Domains: HumanitiesBusinessFinanceLegalMedicalScience
Skills: Knowledge WorkReasoningInstruction Following

Four-Factor Integrity Breakdown & Primary-Source Evidence

Privacy

Weight 40%
7.5/10
Access Model: Hybrid Public / Private
"The full v1.1 dataset has 3,000 questions in 6 domains. AA-Omniscience-Public v1.1 is a 10% subset of it, split across domains in the same proportions:"
Primary source (HuggingFace) ↗ Verified 2026-11-17
"We keep the other 2,700 questions private to protect the integrity of the evaluation."

Originality

Weight 25%
7.2/10
Reuse Profile: Low Reuse (<25%)
"Questions are derived from authoritative academic and industry sources and generated automatically using an LLM-based question generation agent to ensure unambiguity, scalability, and factual precision."

Freshness

Weight 20%
10/10
Initial Release: 2025-11Latest Refresh: 2026-10Rolling Updates: No
"October 2026 to November 2026 Added HLE-Diamond (10%) to the General category Added Terminal-Bench-Science (15%) to the Science category Added FrontierCode-AA 2.0 (15%) to the Coding category Reduced the GDP.pdf weight from 10% to 5% Replaced CritPt with CritPt v2 (Hard Subset), keeping its 10% weight Removed GDPval-AA from the Intelligence Index Removed SciCode from the Intelligence Index Removed AA-LCR from the Intelligence Index Removed Humanity's Last Exam from the Intelligence Index Upgraded AA-Omniscience to v1.1"

Grading

Weight 15%
10/10
Integrity: Independent Offline (Leak-Verified)Sandbox: not applicable single turn
"Models get no context and no tools, so the evaluation measures what they can recall. Before each question, the model is told to answer only if it is confident, and that abstaining is better than a wrong answer:"
Primary source (HuggingFace) ↗ Verified 2026-11-17

Frontier Model Standings on AA-Omniscience v1.1

Top 15 active models tracked
Rank Model Official Score Percentile
#1Claude Fable 5.2 max Anthropic66.77 index100.0p
#2Gemini 4 Neon xhigh Google54.77 index99.4p
#3Gemini 4 Carbon high Google53.50 index97.3p
#4GPT-6.2 Astra max OpenAI50.00 index95.1p
#5Claude Opus 5.5 max Anthropic48.13 index92.9p
#6Claude Fable 5.1 max Anthropic46.27 index89.6p
#6Gemini 4 Hydrogen xhigh Google46.27 index89.6p
#8Gemini 4 Argon high Google46.10 index86.3p
#9GPT-6 Astra max OpenAI42.43 index84.1p
#10GPT-6.1 Sol max OpenAI42.03 index81.9p
#11GPT-6.2 Sol max OpenAI40.37 index79.8p
#12Grok 4.7 xhigh SpaceXAI31.23 index77.6p
#13Muse Wonder Full max Meta30.60 index75.4p
#14Claude Sonnet 5.5 max Anthropic30.47 index73.2p
#15Kimi K3.1 Pro max Kimi29.87 index71.0p

Embeddable Audit Badge

View Markdown (.md)

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

BenchAudit AA-Omniscience v1.1 Tier A 8.3/10
[![BenchAudit Tier A](https://benchaudit.org/badges/aa-omniscience-v1-1.svg)](https://benchaudit.org/benchmarks/aa-omniscience-v1-1/)