Model

Qwen2.5-Coder-7B

Alibaba · open weights

Knowledge & Reasoning

Benchmark	Score	Metric	Harness	Source	Confidence	Link
HellaSwag	76.8	overall_accuracy	N/A	Self-reported	medium	arxiv.org
MMLU	68.0	exact_match	N/A	Self-reported	medium	arxiv.org
WinoGrande	72.9	accuracy	N/A	Self-reported	medium	arxiv.org

Benchmark	Score	Metric	Harness	Source	Confidence	Link
GSM8K	86.7	exact_match	N/A	Self-reported	medium	arxiv.org

Benchmark	Score	Metric	Harness	Source	Confidence	Link
SCCGBench	0.7	mock	N/A	Independent	medium	arxiv.org

Benchmark	Score	Metric	Harness	Source	Confidence	Link
MINTEval	0.1	actionmatch	N/A	Independent	medium	arxiv.org