Four-Factor Integrity Breakdown & Primary-Source Evidence
Access Model: Auto-Gated / Encrypted
"This repository is publicly accessible, but you have to accept the conditions to access its files and content"
"We are releasing HLE-Diamond, a refined subset of Humanity's Last Exam (HLE) question collection, following a year-long process of cleaning and refinement with input from research communities."
Originality
Weight 25%
10/10
Reuse Profile: All Original (0% reuse)
"HLE is developed globally by subject-matter experts and consists of multiple-choice and short-answer questions suitable for automated grading. Each question has a known solution that is unambiguous and easily verifiable, but cannot be quickly answered via internet retrieval."
Freshness
Weight 20%
7/10
Initial Release: 2025-01Latest Refresh: 2026-09Rolling Updates: No
"Center for AI Safety and Scale AI September 22, 2026"
Grading
Weight 15%
7.3/10
Integrity: Independent StandardizedSandbox: not applicable single turn
"We grade each answer with the official HLE judge prompt and response format, using GPT-5.6 Luna (medium) as the judge, with pass@1 scoring."
Frontier Model Standings on HLE-Diamond
Top 15 active models tracked
Benchmark maintainers can embed this live SVG badge in GitHub READMEs or documentation:
[](https://benchaudit.org/benchmarks/hle-diamond/)