Openai’s Deepresearch can complete 26 % of the “Latest Humanity Exam” – a standard of human knowledge limits

Photo of author

By [email protected]




Openai’s O1 and Deepseek models, which were previously sitting on top of the leaders, can only pass nearly 9 % of the exam. Read more



https://fortune.com/img-assets/wp-content/uploads/2025/02/GettyImages-2198379368-e1739310956573.jpg?resize=1200,600

Source link

Leave a Comment