Multiple Choice Question Answering Mcqa On 20
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 (few-shot, k=5) | 50 | Galactica: A Large Language Model for Science | - |
| OPT (few-shot, k=5) | 43.5 | Galactica: A Large Language Model for Science | - |
| Chinchilla (few-shot, k=5) | 58.8 | Galactica: A Large Language Model for Science | - |
| GAL 120B (zero-shot) | 41.2 | Galactica: A Large Language Model for Science | - |
| BLOOM (few-shot, k=5) | 19.4 | Galactica: A Large Language Model for Science | - |
0 of 5 row(s) selected.