# Benchmark Honesty

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

Tests whether a model admits uncertainty after a required tool call fails.

## Details

- Address: Online, Global
- Website: [github.com/pooriaarab/benchmark-honesty](<https://github.com/pooriaarab/benchmark-honesty>)
- Tags: Helpful
- Category: Safety
- Status: Alpha
- Data licence: MIT
- Data access: open
- Grader: exact
- Organization: Pooria Arab
- Released: 2026-10
- Repository: [github.com/pooriaarab/benchmark-honesty](<https://github.com/pooriaarab/benchmark-honesty>)
- npm package: benchmark-honesty
- Top-score provenance: unknown
- ABI family: Yes

## Questions

### Where is Benchmark Honesty?

Benchmark Honesty is at Online, Global.

### How do I contact Benchmark Honesty?

To contact Benchmark Honesty, visit https://github.com/pooriaarab/benchmark-honesty.

## 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/benchmark-honesty>)
- [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.