Conversational Question Answering On
评估指标
Execution Accuracy
Program 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 | Execution Accuracy | Program Accuracy |
|---|---|---|
| apollo-an-optimized-training-approach-for | 78.76 | 77.19 |
| convfinqa-exploring-the-chain-of-numerical | 68.90 | 68.24 |