List your company

Medical Reasoning on GPQA OOD

64.4AccuracyPRA (Ours)
50.25653.92857.661.272Apr 10, 2026

Evaluation results

MethodLinks
PRA (Ours)Policy=Qwen3-4B-Instruct2026.0464.4
CoTPolicy=Qwen3-4B-Instruct2026.0460.8
RAGPolicy=Qwen3-4B-Instruct2026.0459.2
RAG + SCPolicy=Qwen3-4B-Instruct2026.0454.4
CoT + SCPolicy=Qwen3-4B-Instruct2026.0451.8
DirectPolicy=Qwen3-4B-Instruct2026.0451.1
Direct + SCPolicy=Qwen3-4B-Instruct2026.0450.8