# CyberSecEval

CyberSecEval is an AI benchmark; this page records what it measures and traces its data, grader, and scores to primary sources.

Evaluates cybersecurity risks from model-generated code and responses to requests that could enable cyberattacks.

## Details

- Address: Online, Global
- Website: [github.com/meta-llama/PurpleLlama](<https://github.com/meta-llama/PurpleLlama>)
- Tags: Helpful, Viral, Science
- Category: Safety
- Status: Active
- Data licence: MIT
- Data access: open
- Grader: mixed
- Organization: Meta
- Released: 2023-12
- Paper: [ai.meta.com/research/publications/purple-llama-cyberseceval-a-benchmark-for-evaluating-the-cybersecurity-risks-of-large-language-models/](<https://ai.meta.com/research/publications/purple-llama-cyberseceval-a-benchmark-for-evaluating-the-cybersecurity-risks-of-large-language-models/>)
- Repository: [github.com/meta-llama/PurpleLlama](<https://github.com/meta-llama/PurpleLlama>)
- Top-score provenance: unknown
- ABI family: No

## Questions

### Where is CyberSecEval?

CyberSecEval is at Online, Global.

### How do I contact CyberSecEval?

To contact CyberSecEval, visit https://github.com/meta-llama/PurpleLlama.

## Source

From [Benchmark primary sources](https://aibenchmarkindex.com/about), license CC0-1.0, checked 2026-10-15.

Last updated October 15, 2026.

## Links

- This benchmark on the [web page](<https://aibenchmarkindex.com/global/online/cyberseceval>)
- [Safety in Online](<https://aibenchmarkindex.com/global/online/category/safety.md>)
- [More benchmarks in Online](<https://aibenchmarkindex.com/global/online.md>)

> **Check before you compare.** Benchmark methods and leaderboards change. Follow the cited primary source before using a result in a decision.