PaLM 62B (zero-shot)

Reported on 3 benchmarks across 2 tasks · 1 paper

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

Natural Language Processing3 results

Reading ComprehensiononRACE
Accuracy (High)· 2022-04-05
47.5
best: 92.6 (ALBERTxxlarge+DUMA(ensemble))
PaLM: Scaling Language Modeling with Pathways arXiv:2204.02311
Reading ComprehensiononRACE
Accuracy (Middle)· 2022-04-05
64.3
best: 93.1 (Megatron-BERT (ensemble))
PaLM: Scaling Language Modeling with Pathways arXiv:2204.02311
Question AnsweringonOBQA
Accuracy· 2022-04-05
50.4
best: 78.4 (FLAN 137B (zero-shot))
PaLM: Scaling Language Modeling with Pathways arXiv:2204.02311