See Humanity’s Last Exam.
Humanity’s Last Exam A benchmark of expert-written questions across many fields, written to be hard for the best models; row 8 of the Scorecard reads the best model’s score on a text-only subset of its questions, and the Scorecard writes it HLE. The Scorecard.
From The AI Compute Race. Read the book
Where the record uses it
- Scorecard indicator Humanity’s Last Exam
Sources that use it
- Artificial Analysis, “Humanity’s Last Exam Benchmark Leaderboard,” accessed 30 August 2026 (Claude Fable 5, Adaptive Reasoning/Max Effort with Opus 4.8 fallback, scored 55.5% on Artificial Analysis’s 2,158-question text-only HLE evaluation; an independently preserved 15 August 2026 snapshot was not located). In the Sources
- Artificial Analysis, “Intelligence Benchmarking Methodology,” Artificial Analysis Intelligence Index v4.3.2, September 2026 (HLE is graded by an equality checker using GPT-5.6 Luna at its medium setting; read 27 September and 3 October 2026). In the Sources
Related terms
From the glossary of The AI Compute Race.
How to cite this page
Dryburgh, Lee S. “HLE.” In The AI Compute Race. DRYBURGH. https://dryburgh.com/vol1/glossary/hle (accessed 2026-11-01).
BibTeX
@misc{dryburgh-hle-2026,
author = {Dryburgh, Lee S.},
title = {{HLE}},
howpublished = {In \emph{The AI Compute Race}, DRYBURGH},
year = {2026},
url = {https://dryburgh.com/vol1/glossary/hle},
note = {Accessed 2026-11-01}
}