Model

GPT-J

OpenAI · closed weights

Knowledge & Reasoning

Benchmark	Score	Metric	Harness	Source	Confidence	Link
BoolQ	64.9	score	N/A	Independent	medium	crfm.stanford.edu
HellaSwag	66.3	overall_accuracy	N/A	Independent	medium	crfm.stanford.edu

Benchmark	Score	Metric	Harness	Source	Confidence	Link
GSM8K	3.6	exact_match	N/A	Independent	medium	crfm.stanford.edu
MAWPS	9.9	accuracy_(%)	N/A	Independent	medium	arxiv.org
ParaMAWPS	5.9	accuracy_(%)	N/A	Independent	medium	arxiv.org