Model

Phi-1.5 Web

Microsoft · open weights

Knowledge & Reasoning

Benchmark	Score	Metric	Harness	Source	Confidence	Link
BoolQ	72.8	score	N/A	Self-reported	medium	arxiv.org
PIQA	77.0	accuracy	N/A	Independent	medium	arxiv.org
WinoGrande	74.0	accuracy	N/A	Self-reported	medium	arxiv.org