Healthcare AI GYM for Medical Agents

Benchmark Model Rank Results
question-answering-on-medqa-usmleTT-OPD (Qwen3.5-9B)#2Accuracy: 87.1
multiple-choice-question-answering-mcqa-on-medmcqaTT-OPD (Qwen3.5-9B)#7Test Set (Acc-%): 0.662