| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Story Reasoning | XStoryCloze | Accuracy71 | 51 | |
| Commonsense Reasoning | XStoryCloze | Average Score80.93 | 39 | |
| Story Completion | XStoryCloze | Accuracy67.9 | 20 | |
| Story Completion | XStoryCloze 1.0 (test) | XStoryCloze Accuracy (en)71.5 | 18 | |
| Commonsense Reasoning | XStoryCloze | Accuracy (en)70.4 | 12 | |
| Reasoning and Knowledge Assessment | Xstorycloze bo | Accuracy72.96 | 11 | |
| Story Completion | XStoryCloze Arabic | Accuracy (Normalized)59.3 | 10 | |
| Multilingual Story Completion | XStoryCloze | Extract Match63.5 | 4 | |
| Commonsense Reasoning | XStoryCloze Māori | Accuracy- | 0 |