# LiveCodeBench v6 Contamination Audit

> LiveCodeBench v6 scores 3.2/10 (Tier C, High Risk) on BenchAudit as of November 2026, reflecting publicly downloadable plaintext test files and standardized independent third-party grading.

- **Canonical URL:** https://benchaudit.org/benchmarks/livecodebench/
- **Benchmark ID:** `livecodebench`
- **Hub:** LiveCodeBench / UC Berkeley
- **Category:** Coding
- **Domains:** Coding, Math
- **Skills:** Coding, Reasoning
- **BenchAudit Score:** 3.2/10 (Tier C - High Risk)
- **Last Audited:** 2026-11-17 (Ref 2026-11)

## Factor Scores

| Factor | Score (/10) | Weight |
| --- | ---: | ---: |
| Privacy | 0 | 40% |
| Originality | 7.2 | 25% |
| Freshness | 1.5 | 20% |
| Grading | 7.3 | 15% |

## Primary-Source Evidence

### Privacy
> "A contamination-free coding benchmark that continuously harvests fresh competitive programming problems from LeetCode, AtCoder, and CodeForces, evaluating code generation, self-repair, and execution."
- Source: https://artificialanalysis.ai/evaluations/livecodebench

### Originality
> "we propose LiveCodeBench, a comprehensive and contamination-free evaluation of LLMs for code, which continuously collects new problems over time from contests across three competition platforms, namely LeetCode, AtCoder, and CodeForces."
- Source: https://arxiv.org/abs/2403.07974

### Freshness
> "release_v6: The updated release of the dataset with problems released between May 2023 and Apr 2025 containing 1055 problems."
- Source: https://github.com/LiveCodeBench/LiveCodeBench

### Grading
> "We prompt LiveCodeBench with the following prompt, used with no changes from the original implementation of the LiveCodeBench prompt by the original team."
- Source: https://artificialanalysis.ai/methodology/intelligence-benchmarking
