Domains: ScienceMathHumanitiesMedical
Skills: ReasoningKnowledge WorkMultimodal

Four-Factor Integrity Breakdown & Primary-Source Evidence

Privacy

Weight 40%
2/10
Access Model: Auto-Gated / Encrypted
"This repository is publicly accessible, but you have to accept the conditions to access its files and content"
Primary source (HuggingFace) ↗ Verified 2026-11-17
"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."
Primary source (Paper) ↗ Verified 2026-11-17

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
Rank Model Official Score Percentile
#1Claude Fable 5.2 max Anthropic80.2%100.0p
#2GPT-6.2 Astra max OpenAI72.2%97.9p
#3Gemini 4 Neon xhigh Google71.3%95.8p
#4Gemini 4 Carbon high Google69.1%93.8p
#5Claude Opus 5.5 max Anthropic67.9%91.7p
#6GPT-6.2 Sol max OpenAI64.0%89.6p
#7GPT-6 Astra max OpenAI63.8%87.5p
#8Claude Fable 5.1 max Anthropic60.1%85.4p
#9Gemini 4 Hydrogen xhigh Google58.8%82.3p
#9GPT-6.1 Sol max OpenAI58.8%82.3p
#11Gemini 4 Argon high Google56.7%79.2p
#12Claude Sonnet 5.5 max Anthropic53.3%77.1p
#13Muse Wonder Full max Meta48.5%75.0p
#14GPT-6.1 Terra max OpenAI47.3%72.9p
#15GPT-6 Sol max OpenAI45.2%70.8p

Embeddable Audit Badge

View Markdown (.md)

Benchmark maintainers can embed this live SVG badge in GitHub READMEs or documentation:

BenchAudit HLE-Diamond Tier B 5.8/10
[![BenchAudit Tier B](https://benchaudit.org/badges/hle-diamond.svg)](https://benchaudit.org/benchmarks/hle-diamond/)