are evaluated. human feedback on the models’ performance using the Elo rating system.
How the test works: people enter a query and choose the best answer from several options from different models. Based on thousands of user tests, the top is formed and ranked.
According to the new rating of the chatbot arena, GPT4 is currently the leader among LLMs. Claude’s recent claims that their model is better have not been confirmed. She took third place. Right behind it is the Bard (Gemini Pro) model from Google. All of these models received an Elo rating of over 1200.
You can find detailed up-to-date results of the ranking of existing large language models at the following address.
