A benchmark of 817 questions that measures whether models produce truthful answers instead of repeating common misconceptions.
Browse the latest scores, model modes, release dates, and parameter sizes for TruthfulQA.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
| Rank | Model | License | |||
|---|---|---|---|---|---|
 Qwen2.5-72B Standard Mode | 60.40 | 2024-09-18 | 72.7B | Free Commercial | |
 Gemini 1.5 Pro Standard Mode | 0.00 | 2024-02-15 | Unknown | Closed | |
 Llama3.1-405B Instruct Standard Mode | 0.00 | 2024-07-23 | 405B | Free Commercial | |
4 |  Amazon Nova Pro Standard Mode | 0.00 | 2024-12-03 | Unknown | Closed |
