| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Natural Questions (NQ) In-Domain | EliCal | AUROC85.16 | 33 | 3mo ago | |
| HHH alignment | AMBS | Win Rate (WR)86.1 | 20 | 15d ago | |
| HonestyBench OOD | Cal-Only | Squad Score81.19 | 13 | 3mo ago | |
| HonestyBench In-Domain | EliCal | NQ Score85.16 | 13 | 3mo ago | |
| OOD Aggregate Average | EliCal | AUROC0.8447 | 3 | 3mo ago | |
| In-Domain Aggregate Average | EliCal | AUROC84.36 | 3 | 3mo ago |