FLAN 137B (0-shot)

Reported on 5 benchmarks across 3 tasks · 1 paper

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

Natural Language Processing5 results

Question AnsweringonPIQA
Accuracy· 2021-09-03
80.5
best: 90.1 (Unicorn 11B (fine-tuned))
Finetuned Language Models Are Zero-Shot Learners arXiv:2109.01652
Question AnsweringonBoolQ
Accuracy· 2021-09-03
82.9
best: 99.87 (Mistral-Nemo 12B (HPT))
Finetuned Language Models Are Zero-Shot Learners arXiv:2109.01652
Common Sense ReasoningonWinoGrande
Accuracy· 2021-09-03
71.2
best: 96.1 (ST-MoE-32B 269B (fine-tuned))
Finetuned Language Models Are Zero-Shot Learners arXiv:2109.01652
Common Sense ReasoningonARC (Easy)
Accuracy· 2021-09-03
79.6
best: 95.2 (ST-MoE-32B 269B (fine-tuned))
Finetuned Language Models Are Zero-Shot Learners arXiv:2109.01652
Sentence CompletiononHellaSwag
Accuracy· 2021-09-03
56.7
best: 96.1 (CompassMTL 567M with Tailor)
Finetuned Language Models Are Zero-Shot Learners arXiv:2109.01652