Model

Muse Spark

Meta AI

Knowledge & Reasoning

Benchmark	Score	Metric	Harness	Source	Confidence	Link
CritPt	11.3	accuracy	N/A	Independent	low	epoch.ai
GPQA Diamond	89.8	accuracy	N/A	Independent	high	epoch.ai
HLE	40.6	accuracy	N/A	Independent	low	epoch.ai

Benchmark	Score	Metric	Harness	Source	Confidence	Link
SciCode	51.5	score	N/A	Independent	medium	artificialanalysis.ai