Model

text-davinci-003

OpenAI · closed weights

Knowledge & Reasoning

Benchmark	Score	Metric	Harness	Source	Confidence	Link
BoolQ	88.1	score	N/A	Independent	medium	crfm.stanford.edu
HellaSwag	85.5	overall_accuracy	N/A	Independent	medium	arxiv.org

Benchmark	Score	Metric	Harness	Source	Confidence	Link
GSM8K	78.2	exact_match	N/A	Independent	medium	arxiv.org
TheoremQA	22.8	accuracy	N/A	Independent	medium	arxiv.org

Benchmark	Score	Metric	Harness	Source	Confidence	Link
MGSM	36.0	average_(%)	N/A	Independent	medium	arxiv.org