SOTA Comment Prediction on HealthBench (test) and PapersWithCode

7.31Medical Chat Annotation Score

Feedback-to-Rubrics

Updated 1mo ago

Evaluation Results

Method	Links
Feedback-to-Rubrics 2026.05		7.31
Iterative rubric refinement 2026.05		7.15
Top-3 RAG with LLM 2026.05		7.08
Initial rubric 2026.05		6.72
No rubric 2026.05		6.62
Top-1 retrieval 2026.05		0.2