A Benchmark of Expert-Level Academic Questions to Assess AI Capabilities

@article{phan2025humanity,
    author = "{Center for AI Safety} and {Scale AI} and {HLE Contributors Consortium}",
    title = "A Benchmark of Expert-Level Academic Questions to Assess AI Capabilities",
    year = "2026",
    month = "January",
    journal = "Nature",
    volume = "649",
    pages = "1139--1146",
    doi = "10.1038/s41586-025-09962-4"
}