Broad expert-created benchmark for measuring frontier AI knowledge and reasoning across highly difficult academic and professional questions.
- Jan 23, 2025
- —
- —
- —
- —
- 2
Releases
Jan 23, 2025Humanity's Last Exam results and benchmark releasedBenchmark result
Scale and the Center for AI Safety published Humanity’s Last Exam, assembled from nearly 1,000 contributors across more than 500 institutions in 50 countries.
Sep 2024Scale and Center for AI Safety develop Humanity's Last ExamPartnership
Scale and the Center for AI Safety launched an international effort to create a broad expert-written benchmark for frontier AI systems.