LetTokenBurnBenchHub

Model

GPT-3

OpenAI · closed weights

Knowledge & Reasoning

Knowledge & Reasoning

Benchmark	Score	Metric	Harness	Source	Confidence	Link
ARC-Challenge	51.4	accuracy	N/A	Independent	medium	arxiv.org
ARC-Easy	68.8	accuracy	N/A	Independent	medium	arxiv.org
HellaSwag	78.9	accuracy	N/A	Independent	medium	arxiv.org
RAFT	62.7	avg	N/A	Independent	medium	arxiv.org
The Pile	0.7	bits_per_byte	N/A	Independent	medium	arxiv.org

Math

Benchmark	Score	Metric	Harness	Source	Confidence	Link
MAWPS	19.8	accuracy_(%)	N/A	Independent	medium	paperswithcode.com

Reproduced by the community