| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Calibration | MSciNLI | Expected Calibration Error (ECE)3.75 | 22 | |
| Natural Language Inference | MSciNLI | ECE2.08 | 16 | |
| Classification | MSciNLI | Expected Calibration Error (ECE)1.52 | 16 | |
| Natural Language Inference | MSciNLI | AUROC68.27 | 5 | |
| Scientific Natural Language Inference | MSCINLI (test) | Macro F1 (Hardware)77.41 | 4 |