TruthfulQA: leaderboard, scores and methodology
Questions designed to elicit common misconceptions and false beliefs.
Top 10
Bars are scaled to the highest observed score. The leader sets the pace; the spread below it shows how much separation exists in this benchmark.
Leaderboard
| # | Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|---|
| 1 | GPT-5.1 Max | OpenAI | 2000000 | $20.50 | 87.9 |
| 2 | Gemini 3 Pro Reasoning | Google DeepMind | 200000 | $19.69 | 87.5 |
| 3 | GPT-5.1 Reasoning | OpenAI | 400000 | $20.27 | 88.3 |
| 4 | GPT-5.2 Pro | OpenAI | 2000000 | $21.32 | 89.6 |
| 5 | GPT-5.2 | OpenAI | 2000000 | $19.71 | 88.0 |
| 6 | Gemini 3 Pro Max | Google DeepMind | 2000000 | $20.57 | 87.9 |
| 7 | Grok 4 Reasoning | xAI | 2000000 | $19.67 | 87.8 |
| 8 | Qwen3-Max Max | Alibaba Cloud | 400000 | $18.53 | 85.9 |
| 9 | GPT-5.1 | OpenAI | 2000000 | $19.01 | 86.0 |
| 10 | GPT-5.1 Turbo | OpenAI | 2000000 | $19.19 | 86.1 |
| 11 | Claude Opus 4.5 Reasoning | Anthropic | 2000000 | $20.91 | 88.2 |
| 12 | o4 Reasoning | OpenAI | 1000000 | $19.69 | 87.5 |
| 13 | Gemini 3 Pro | Google DeepMind | 2000000 | $18.24 | 86.1 |
| 14 | Grok 4 Turbo | xAI | 1000000 | $19.21 | 86.7 |
| 15 | Qwen3-Max Reasoning | Alibaba Cloud | 2000000 | $18.12 | 85.9 |
| 16 | o4 Turbo | OpenAI | 2000000 | $19.34 | 86.6 |
| 17 | Qwen3-Max Pro | Alibaba Cloud | 400000 | $18.87 | 86.2 |
| 18 | o3 Pro | OpenAI | 400000 | $17.89 | 85.8 |
| 19 | GPT-5.2 Reasoning | OpenAI | 1000000 | $20.98 | 87.5 |
| 20 | Claude Opus 4.5 | Anthropic | 400000 | $19.42 | 87.7 |
| 21 | GPT-5.2 Max | OpenAI | 1000000 | $21.39 | 89.2 |
| 22 | o4 Pro | OpenAI | 1000000 | $19.37 | 87.3 |
| 23 | Gemini 3 Pro Turbo | Google DeepMind | 400000 | $19.62 | 86.4 |
| 24 | Claude Sonnet 4.5 Turbo | Anthropic | 1000000 | $18.37 | 85.9 |
| 25 | GPT-4.1 Pro | OpenAI | 400000 | $17.56 | 85.2 |
| 26 | Claude Sonnet 4.5 Reasoning | Anthropic | 400000 | $19.48 | 87.7 |
| 27 | Gemini 3 Pro Pro | Google DeepMind | 200000 | $19.80 | 87.3 |
| 28 | Grok 4 | xAI | 200000 | $17.90 | 86.5 |
| 29 | Gemini 3 Flash Turbo | Google DeepMind | 200000 | $17.07 | 84.1 |
| 30 | Claude Sonnet 4.5 Max | Anthropic | 1000000 | $19.90 | 87.2 |
| 31 | GPT-5.2 Turbo | OpenAI | 1000000 | $20.73 | 87.4 |
| 32 | o3 Max | OpenAI | 2000000 | $17.82 | 84.8 |
| 33 | Claude Sonnet 4.5 | Anthropic | 400000 | $17.84 | 86.0 |
| 34 | Gemini 3 Flash Max | Google DeepMind | 1000000 | $17.43 | 85.0 |
| 35 | o4 Max | OpenAI | 2000000 | $19.51 | 86.2 |
| 36 | GPT-4.1 Turbo | OpenAI | 1000000 | $16.12 | 82.9 |
| 37 | Claude Opus 4.5 Max | Anthropic | 1000000 | $20.90 | 87.8 |
| 38 | Claude Opus 4.5 Vision | Anthropic | 200000 | $17.70 | 85.9 |
| 39 | GPT-5.1 Pro | OpenAI | 200000 | $19.77 | 87.8 |
| 40 | GPT-5.1 Vision | OpenAI | 400000 | $17.76 | 84.8 |
| 41 | Claude Opus 4.5 Pro | Anthropic | 200000 | $20.98 | 89.1 |
| 42 | Grok 3 Max | xAI | 2000000 | $17.66 | 85.9 |
| 43 | Gemini 3 Flash Reasoning | Google DeepMind | 128000 | $17.05 | 83.7 |
| 44 | o3 Reasoning | OpenAI | 200000 | $18.07 | 85.3 |
| 45 | DeepSeek-V3.2 Chat | DeepSeek | 1000000 | $5.80 | 82.5 |
| 46 | Qwen3-Max Turbo | Alibaba Cloud | 1000000 | $17.70 | 84.7 |
| 47 | Claude 3.7 Sonnet Reasoning | Anthropic | 128000 | $16.30 | 83.7 |
| 48 | Gemini 3 Flash Pro | Google DeepMind | 400000 | $17.71 | 84.8 |
| 49 | Claude Sonnet 4.5 Pro | Anthropic | 1000000 | $18.73 | 86.7 |
| 50 | Claude 3.7 Sonnet Pro | Anthropic | 128000 | $16.07 | 83.3 |
Methodology
TruthfulQA is included as a safety benchmark with a typical score range of 0 to 100. The values in this index are deterministic modelled estimates generated for comparison at scale. They are not official leaderboard results and should not be quoted as vendor benchmarks.
Each model receives a score derived from its capability tier, release generation and benchmark difficulty. Scores are normalised to a 0–100 scale so that models from different providers can be placed side by side. The average shown is the arithmetic mean across all 600 scored models.
Read the leaderboard as a relative map. A five-point gap is meaningful at the top and less meaningful in the middle of the distribution. Pair the score with price and context data before choosing a model.
How to use this leaderboard
- Use the top 10 to shortlist candidates, not to declare a winner.
- Check whether the leader is open weights or proprietary before assuming you can deploy it.
- Compare the score against input and output price on each model page.
- Look at the model's scores on related benchmarks before trusting a single number.
FAQ
What is TruthfulQA?
Questions designed to elicit common misconceptions and false beliefs.
Who leads TruthfulQA?
GPT-5.1 Max from OpenAI leads this index with a score of 91.1, followed by Gemini 3 Pro Reasoning at 90.3.
What is a good TruthfulQA score?
The top quartile starts around 81.2. The index average is 73.6, so a score above 81.2 is a strong result relative to this dataset.
How are TruthfulQA scores calculated?
The values are modelled estimates on a 0–100 scale, generated from capability tier, release generation and benchmark difficulty. They are not official leaderboard results.
Which models are included?
All 600 models in the index are scored on TruthfulQA, across 40 providers and every model category.