Multiple Choice Question Answering Mcqa On 29
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
比較表
| モデル名 | Accuracy |
|---|---|
| palm-2-technical-report-1 | 68.8 |
| bloomberggpt-a-large-language-model-for | 42 |
| scaling-language-models-methods-analysis-1 | 51.1 |
| bloomberggpt-a-large-language-model-for | 50 |
| bloomberggpt-a-large-language-model-for | 62.4 |
| palm-2-technical-report-1 | 91.2 |
| bloomberggpt-a-large-language-model-for | 42 |
| bloomberggpt-a-large-language-model-for | 45.2 |
| training-compute-optimal-large-language | 52.6 |