FLAN 137B (few-shot, k=14)

Reported on 1 benchmark across 1 task · 1 paper · 1 SOTA

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 (Easy)
Accuracy· 2021-09-03
80.7
best: 95.2 (ST-MoE-32B 269B (fine-tuned))
SOTA
Finetuned Language Models Are Zero-Shot Learners arXiv:2109.01652