# Code2Video-AA Contamination Audit

> Code2Video-AA scores 8.8/10 (Tier S, Fortified) 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/code2video-aa/
- **Benchmark ID:** `code2video-aa`
- **Hub:** Artificial Analysis / HeyGen
- **Category:** Coding
- **Domains:** Coding
- **Skills:** Coding, Multimodal, Instruction Following, Reasoning
- **BenchAudit Score:** 8.8/10 (Tier S - Fortified)
- **Last Audited:** 2026-11-17 (Ref 2026-11)

## Factor Scores

| Factor | Score (/10) | Weight |
| --- | ---: | ---: |
| Privacy | 7.5 | 40% |
| Originality | 10 | 25% |
| Freshness | 9 | 20% |
| Grading | 10 | 15% |

## Primary-Source Evidence

### Privacy
> "We evaluate 114 of the 168 briefs in Code2Video Bench: 39 from HeyGen's public split and 75 private briefs shared with us by HeyGen."
- Source: https://artificialanalysis.ai/methodology/intelligence-benchmarking

### Originality
> "Each model gets one brief and writes one HyperFrames HTML composition: HTML for layout and GSAP for animation. We render the composition to a video with HyperFrames."
- Source: https://artificialanalysis.ai/evaluations/code2video-aa

### Freshness
> "Data as at 26 October 2026 (dataset 0.3.0)"
- Source: https://artificialanalysis.ai/articles/code2video-aa

### Grading
> "We render each composition to an MP4 video with HyperFrames 0.8.30, with no network access and a 5-minute limit."
- Source: https://artificialanalysis.ai/methodology/intelligence-benchmarking

## Top Frontier Models on Code2Video-AA

| Rank | Model | Creator | Percentile |
| ---: | --- | --- | ---: |
| #1 | [Claude Opus 5.5](https://benchaudit.org/models/claude-opus-5-5__max/) | Anthropic | 88.5p |
| #2 | [Claude Sonnet 5.5](https://benchaudit.org/models/claude-sonnet-5-5__max/) | Anthropic | 84.9p |
| #3 | [GPT-6 Astra](https://benchaudit.org/models/gpt-6-astra__max/) | OpenAI | 81.2p |
| #4 | [GPT-6.1 Sol](https://benchaudit.org/models/gpt-6-1-sol__max/) | OpenAI | 77.6p |
| #5 | [Claude Fable 5.1](https://benchaudit.org/models/claude-fable-5-1__max/) | Anthropic | 73.9p |
| #6 | [Gemini 4 Argon](https://benchaudit.org/models/gemini-4-argon__high/) | Google | 70.2p |
| #7 | [Claude Haiku 5.5](https://benchaudit.org/models/claude-haiku-5-5__max/) | Anthropic | 66.5p |
| #8 | [Grok 4.7](https://benchaudit.org/models/grok-4-7__xhigh/) | SpaceXAI | 62.9p |
| #9 | [DeepSeek V4.1 Flash](https://benchaudit.org/models/deepseek-v4-1-flash__max/) | DeepSeek | 59.2p |
| #10 | [MiMo-V2.6-Flash](https://benchaudit.org/models/mimo-v2-6-flash/) | Xiaomi | 55.6p |
