LetTokenBurnBenchHub

Model

UL2 20B

Vendor N/A

Knowledge & Reasoning

Knowledge & Reasoning

Benchmark	Score	Metric	Harness	Source	Confidence	Link
ARC-Challenge	42.9	accuracy	N/A	Independent	medium	arxiv.org
ARC-Challenge	29.8	accuracy	N/A	Independent	medium	arxiv.org
ARC-Easy	38.4	accuracy	N/A	Independent	medium	arxiv.org
ARC-Easy	32.2	accuracy	N/A	Independent	medium	arxiv.org
BoolQ	63.1	accuracy	N/A	Independent	medium	arxiv.org
commonsense_qa	51.4	accuracy	N/A	Independent	medium	arxiv.org
commonsense_qa	34.2	accuracy	N/A	Independent	medium	arxiv.org
MMLU	39.2	average_(%)	N/A	Independent	medium	arxiv.org
RTE	60.7	accuracy	N/A	Independent	medium	arxiv.org
WiC	49.8	accuracy	N/A	Independent	medium	arxiv.org
WSC	79.9	accuracy	N/A	Independent	medium	arxiv.org

Math

Benchmark	Score	Metric	Harness	Source	Confidence	Link
GSM8K	4.4	accuracy	N/A	Independent	medium	arxiv.org
GSM8K	4.1	accuracy	N/A	Independent	medium	arxiv.org

Multimodal

Benchmark	Score	Metric	Harness	Source	Confidence	Link
COPA	85.0	accuracy	N/A	Independent	medium	arxiv.org

Reproduced by the community