# DeepSWE v1.1 Contamination Audit

> DeepSWE v1.1 scores 4.3/10 (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/deepswe/
- **Benchmark ID:** `deepswe`
- **Hub:** Datacurve
- **Category:** Coding
- **Domains:** Coding
- **Skills:** Coding, Agentic, Tool Use, Reasoning
- **BenchAudit Score:** 4.3/10 (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 | 7 | 20% |
| Grading | 7.3 | 15% |

## Primary-Source Evidence

### Privacy
> "The reference patch in `solution/` is never used at grading time; it exists so reviewers can spot-check correctness offline."
- Source: https://raw.githubusercontent.com/datacurve-ai/deep-swe/main/README.md

### Originality
> "Every DeepSWE task is original: the reference solution is written from scratch rather than copied or adapted from an existing pull request, commit, or public patch."
- Source: https://deepswe.datacurve.ai/blog/deepswe

### Freshness
> "DeepSWE v1.1 keeps the same long-horizon engineering tasks as v1, but updates how agents are executed and scored by grading their committed code in a clean, isolated environment, making results easier to reproduce, audit, and analyze."
- Source: https://deepswe.datacurve.ai/blog/deepswe-v1-1

### Grading
> "The agent commits its proposed changes, and we extract the git patch to evaluate in an isolated container, separate from where the agent worked."
- Source: https://deepswe.datacurve.ai/blog/deepswe-v1-1
