| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| RMB-SafeRLHF (Target) | Seed Rubric | Accuracy69 | 4 | 4d ago | |
| RMB-SafeRLHF (Bench) | Biased Rubric Search | Accuracy85.6 | 4 | 4d ago | |
| Ultra-Problem (Target) | Seed Rubric | Accuracy61.5 | 2 | 4d ago | |
| Ultra-Problem (Bench) | Biased Rubric Search | Accuracy73 | 2 | 4d ago |