GPT-3 175B (zero-shot)

Reported on 2 benchmarks across 2 tasks · 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 AnsweringonOBQA
Accuracy· 2020-05-28
57.6
best: 78.4 (FLAN 137B (zero-shot))
SOTA
Language Models are Few-Shot Learners arXiv:2005.14165
Reading ComprehensiononRACE
Accuracy (High)· 2020-05-28
45.5
best: 92.6 (ALBERTxxlarge+DUMA(ensemble))
Language Models are Few-Shot Learners arXiv:2005.14165