# SWE-bench Verified Contamination Audit

> SWE-bench Verified scores 1.5/10 (Tier D, Compromised) on BenchAudit as of November 2026, reflecting publicly downloadable plaintext test files and self-reported or live-network evaluation.

- **Canonical URL:** https://benchaudit.org/benchmarks/swe-bench-verified/
- **Benchmark ID:** `swe-bench-verified`
- **Hub:** SWE-bench / Princeton / OpenAI
- **Category:** Coding
- **Domains:** Coding
- **Skills:** Coding, Agentic, Tool Use, Reasoning, Long Context
- **BenchAudit Score:** 1.5/10 (Tier D - Compromised)
- **Last Audited:** 2026-11-17 (Ref 2026-11)

## Factor Scores

| Factor | Score (/10) | Weight |
| --- | ---: | ---: |
| Privacy | 0 | 40% |
| Originality | 4 | 25% |
| Freshness | 0 | 20% |
| Grading | 3.3 | 15% |

## Primary-Source Evidence

### Privacy
> "A human-validated subset of 500 SWE-bench instances for reliable evaluation of coding agents and language models."
- Source: https://www.swebench.com/verified.html

### Originality
> "To this end, we introduce SWE-bench, an evaluation framework consisting of $2,294$ software engineering problems drawn from real GitHub issues and corresponding pull requests across $12$ popular Python repositories."
- Source: https://arxiv.org/abs/2310.06770

### Freshness
> "**[Aug. 13, 2024]**: Introducing *SWE-bench Verified*! Part 2 of our collaboration with [OpenAI Preparedness](https://openai.com/preparedness/). A subset of 500 problems that real software engineers have confirmed are solvable."
- Source: https://raw.githubusercontent.com/SWE-bench/SWE-bench/main/README.md

### Grading
> "Check out the main SWE-bench repository docs for instructions on how to generate and evaluate predictions on SWE-bench [Lite, Verified, Multimodal]."
- Source: https://www.swebench.com/submit.html
