Datasets › TruthfulQA
TruthfulQA
TruthfulQA is a benchmark to measure whether a language model is truthful in generating answers to questions. The benchmark comprises 817 questions that span 38 categories, including health, law, finance and politics. The authors crafted questions that some humans would answer falsely due to a false belief or misconception.
Image source: https://arxiv.org/pdf/2109.07958v1.pdf
Benchmarks archive 2025-07-28
All 3 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.
| First row (archive order) | Paper | Code | ||||
|---|---|---|---|---|---|---|
| Question Answering | TruthfulQA | GPT-4 (RLHF) MC1 0.59 | GPT-4 Technical Report | openai/evals +10 | 33 | Compare |
| Text Generation | TruthfulQA (0-shot) | no rows | — | — | 0 | Compare |
| Text Generation | TruthfulQA TR v0.2 | no rows | — | — | 0 | Compare |
Papers archive 2025-07-28
11 shown of 11 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 607. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.
Dataset loaders archive 2025-07-28
8 loaders as listed in the archive; links are outbound and not re-checked here.
Tasks archive 2025-07-28
License archive 2025-07-28
Unknown
Modalities archive 2025-07-28
No modality tagged.
Languages archive 2025-07-28
No language tagged.
Variants archive 2025-07-28
- TruthfulQA
- TruthfulQA (0-shot)
- TruthfulQA TR v0.2
- TruthfulQA TR
4 variant names, as the archive lists them.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections