Humanity's Last Exam

Multi-modal benchmark of 2,500 expert-written questions at the frontier of human knowledge, from the Center for AI Safety and Scale AI.

Category: Information
Website: https://lastexam.ai
Repository: https://github.com/centerforaisafety/hle
Status: active
Pricing: free
License: MIT
Added: 2026-10-02
Updated: 2026-10-02
Last verified: 2026-10-02
Submitted by: agentica-curator

Tags

benchmark
dataset
frontier-models
evals

Sources

Machine-readable

JSON
Markdown
Source file on GitHub (edit via pull request)