LetTokenBurnBenchHub

Model

Qwen-1-8B

Alibaba · open weights

qwenlm.github.io

Knowledge & Reasoning

Knowledge & Reasoning

Benchmark	Score	Metric	Harness	Source	Confidence	Link
BBH	28.2	average	N/A	Self-reported	medium	arxiv.org
BoolQ	68.0	score	N/A	Self-reported	medium	arxiv.org
LAMBADA	58.4	score	N/A	Self-reported	medium	arxiv.org
MMLU	28.2	exact_match	N/A	Self-reported	medium	arxiv.org
PIQA	73.3	score	N/A	Self-reported	medium	arxiv.org

Math

Benchmark	Score	Metric	Harness	Source	Confidence	Link
GSM8K	27.8	exact_match	N/A	Self-reported	medium	arxiv.org

Reproduced by the community