| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| SciQA | PR-AUC44 | 19 | 1mo ago | ||
| StrQA | PR-AUC52.7 | 19 | 1mo ago | ||
| Calendar | ReProbe, Hidden States, GPT-OSS-anno | PR-AUC69.8 | 19 | 1mo ago | |
| Meetings | ReProbe, Hidden States, GPT-OSS-anno | PR-AUC73.4 | 19 | 1mo ago | |
| Trips | Qwen2.5-Math-7B-PRM800k | PR-AUC82.5 | 19 | 1mo ago | |
| ProofNet | ReProbe, Hidden States, GPT-OSS-anno | PR-AUC68.2 | 19 | 1mo ago | |
| GSM8k | Qwen2.5-Math-PRM-7B | PR-AUC93 | 19 | 1mo ago | |
| Aggregate ID/OOD | Qwen2.5-Math-7B-PRM800k | ID Score37.3 | 13 | 1mo ago |
