| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| ExpertLongBench (test) | Feedback-to-Rubrics | Bio Score2.75 | 6 | 1mo ago | |
| HealthBench (test) | Feedback-to-Rubrics | Medical Chat Annotation Score7.31 | 6 | 1mo ago | |
| Essay Review (test) | Feedback-to-Rubrics | Essay Review Score8.71 | 6 | 1mo ago | |
| Research Proposal Review (test) | Feedback-to-Rubrics | Review Score3.42 | 6 | 1mo ago | |
| Surface 1 (eval) | CMSL | NE Change-0.62 | 1 | 26d ago | |
| Surface 1 (train) | CMSL | NE Change (%)-0.54 | 1 | 26d ago |
