| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Causal Reasoning | XCOPA | Accuracy94.4 | 33 | |
| Commonsense Reasoning | XCOPA | Accuracy74.5 | 24 | |
| Causal Reasoning | XCOPA (test) | Accuracy (id)97.2 | 13 | |
| Causal Reasoning | XCOPA | Accuracy (zh)55.5 | 12 | |
| Natural Language Understanding | XCOPA 1.0 (test) | Accuracy54.5 | 11 | |
| Performance Prediction | XCOPA | MAE1.96 | 9 | |
| Zero-shot performance prediction | XCOPA | MAE2.59 | 9 | |
| Causal Reasoning | XCOPA ET | Accuracy71.8 | 8 | |
| Multilingual Reasoning | XCOPA | Accuracy73 | 6 | |
| Causal Reasoning | XCOPA | XCOPA ET Accuracy57 | 6 | |
| Commonsense Reasoning | XCOPA (test) | Language Democratization99.31 | 4 | |
| Causal Reasoning | XCOPA Thai | Accuracy60 | 3 | |
| Commonsense Reasoning | XCOPA Indonesian | Accuracy60 | 3 | |
| Commonsense Reasoning | XCOPA 74 (test) | Score- | 0 | |
| Causal Reasoning | XCOPA Māori | Accuracy- | 0 |