LetTokenBurnBenchHub

Model

OPT 66B

Vendor N/A

Knowledge & Reasoning

Knowledge & Reasoning

Benchmark	Score	Metric	Harness	Source	Confidence	Link
ARC-Challenge	44.5	accuracy	N/A	Independent	medium	arxiv.org
ARC-Easy	71.3	accuracy	N/A	Independent	medium	arxiv.org
BoolQ	76.0	score	N/A	Independent	medium	crfm.stanford.edu
BoolQ	57.5	accuracy	N/A	Independent	medium	arxiv.org
CommitmentBank	44.6	accuracy	N/A	Independent	medium	arxiv.org
commonsense_qa	66.4	accuracy	N/A	Independent	medium	arxiv.org
HellaSwag	74.5	overall_accuracy	N/A	Independent	medium	crfm.stanford.edu
HellaSwag	73.5	accuracy	N/A	Independent	medium	arxiv.org
MMLU	36.0	average_(%)	N/A	Independent	medium	arxiv.org
MultiRC	18.8	f1	N/A	Independent	medium	arxiv.org
OpenBookQA	58.0	accuracy	N/A	Independent	medium	arxiv.org
PIQA	77.6	accuracy	N/A	Independent	medium	arxiv.org
RTE	54.9	accuracy	N/A	Independent	medium	arxiv.org
WinoGrande	66.1	accuracy	N/A	Independent	medium	arxiv.org

Math

Benchmark	Score	Metric	Harness	Source	Confidence	Link
GSM8K	1.8	exact_match	N/A	Independent	medium	crfm.stanford.edu

Multimodal

Benchmark	Score	Metric	Harness	Source	Confidence	Link
COPA	86.0	accuracy	N/A	Independent	medium	arxiv.org

Reproduced by the community