HELM Classic - TruthfulQA: leaderboard
The "TruthfulQA" subtask of HELM Classic. A scenario from Stanford HELM Classic, the holistic evaluation suite scoring language models across accuracy, robustness and calibration on a broad set of tasks.
Metric: Exact Match (%). Source: crfm.stanford.edu. Saturation forecast: Estimated already saturated. 67 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Palmyra X (43B) | 61.57 | #1317 |
| 2 | text-davinci-002 | 60.96 | #1225 |
| 3 | text-davinci-003 | 59.33 | #1146 |
| 4 | Llama 2 70B | 55.35 | #1201 |
| 5 | LLaMA-65B | 50.76 | #1303 |
| 6 | Mistral-7B-v0.1 | 42.2 | #1326 |
| 7 | vicuna-13B-v1.3 | 38.53 | #1447 |
| 8 | falcon-40B Instruct | 38.38 | #1458 |
| 9 | falcon-40B | 35.32 | #1442 |
| 10 | LLaMA-30B | 34.4 | #1423 |
| 11 | GPT-3.5 Turbo (0613) | 33.94 | #1118 |
| 12 | Llama 2 13B | 33.03 | #1436 |
| 13 | LLaMA-13B | 32.42 | #1516 |
| 14 | vicuna-7B-v1.3 | 29.2 | #1507 |
| 15 | LLaMA-7B | 27.98 | #1564 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=helm-classic-truthfulqa · How It Works · Data refreshed daily, snapshot 2026-10-20.