HLE

Humanity's Last Exam evaluation environment

Type: RL Env
Publisher: Prime Intellect
Tags: Hle V1 Academic Reasoning
Runtime: single-turn
License: unknown
Size: v0.3.0
Published: Sep 2025
Updated: Sep 2026
Canonical: app.primeintellect.ai/dashboard/environments/primeintellect/hle

Cite

Notes

Only stored in your browser.

Attribution

README: api.primeintellect.ai/api/v1/environmentshub/primeintellect/hle/@0.2.1/inspect

Attribution policy →

Evals this tool implements

Same problem set, this tool's harness. Run it to score a model on the test.

Humanity's Last Exam (HLE)

Center for AI Safety

2,500 expert-authored questions across math, sciences, and humanities designed to be the hardest closed-ended benchmark for frontier models.

ActiveScientific ReasoningMathFactual Recall

Humanity's Last Exam

Center for AI Safety

Humanity's Last Exam (HLE) is a multi-modal benchmark at the frontier of human knowledge, designed to be the final closed-ended academic benchmark of its kind with broad subject coverage. Humanity's Last Exam consists of 3,000 questions across dozens of subjects, including mathem

ActiveKnowledge