| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| AIME 1983–2024 | Master-RM 7B | Average False Positive Rate0 | 12 | 1mo ago | |
| MATH | Master-RM 7B | Average FPR0 | 12 | 1mo ago | |
| GSM8K | Master-RM 7B | Average False Positive Rate0 | 12 | 1mo ago | |
| NaturalReasoning | Master-RM 7B | Average FPR0.7 | 12 | 1mo ago | |
| RLVR Multi-subject | Master-RM 7B | Average FPR (%)0 | 12 | 1mo ago |