Humanity's Last Exam (HLE)
2,500 expert-written, closed-ended questions across dozens of academic subjects, including multimodal items.
Reference by Center for AI Safety and Scale AI
IndexedMIT★ 1,725
About
How well a model answers very difficult, expert-level questions in mathematics, sciences and humanities.
Use cases: llm-evaluation
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
About the benchmark
- Benchmark site
- lastexam.ai/
- Maintainer
- Center for AI Safety and Scale AIlastexam.ai
- Launched
- 2025-01arxiv.org
We link to the official leaderboard instead of copying scores. Benchmarks get gamed and saturate; we never use them to rank listings.
Signals
- Stars
- 1,725
- Forks
- 114
- Open issues
- 0
- Last commit
- Sep 23, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/centerforaisafety/hle
- Website
- lastexam.ai/
- Docs
- lastexam.ai/
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
Cite this page
Humanity's Last Exam (HLE) benchmark. Agent Mart. https://agentmart.dev/reference/humanitys-last-exam (last updated 2026-10-24)