Common Sense Reasoning On Big Bench Winowhy
평가 지표
Accuracy
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | Accuracy | Paper Title | Repository |
|---|---|---|---|
| PaLM-62B (few-shot, k=5) | 61.0 | PaLM: Scaling Language Modeling with Pathways | - |
| PaLM-540B (few-shot, k=5) | 65.9 | PaLM: Scaling Language Modeling with Pathways | - |
| Gopher-280B (few-shot, k=5) | 56.7 | Scaling Language Models: Methods, Analysis & Insights from Training Gopher | - |
| Chinchilla-70B (few-shot, k=5) | 62.5 | Training Compute-Optimal Large Language Models | - |
0 of 4 row(s) selected.