# Do-Not-Answer

Do-Not-Answer is an AI benchmark; this page records what it measures and traces its data, grader, and scores to primary sources.

Evaluates whether language models decline risky instructions while still answering harmless requests.

## Details

- Address: Online, Global
- Website: [github.com/Libr-AI/do-not-answer](<https://github.com/Libr-AI/do-not-answer>)
- Tags: Helpful, Science
- Category: Safety
- Status: Active
- Data licence: Apache-2.0
- Data access: open
- Grader: mixed
- Organization: Libr-AI
- Released: 2023-08
- Repository: [github.com/Libr-AI/do-not-answer](<https://github.com/Libr-AI/do-not-answer>)
- Task count: 939
- Top-score provenance: unknown
- ABI family: No

## Questions

### Where is Do-Not-Answer?

Do-Not-Answer is at Online, Global.

### How do I contact Do-Not-Answer?

To contact Do-Not-Answer, visit https://github.com/Libr-AI/do-not-answer.

## 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/do-not-answer>)
- [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.