← all datasets

HealthBench-Hard

Emerging

2papers using it

92HF downloads

0HF likes

2025first seen

🤗 Hugging Face⚖ mit

Papers using HealthBench-Hard (2)

Self-Rewarding Rubric-Based Reinforcement Learning for Open-Ended Reasoning2025 · 3 cites

InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training2025

HealthBench-Hard — datasets — reinforcement-learning