# TruthfulQA

> A benchmark designed to measure whether language models produce truthful answers instead of repeating common misconceptions or misleading falsehoods.

Canonical page: https://benchlm.ai/benchmarks/truthfulqa

- Category: [Knowledge](/knowledge)
- Last updated: October 17, 2026

## About TruthfulQA

- Year: 2021
- Tasks: Truthfulness and misconception resistance
- Format: Question answering
- Difficulty: Hallucination and factuality stress test
- Paper: [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://arxiv.org/abs/2109.07958)

TruthfulQA matters because many models sound confident while repeating popular but false answers. It is a useful factuality and hallucination-adjacent benchmark even though it is older than newer factuality suites.

TruthfulQA is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (0 models)

Benchmark data for this page is coming soon.

## FAQ

### What does TruthfulQA measure?

A benchmark designed to measure whether language models produce truthful answers instead of repeating common misconceptions or misleading falsehoods.

### Which model scores highest on TruthfulQA?

No sourced model results are published for TruthfulQA on BenchLM yet.

### How many models are evaluated on TruthfulQA?

0 AI models have published results on TruthfulQA in the BenchLM catalog.

### Does TruthfulQA affect BenchLM's overall score?

Not directly. TruthfulQA is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.