AI fails the “final test of humanity”. So what does this mean for machine intelligence?

AI fails the “final test of humanity”. So what does this mean for machine intelligence?

By Sandra Peter
Publication Date: 2026-01-29 23:54:00

How do you translate the ancient Palmyrene script from a Roman tombstone? How many pairs of tendons are supported by a given sesamoid bone in a hummingbird? Can you identify closed syllables in Biblical Hebrew using the latest research on Tiberian pronunciation traditions?

These are some of the questions in “Humanity’s Last Exam,” a new benchmark introduced in a study published this week in Nature. The collection of 2,500 questions is specifically designed to explore the outer limits of what today’s artificial intelligence (AI) systems cannot achieve.

The benchmark represents a global collaboration of nearly 1,000 international experts from various academic fields. These academics and researchers asked questions at the frontier of human knowledge. The problems required graduate-level expertise in mathematics, physics, chemistry, biology, computer science, and humanities. Importantly, each question has been tested using leading AI models before being included. If…