Multiple Choice Question Answering Mcqa On 27
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 |
|---|---|
| scaling-language-models-methods-analysis-1 | 51.7 |
| bloomberggpt-a-large-language-model-for | 92 |
| bloomberggpt-a-large-language-model-for | 91.6 |
| bloomberggpt-a-large-language-model-for | 92 |
| palm-2-technical-report-1 | 84.8 |
| bloomberggpt-a-large-language-model-for | 92 |
| bloomberggpt-a-large-language-model-for | 70.8 |
| training-compute-optimal-large-language | 54.2 |
| palm-2-technical-report-1 | 82.4 |