PaLM 540B (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
- Accuracy (High)· 2022-04-0549.1best: 92.6 (ALBERTxxlarge+DUMA(ensemble))
- Accuracy (Middle)· 2022-04-0568.1best: 93.1 (Megatron-BERT (ensemble))
- Accuracy· 2022-04-0553.4best: 78.4 (FLAN 137B (zero-shot))