Question Answering On Convfinqa
评估指标
Execution 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 |
|---|---|
| are-chatgpt-and-gpt-4-general-purpose-solvers | 46.90 |
| convfinqa-exploring-the-chain-of-numerical | 68.9 |
| are-chatgpt-and-gpt-4-general-purpose-solvers | 76.48 |