Multiple Choice Question Answering Mcqa On 28
评估指标
Accuracy
评测结果
各个模型在此基准测试上的表现结果
比较表格
| 模型名称 | Accuracy |
|---|---|
| bloomberggpt-a-large-language-model-for | 86.4 |
| bloomberggpt-a-large-language-model-for | 91.2 |
| scaling-language-models-methods-analysis-1 | 50.5 |
| bloomberggpt-a-large-language-model-for | 91.2 |
| training-compute-optimal-large-language | 75.6 |
| palm-2-technical-report-1 | 93.6 |
| bloomberggpt-a-large-language-model-for | 90.4 |
| palm-2-technical-report-1 | 94.4 |
| bloomberggpt-a-large-language-model-for | 87.2 |