HELM Classic - WikiFact — leaderboard
Metric: Exact Match (%). Source: crfm.stanford.edu. 67 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Llama 2 70B | 44.92 |
| 2 | LLaMA-65B | 42.08 |
| 3 | text-davinci-002 | 39.25 |
| 4 | falcon-40B | 38.03 |
| 5 | text-davinci-003 | 37.34 |
| 6 | mpt-30B | 36.93 |
| 7 | Llama 2 13B | 36.47 |
| 8 | Mistral-7B-v0.1 | 34.87 |
| 9 | Llama 2 7B | 33.49 |
| 10 | falcon-7B | 30.87 |
| 11 | davinci | 30.61 |
| 12 | GPT-3.5 Turbo (0613) | 28.86 |
| 13 | GPT-3.5 Turbo (0301) | 27.93 |
| 14 | LLaMA-30B | 27.54 |
| 15 | LLaMA-13B | 23.27 |
Interactive version: theaggregate.ai/benchmark?slug=helm-classic-wikifact · How the rankings work · Data refreshed daily, snapshot 2026-07-22.