baichuan-inc/Baichuan-M2-32B

Baichuan-M2-32B is Baichuan AI's 32 billion parameter medical-enhanced reasoning model, built upon Qwen2.5-32B. It integrates an innovative Large Verifier System and medical domain adaptation through Mid-Training and multi-stage reinforcement learning. This model is specifically optimized for real-world medical reasoning tasks, achieving leading performance among open-source medical models on HealthBench while maintaining strong general capabilities.