# AutomationBench-AA Contamination Audit

> AutomationBench-AA 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/automationbench-aa/
- **Benchmark ID:** `automationbench-aa`
- **Hub:** Artificial Analysis / Zapier
- **Category:** Knowledge Work
- **Domains:** Business
- **Skills:** Knowledge Work, Agentic, Tool Use, Reasoning, Instruction Following
- **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
> "We evaluate a private 657-task held-out split from AutomationBench dataset version 1.0.6"
- Source: https://artificialanalysis.ai/methodology/intelligence-benchmarking

### Originality
> "It tests whether models can complete realistic SaaS workflows that span multiple simulated business apps, using REST APIs as the tool interface."
- Source: https://artificialanalysis.ai/methodology/intelligence-benchmarking

### Freshness
> "Version 4.3 September 2026 Replaced 𝜏³-Banking with AutomationBench-AA (5%) in the Agents category"
- Source: https://artificialanalysis.ai/methodology/intelligence-benchmarking

### Grading
> "Objectives and guardrails are graded using programmatic checks on the final environment state. AutomationBench-AA does not use a separate LLM judge for grading"
- Source: https://artificialanalysis.ai/methodology/intelligence-benchmarking

## Top Frontier Models on AutomationBench-AA

| Rank | Model | Creator | Percentile |
| ---: | --- | --- | ---: |
| #1 | [Gemini 4 Neon](https://benchaudit.org/models/gemini-4-neon__xhigh/) | Google | 100.0p |
| #2 | [Gemini 4 Carbon](https://benchaudit.org/models/gemini-4-carbon__high/) | Google | 98.0p |
| #3 | [Gemini 4 Argon](https://benchaudit.org/models/gemini-4-argon__high/) | Google | 95.9p |
| #4 | [GPT-6.2 Astra](https://benchaudit.org/models/gpt-6-2-astra__max/) | OpenAI | 93.9p |
| #5 | [Claude Fable 5.2](https://benchaudit.org/models/claude-fable-5-2__max/) | Anthropic | 91.8p |
| #6 | [Gemini 4 Hydrogen](https://benchaudit.org/models/gemini-4-hydrogen__xhigh/) | Google | 89.8p |
| #7 | [Kimi K3.1 Pro](https://benchaudit.org/models/kimi-k3-1-pro__max/) | Kimi | 87.8p |
| #8 | [Qwen4 Max](https://benchaudit.org/models/qwen4-max__xhigh/) | Alibaba | 85.7p |
| #9 | [MiniMax-M3.1-Flash](https://benchaudit.org/models/minimax-m3-1-flash__max/) | MiniMax | 83.7p |
| #10 | [Claude Sonnet 5.5](https://benchaudit.org/models/claude-sonnet-5-5__max/) | Anthropic | 81.6p |
