Model

Qwen2.5-Coder-0.5B

Alibaba · open weights

Knowledge & Reasoning

Benchmark	Score	Metric	Harness	Source	Confidence	Link
HellaSwag	48.4	overall_accuracy	N/A	Self-reported	medium	arxiv.org
MMLU	42.0	exact_match	N/A	Self-reported	medium	arxiv.org
WinoGrande	54.8	accuracy	N/A	Self-reported	medium	arxiv.org

Benchmark	Score	Metric	Harness	Source	Confidence	Link
GSM8K	34.5	exact_match	N/A	Self-reported	medium	arxiv.org