| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Helpfulness | AdvGLUE | Accuracy75.15 | 20 | |
| Binary classification | AdvGLUE (test) | QNLI Accuracy0.701 | 17 | |
| Natural Language Understanding | AdvGLUE | RTE Accuracy67.9 | 8 | |
| Adversarial Robustness | AdvGLUE (test) | AdvGLUE Score76.73 | 6 |