HELM Classic - WikiFact — leaderboard

Metric: Exact Match (%). Source: crfm.stanford.edu. 67 models tracked.

Top models

#ModelScore
1Llama 2 70B44.92
2LLaMA-65B42.08
3text-davinci-00239.25
4falcon-40B38.03
5text-davinci-00337.34
6mpt-30B36.93
7Llama 2 13B36.47
8Mistral-7B-v0.134.87
9Llama 2 7B33.49
10falcon-7B30.87
11davinci30.61
12GPT-3.5 Turbo (0613)28.86
13GPT-3.5 Turbo (0301)27.93
14LLaMA-30B27.54
15LLaMA-13B23.27

Interactive version: theaggregate.ai/benchmark?slug=helm-classic-wikifact · How the rankings work · Data refreshed daily, snapshot 2026-07-22.