# FrontierCode-AA 2.0 Contamination Audit

> FrontierCode-AA 2.0 scores 9.3/10 (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/frontiercode-aa-2-0/
- **Benchmark ID:** `frontiercode-aa-2-0`
- **Hub:** Artificial Analysis / Cognition
- **Category:** Coding
- **Domains:** Coding
- **Skills:** Coding, Agentic, Tool Use, Reasoning, Instruction Following
- **BenchAudit Score:** 9.3/10 (Tier S - Fortified)
- **Last Audited:** 2026-11-17 (Ref 2026-11)

## Factor Scores

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

## Primary-Source Evidence

### Privacy
> "Artificial Analysis' implementation of Cognition's FrontierCode 2.0, a private agentic coding benchmark of 132 tasks in real open-source repositories, graded on whether a maintainer would merge the agent's change."
- Source: https://artificialanalysis.ai/evaluations/frontiercode-2-0

### Originality
> "FrontierCode 2.0 is a coding benchmark from Cognition, built with maintainers of open-source repositories. Each task asks an agent to make a change to a real open-source repository, and the benchmark measures whether the change is good enough for a maintainer to merge."
- Source: https://artificialanalysis.ai/methodology/intelligence-benchmarking

### Freshness
> "FrontierCode 2.0 By The Cognition Team 2026.10.27 FrontierCode Leaderboard"
- Source: https://cognition.com/blog/frontier-code-2.0

### Grading
> "An attempt that fails any blocking check, or that the trajectory scanner flags for looking up the solution, scores 0. Other attempts get a weighted score across the rubric's criteria."
- Source: https://artificialanalysis.ai/methodology/intelligence-benchmarking

## Top Frontier Models on FrontierCode-AA 2.0

| Rank | Model | Creator | Percentile |
| ---: | --- | --- | ---: |
| #1 | [Claude Fable 5.2](https://benchaudit.org/models/claude-fable-5-2__max/) | Anthropic | 100.0p |
| #2 | [Claude Opus 5.5](https://benchaudit.org/models/claude-opus-5-5__max/) | Anthropic | 100.0p |
| #3 | [GPT-6.2 Astra](https://benchaudit.org/models/gpt-6-2-astra__max/) | OpenAI | 97.8p |
| #4 | [Gemini 4 Neon](https://benchaudit.org/models/gemini-4-neon__xhigh/) | Google | 95.5p |
| #5 | [GPT-6.2 Sol](https://benchaudit.org/models/gpt-6-2-sol__max/) | OpenAI | 93.2p |
| #6 | [GPT-6 Astra](https://benchaudit.org/models/gpt-6-astra__max/) | OpenAI | 91.0p |
| #7 | [GPT-6.1 Terra](https://benchaudit.org/models/gpt-6-1-terra__max/) | OpenAI | 88.8p |
| #8 | [Claude Sonnet 5.5](https://benchaudit.org/models/claude-sonnet-5-5__max/) | Anthropic | 86.4p |
| #9 | [GPT-6.1 Sol](https://benchaudit.org/models/gpt-6-1-sol__max/) | OpenAI | 84.2p |
| #10 | [Gemini 4 Carbon](https://benchaudit.org/models/gemini-4-carbon__high/) | Google | 81.9p |
