# AA-Omniscience v1.1 Contamination Audit

> AA-Omniscience v1.1 scores 8.3/10 (Tier A, Low Risk) on BenchAudit as of November 2026, reflecting a hybrid public and private held-out split and isolated offline third-party grading.

- **Canonical URL:** https://benchaudit.org/benchmarks/aa-omniscience-v1-1/
- **Benchmark ID:** `aa-omniscience-v1-1`
- **Hub:** Artificial Analysis
- **Category:** General
- **Domains:** Humanities, Business, Finance, Legal, Medical, Science
- **Skills:** Knowledge Work, Reasoning, Instruction Following
- **BenchAudit Score:** 8.3/10 (Tier A - Low Risk)
- **Last Audited:** 2026-11-17 (Ref 2026-11)

## Factor Scores

| Factor | Score (/10) | Weight |
| --- | ---: | ---: |
| Privacy | 7.5 | 40% |
| Originality | 7.2 | 25% |
| Freshness | 10 | 20% |
| Grading | 10 | 15% |

## Primary-Source Evidence

### Privacy
> "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:"
- Source: https://huggingface.co/datasets/ArtificialAnalysis/AA-Omniscience-Public-v1.1

### Originality
> "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."
- Source: https://artificialanalysis.ai/evaluations/omniscience

### Freshness
> "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"
- Source: https://artificialanalysis.ai/methodology/intelligence-benchmarking

### Grading
> "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:"
- Source: https://huggingface.co/datasets/ArtificialAnalysis/AA-Omniscience-Public-v1.1

## Top Frontier Models on AA-Omniscience v1.1

| Rank | Model | Creator | Percentile |
| ---: | --- | --- | ---: |
| #1 | [Claude Fable 5.2](https://benchaudit.org/models/claude-fable-5-2__max/) | Anthropic | 100.0p |
| #2 | [Gemini 4 Neon](https://benchaudit.org/models/gemini-4-neon__xhigh/) | Google | 99.4p |
| #3 | [Gemini 4 Carbon](https://benchaudit.org/models/gemini-4-carbon__high/) | Google | 97.3p |
| #4 | [GPT-6.2 Astra](https://benchaudit.org/models/gpt-6-2-astra__max/) | OpenAI | 95.1p |
| #5 | [Claude Opus 5.5](https://benchaudit.org/models/claude-opus-5-5__max/) | Anthropic | 92.9p |
| #6 | [Claude Fable 5.1](https://benchaudit.org/models/claude-fable-5-1__max/) | Anthropic | 89.6p |
| #6 | [Gemini 4 Hydrogen](https://benchaudit.org/models/gemini-4-hydrogen__xhigh/) | Google | 89.6p |
| #8 | [Gemini 4 Argon](https://benchaudit.org/models/gemini-4-argon__high/) | Google | 86.3p |
| #9 | [GPT-6 Astra](https://benchaudit.org/models/gpt-6-astra__max/) | OpenAI | 84.1p |
| #10 | [GPT-6.1 Sol](https://benchaudit.org/models/gpt-6-1-sol__max/) | OpenAI | 81.9p |
