HELM Classic - BoolQ — leaderboard

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

Top models

#ModelScore
1Llama 2 70B88.6
2text-davinci-00388.13
3text-davinci-00287.7
4Mistral-7B-v0.187.4
5LLaMA-65B87.1
6GPT-3.5 Turbo (0613)87
7LLaMA-30B86.1
8falcon-40B81.9
9Llama 2 13B81.1
10alpaca-7B77.8
11Llama 2 7B76.2
12LLaMA-7B75.6
13falcon-7B75.3
14GPT-3.5 Turbo (0301)74
15davinci72.23

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