# TruthfulQA

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

Tests whether language models reproduce common human misconceptions and falsehoods when answering questions.

## Details

- Address: Online, Global
- Website: [github.com/sylinrl/TruthfulQA](<https://github.com/sylinrl/TruthfulQA>)
- Tags: Helpful, Viral, Science
- Category: Reasoning
- Status: Active
- Data licence: Apache-2.0
- Data access: open
- Grader: mixed
- Organization: TruthfulQA authors
- Released: 2021-09
- Paper: [arxiv.org/abs/2109.07958](<https://arxiv.org/abs/2109.07958>)
- Repository: [github.com/sylinrl/TruthfulQA](<https://github.com/sylinrl/TruthfulQA>)
- Task count: 817
- Top-score provenance: unknown
- ABI family: No

## Questions

### Where is TruthfulQA?

TruthfulQA is at Online, Global.

### How do I contact TruthfulQA?

To contact TruthfulQA, visit https://github.com/sylinrl/TruthfulQA.

## 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/truthfulqa>)
- [Reasoning in Online](<https://aibenchmarkindex.com/global/online/category/reasoning.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.