GLaM 64B/64E (1 shot)

Reported on 1 benchmark across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing1 result

Common Sense ReasoningonARC (Challenge)
Accuracy· uses extra data· 2021-12-13
48.2
best: 96.4 (GPT-4 (few-shot, k=25))
GLaM: Efficient Scaling of Language Models with Mixture-of-Experts arXiv:2112.06905