FLAN 137B (few-shot, k=10)

Reported on 2 benchmarks 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 Processing2 results

Question AnsweringonStoryCloze
Accuracy· 2021-09-03
94.7
best: 96.3 (BLOOMZ)
SOTA
Finetuned Language Models Are Zero-Shot Learners arXiv:2109.01652
Question AnsweringonPIQA
Accuracy· 2021-09-03
81.7
best: 90.1 (Unicorn 11B (fine-tuned))
Finetuned Language Models Are Zero-Shot Learners arXiv:2109.01652