Tag
hendrycks
3 verified claims carrying this tag. Each has 2+ primary sources and an HMAC-SHA256 signature.
MMLU benchmark introduced in paper: Measuring Massive Multitask Language Understanding (Hendrycks et al., 2020).
428d754e7c651be6 · 2 sources · 100% confidence
MATH dataset introduced in paper: Measuring Mathematical Problem Solving With the MATH Dataset (Hendrycks et al., 2021).
8c1f847ae98570da · 3 sources · 92% confidence
GELU (Gaussian Error Linear Unit) introduced in paper: Gaussian Error Linear Units (GELUs) (Hendrycks & Gimpel, 2016).
fbd32ca73f2746c9 · 2 sources · 82% confidence