OpenAI has introduced the updated GPT-4 Turbo to developers and ChatGPT subscribers, showcasing noteworthy enhancements over its predecessor. The new model, gpt-4-turbo-2024-04-09, recently claimed the top rank on the Large Model Systems Organization’s Chatbot Arena, a platform enabling users to compare responses from different large language models (LLMs) without disclosing their identities. Evaluations from users have highlighted the GPT-4 Turbo’s advanced capabilities in coding, reasoning, and English proficiency, propelling it to lead in various categories on the leaderboard as of the latest update on April 13.
Anthropic’s Claude 3 Opus, which momentarily surpassed GPT-4 Turbo in the competition, has now fallen to second place overall, followed by an older version of GPT-4 Turbo in third place. This shift in rankings can be attributed to the enhanced performance of gpt-4-turbo-2024-04-09, particularly in coding, math, logical reasoning, and writing skills, as demonstrated in benchmark tests. Users interested in exploring GPT-4 Turbo’s performance firsthand can visit the Chatbot Arena website to compare the model against other LLMs.
HEALTH
WORLD AFFAIRS
TECHNOLOGY
CREATIVE
