Model

code-davinci-002

Vendor N/A

Math

Benchmark	Score	Metric	Harness	Source	Confidence	Link
GSM8K	56.8	exact_match	N/A	Independent	medium	crfm.stanford.edu
TheoremQA	23.9	accuracy	N/A	Independent	medium	arxiv.org

Benchmark	Score	Metric	Harness	Source	Confidence	Link
MGSM	35.0	average_(%)	N/A	Independent	medium	arxiv.org