Healthcare AI GYM for Medical Agents
Open paper
Benchmark
Model
Rank
Results
question-answering-on-medqa-usmle
TT-OPD (Qwen3.5-9B)
#2
Accuracy: 87.1
multiple-choice-question-answering-mcqa-on-medmcqa
TT-OPD (Qwen3.5-9B)
#7
Test Set (Acc-%): 0.662
Rank counts only results with a code link.