Crass Ai On Big Bench
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 |
|---|---|---|---|
| Orca 2-13B | 86.86 | Orca 2: Teaching Small Language Models How to Reason | - |
| Gopher-280B (few-shot, k=5) | 56.8 | Scaling Language Models: Methods, Analysis & Insights from Training Gopher | |
| Orca 2-7B | 84.31 | Orca 2: Teaching Small Language Models How to Reason | - |
| Chinchilla-70B (few-shot, k=5) | 75.0 | Training Compute-Optimal Large Language Models |
0 of 4 row(s) selected.