# Vibe Code Bench 1-100 v1.1 Contamination Audit

> Vibe Code Bench 1-100 v1.1 scores 9.6/10 (Tier S, Fortified) on BenchAudit as of November 2026, reflecting a strictly private held-out test set and standardized independent third-party grading.

- **Canonical URL:** https://benchaudit.org/benchmarks/vcb-1-100-v1-1/
- **Benchmark ID:** `vcb-1-100-v1-1`
- **Hub:** Vals AI
- **Category:** Coding
- **Domains:** Coding
- **Skills:** Agentic, Coding, Tool Use, Long Context, Instruction Following
- **BenchAudit Score:** 9.6/10 (Tier S - Fortified)
- **Last Audited:** 2026-11-22 (Ref 2026-11)

## Factor Scores

| Factor | Score (/10) | Weight |
| --- | ---: | ---: |
| Privacy | 10 | 40% |
| Originality | 10 | 25% |
| Freshness | 10 | 20% |
| Grading | 7.3 | 15% |

## Primary-Source Evidence

### Privacy
> "The dataset contains 50 test set scenarios and 50 separate validation scenarios. All model scores reported on this page are based only on the test subset."
- Source: https://www.vals.ai/benchmarks/vcb-1-100-v1-1

### Originality
> "The v1.1 workflow definitions contain 6022 workflows across 456 requests in 50 test scenarios. Of these, 1572 (26.1%) check earlier behavior, and 4450 cover the new request. These figures exclude the separate validation set."
- Source: https://www.vals.ai/benchmarks/vcb-1-100-v1-1

### Freshness
> "In v1.1, we changed iteration prompts to make requirements less ambiguous. We also audited task workflows to check that each assertion follows from the task request. We added a step to the grading process in which a second judge model, Claude Sonnet 5.5, reviews browser-agent failure verdicts against the recorded evidence."
- Source: https://www.vals.ai/benchmarks/vcb-1-100-v1-1

### Grading
> "All models use the same modified OpenHands V1 environment, with terminal access and preconfigured Supabase, Stripe test services, and MailHog. Each task has one ten-hour generation budget shared across its iterations. Evaluation time is excluded."
- Source: https://www.vals.ai/benchmarks/vcb-1-100-v1-1

## Top Frontier Models on Vibe Code Bench 1-100 v1.1

| Rank | Model | Creator | Percentile |
| ---: | --- | --- | ---: |
| #1 | [GPT-6.2 Astra](https://benchaudit.org/models/gpt-6-2-astra__max/) | OpenAI | 100.0p |
| #2 | [Gemini 4 Carbon](https://benchaudit.org/models/gemini-4-carbon__high/) | Google | 95.6p |
| #3 | [GPT-6.2 Sol](https://benchaudit.org/models/gpt-6-2-sol__max/) | OpenAI | 86.4p |
| #4 | [Claude Opus 5.5](https://benchaudit.org/models/claude-opus-5-5__max/) | Anthropic | 77.2p |
| #5 | [GLM-5.3](https://benchaudit.org/models/glm-5-3__max/) | Z AI | 68.0p |
| #6 | [MiMo-V2.6-Pro](https://benchaudit.org/models/mimo-v2-6-pro/) | Xiaomi | 58.8p |
| #7 | [Grok 4.7](https://benchaudit.org/models/grok-4-7__xhigh/) | SpaceXAI | 49.6p |
| #8 | [DeepSeek V4.1 Flash 1017](https://benchaudit.org/models/deepseek-v4-1-flash-1017__max/) | DeepSeek | 40.4p |
| #9 | [MiMo-V2.6-Flash](https://benchaudit.org/models/mimo-v2-6-flash/) | Xiaomi | 31.2p |
| #10 | [MiniMax-M3.1-Flash](https://benchaudit.org/models/minimax-m3-1-flash__max/) | MiniMax | 22.0p |
