OpenAI’s DeepResearch can complete 26% of ‘Humanity’s Last Exam’ — a benchmark for the frontier of human knowledge

[
OpenAI’s o1 and DeepSeek’s R1 models, which previously sat atop the leaderboard, could only get through roughly 9% of the exam. Read More
https://fortune.com/img-assets/wp-content/uploads/2025/02/GettyImages-2198379368-e1739310956573.jpg?resize=1200,600
https://fortune.com/2025/02/12/openai-deepresearch-humanity-last-exam/


Greg McKenna