Logical Reasoning On Ruworldtree
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 |
|---|---|---|---|
| RuGPT-3 Medium | 38.0 | TAPE: Assessing Few-shot Russian Language Understanding | - |
| Human benchmark | 83.7 | TAPE: Assessing Few-shot Russian Language Understanding | - |
| RuGPT-3 Small | 34.0 | TAPE: Assessing Few-shot Russian Language Understanding | - |
| RuGPT-3 Large | 40.7 | TAPE: Assessing Few-shot Russian Language Understanding | - |
0 of 4 row(s) selected.