| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Bias-in-Bios | MCC0.9731 | 12 | 1mo ago | ||
| TruthfulQA | MCC0.7758 | 12 | 1mo ago | ||
| CORR (2, 1) | SSAE | MCC90.47 | 12 | 1mo ago | |
| BINARY (2, 2) | SSAE | MCC0.8896 | 12 | 1mo ago | |
| LANG (1, 1) | SSAE | MCC0.9121 | 12 | 1mo ago | |
| Refusal | MCC0.9 | 6 | 1mo ago | ||
| Sycophancy | MCC1 | 6 | 1mo ago | ||
| GENDER (1, 1) | SSAE | MCC90.18 | 6 | 1mo ago |