结果
| Metric | Dev (1534 questions) | Test (1789 questions) |
|---|---|---|
| Execution Accuracy (EX) | 78.10% | 82.39% |
| R-VES | — | 77.69% |
方法概述
More details to be released soon in arxiv preview.
| Metric | Dev (1534 questions) | Test (1789 questions) |
|---|---|---|
| Execution Accuracy (EX) | 78.10% | 82.39% |
| R-VES | — | 77.69% |
More details to be released soon in arxiv preview.