# StrongREJECT

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

Evaluates jailbreak responses with a forbidden-prompt dataset and an automated judge designed to penalize empty refusals and ineffective attacks.

## Details

- Address: Online, Global
- Website: [strong-reject.github.io/](<https://strong-reject.github.io/>)
- Tags: Helpful, Science
- Category: Safety
- Status: Active
- Data licence: MIT
- Data access: open
- Grader: llm-judge
- Organization: StrongREJECT authors
- Released: 2024-02
- Paper: [arxiv.org/abs/2402.10260](<https://arxiv.org/abs/2402.10260>)
- Leaderboard: [strong-reject.github.io/](<https://strong-reject.github.io/>)
- Repository: [github.com/alexandrasouly/strongreject](<https://github.com/alexandrasouly/strongreject>)
- Task count: 313
- Top-score provenance: unknown
- ABI family: No

## Questions

### Where is StrongREJECT?

StrongREJECT is at Online, Global.

### How do I contact StrongREJECT?

To contact StrongREJECT, visit https://strong-reject.github.io/.

## 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/strongreject>)
- [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.