Common Sense Reasoning On Big Bench Known
評価指標
Accuracy
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | Accuracy | Paper Title | Repository |
|---|---|---|---|
| Gopher-280B (few-shot, k=5) | 63.6 | Scaling Language Models: Methods, Analysis & Insights from Training Gopher | - |
| PaLM-540B (few-shot, k=5) | 73.9 | PaLM: Scaling Language Modeling with Pathways | - |
| Chinchilla-70B (few-shot, k=5) | 65.2 | Training Compute-Optimal Large Language Models | - |
0 of 3 row(s) selected.