# AA-Briefcase v1.1 Contamination Audit

> AA-Briefcase v1.1 scores 10/10 (Tier S, Fortified) on BenchAudit as of November 2026, reflecting a strictly private held-out test set and isolated offline third-party grading.

- **Canonical URL:** https://benchaudit.org/benchmarks/aa-briefcase-v1-1/
- **Benchmark ID:** `aa-briefcase-v1-1`
- **Hub:** Artificial Analysis
- **Category:** Knowledge Work
- **Domains:** Business
- **Skills:** Knowledge Work, Agentic, Tool Use, Writing, Reasoning, Long Context
- **BenchAudit Score:** 10/10 (Tier S - Fortified)
- **Last Audited:** 2026-11-17 (Ref 2026-11)

## Factor Scores

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

## Primary-Source Evidence

### Privacy
> "To maintain evaluation integrity, all 91 tasks across the four AA-Briefcase project scenarios are private, including task instructions, project input files and grading rubrics."
- Source: https://artificialanalysis.ai/articles/aa-briefcase

### Originality
> "AA-Briefcase is a new benchmark for testing models on realistic knowledge work tasks in complex projects built by industry experts. Models are evaluated on multi-week knowledge work projects, each with many linked tasks and thousands of input source files."
- Source: https://artificialanalysis.ai/methodology/intelligence-benchmarking

### Freshness
> "Version 4.3.2 September 2026 to October 2026 GDPval-AA v2.1: the Elo scale is now anchored to DeepSeek V4.1 Flash (max) at 1600, and ratings are fitted with a Crowd-BT model. AA-Briefcase v1.1: the anchor is unchanged at GPT-5.5 (medium) at 1000, but each pairwise scope is now fitted with a Crowd-BT model."
- Source: https://artificialanalysis.ai/methodology/intelligence-benchmarking

### Grading
> "Model submissions are run with Stirrup in a week-scoped E2B sandbox. Turns: Agents run for up to 500 turns per task. Tools: The agent is given a single code-execution tool that runs shell commands and code inside the sandbox, plus the finish tools below (and a view-image tool when the model supports vision). The sandbox has no internet access, so the agent can only use the provided source files."
- Source: https://artificialanalysis.ai/methodology/intelligence-benchmarking

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

| Rank | Model | Creator | Percentile |
| ---: | --- | --- | ---: |
| #1 | [Claude Sonnet 5.5](https://benchaudit.org/models/claude-sonnet-5-5__max/) | Anthropic | 100.0p |
| #2 | [Claude Opus 5.5](https://benchaudit.org/models/claude-opus-5-5__max/) | Anthropic | 98.0p |
| #3 | [Claude Fable 5.2](https://benchaudit.org/models/claude-fable-5-2__max/) | Anthropic | 95.9p |
| #4 | [Muse Wonder Full](https://benchaudit.org/models/muse-wonder-full__max/) | Meta | 93.9p |
| #5 | [Gemini 4 Neon](https://benchaudit.org/models/gemini-4-neon__xhigh/) | Google | 91.8p |
| #6 | [Qwen4 Max](https://benchaudit.org/models/qwen4-max__xhigh/) | Alibaba | 89.8p |
| #7 | [Kimi K3.1 Pro](https://benchaudit.org/models/kimi-k3-1-pro__max/) | Kimi | 87.8p |
| #8 | [Claude Fable 5.1](https://benchaudit.org/models/claude-fable-5-1__max/) | Anthropic | 85.7p |
| #9 | [Muse Wonder](https://benchaudit.org/models/muse-wonder__max/) | Meta | 83.7p |
| #10 | [GPT-6.2 Astra](https://benchaudit.org/models/gpt-6-2-astra__max/) | OpenAI | 81.6p |
