| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| m-ARC | NAVCA | Pearson Correlation0.9847 | 13 | 4d ago | |
| m-MMLU | NASCA | Pearson Correlation (r)0.9849 | 6 | 4d ago | |
| Belebele | MEXA | Pearson Correlation0.9745 | 4 | 4d ago | |
| Tasks sensitive to language variation | logistic regression | Pearson Correlation0.84 | 3 | 4d ago | |
| Tasks robust to language variation | logistic regression | Pearson Correlation (r)0.85 | 3 | 4d ago |