Model

text-davinci-001

OpenAI · closed weights

Knowledge & Reasoning

Benchmark	Score	Metric	Harness	Source	Confidence	Link
ANLI	35.4	score	N/A	Independent	medium	arxiv.org
BoolQ	77.5	score	N/A	Independent	medium	arxiv.org
HellaSwag	79.3	overall_accuracy	N/A	Independent	medium	arxiv.org
LAMBADA	86.4	score	N/A	Independent	medium	arxiv.org
MMLU	43.9	exact_match	N/A	Independent	medium	arxiv.org
OpenBookQA	65.4	accuracy	N/A	Independent	medium	arxiv.org
PIQA	82.3	score	N/A	Independent	medium	arxiv.org
ScienceQA	74.0	score	N/A	Independent	medium	scienceqa.github.io
SuperGLUE	71.8	score	N/A	Independent	medium	arxiv.org
Trivia QA	71.2	exact_match	N/A	Independent	medium	arxiv.org
WinoGrande	77.7	accuracy	N/A	Independent	medium	arxiv.org