# GDPval-AA v2.1 Contamination Audit

> GDPval-AA v2.1 scores 3.3/10 (Tier C, High Risk) on BenchAudit as of November 2026, reflecting publicly downloadable plaintext test files and self-reported or live-network evaluation.

- **Canonical URL:** https://benchaudit.org/benchmarks/gdpval-aa-v2-1/
- **Benchmark ID:** `gdpval-aa-v2-1`
- **Hub:** Artificial Analysis / OpenAI
- **Category:** Knowledge Work
- **Domains:** Business, Finance, Legal, Medical, Humanities
- **Skills:** Knowledge Work, Agentic, Tool Use, Writing, Reasoning, Multimodal
- **BenchAudit Score:** 3.3/10 (Tier C - High Risk)
- **Last Audited:** 2026-11-17 (Ref 2026-11)

## Factor Scores

| Factor | Score (/10) | Weight |
| --- | ---: | ---: |
| Privacy | 0 | 40% |
| Originality | 10 | 25% |
| Freshness | 1.5 | 20% |
| Grading | 3.3 | 15% |

## Primary-Source Evidence

### Privacy
> "We base our evaluation on the public gold OpenAI GDPval dataset from https://huggingface.co/datasets/openai/gdpval"
- Source: https://artificialanalysis.ai/methodology/intelligence-benchmarking

### Originality
> "GDPval-AA v2.1 is Artificial Analysis' evaluation framework for OpenAI's GDPval dataset. It assesses language models' capabilities on economically valuable tasks, covering 44 occupations across key sectors contributing to GDP in the United States."
- Source: https://artificialanalysis.ai/methodology/intelligence-benchmarking

### Freshness
> "arXiv:2510.04374 (cs) [Submitted on 5 Oct 2025] Title: GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks"
- Source: https://arxiv.org/abs/2510.04374

### Grading
> "GDPval-AA v2.1 is Artificial Analysis' evaluation framework for OpenAI's GDPval dataset. It tests AI models on real-world tasks across 44 occupations and 9 major industries. Models are given shell access and web browsing capabilities in an agentic loop via Stirrup to solve tasks, with Elo ratings derived from blind pairwise comparisons."
- Source: https://artificialanalysis.ai/evaluations

## Top Frontier Models on GDPval-AA v2.1

| Rank | Model | Creator | Percentile |
| ---: | --- | --- | ---: |
| #1 | [Claude Opus 5.5](https://benchaudit.org/models/claude-opus-5-5__max/) | Anthropic | 96.1p |
| #2 | [Kimi K3.1 Pro](https://benchaudit.org/models/kimi-k3-1-pro__max/) | Kimi | 93.8p |
| #3 | [Muse Wonder Full](https://benchaudit.org/models/muse-wonder-full__max/) | Meta | 91.4p |
| #4 | [Claude Sonnet 5.5](https://benchaudit.org/models/claude-sonnet-5-5__max/) | Anthropic | 89.1p |
| #5 | [Claude Fable 5.2](https://benchaudit.org/models/claude-fable-5-2__max/) | Anthropic | 86.8p |
| #6 | [Qwen4 Max](https://benchaudit.org/models/qwen4-max__xhigh/) | Alibaba | 84.4p |
| #7 | [Muse Wonder](https://benchaudit.org/models/muse-wonder__max/) | Meta | 82.0p |
| #8 | [Claude Fable 5.1](https://benchaudit.org/models/claude-fable-5-1__max/) | Anthropic | 79.6p |
| #9 | [DeepSeek V4.1 Flash 1017](https://benchaudit.org/models/deepseek-v4-1-flash-1017__max/) | DeepSeek | 77.4p |
| #10 | [Gemini 4 Carbon](https://benchaudit.org/models/gemini-4-carbon__high/) | Google | 75.0p |
