TruthfulQA
truthfulnessPending Verification
Measures a model's tendency to reproduce falsehoods commonly believed by humans.
Published: 2021
Score Range: 0-100
Top Score: 68.7
TruthfulQA Leaderboard
| Rank | Model | Provider | Score | Parameters | Released | Type |
|---|---|---|---|---|---|---|
| 1 | Gemma 3 | 68.7 | 1B, 4B, 12B, 27B | 2025-03-12 | Multimodal |
About TruthfulQA
Methodology
TruthfulQA evaluates model performance using a standardized scoring methodology. Scores are reported on a scale of 0 to 100, where higher scores indicate better performance. For detailed information about the scoring system and methodology, please refer to the original paper.
Publication
This benchmark was published in 2021.Read the full paper