Collections
Organised by question, generated from the cards, stable addresses.
- 14
Chinese medical QA datasets with a permissive license
Huatuo_knowledge_graph_qaLingLanMedBench Traditional Chinese Medicine Benchmark Datasethuatuo26M-testdatasetsTCM-LadderHuatuoGPT2-Pretraining-InstructionHuatuoGPT2-SFT-GPT4-140K+8 - 13
Traditional Chinese medicine benchmarks
医学考试题库 JSON 数据集LingLanMedBench Traditional Chinese Medicine Benchmark Datasettmmlu++Traditional Chinese Medicine ExaminationHWTCMTCM-Ladder+7 - 4
Datasets whose license statements conflict
ESL-benchMedChatZHChatMed_Consult_DatasetShenNong_TCM_Dataset - 8
Multiple-choice evaluation sets with explanations
医学考试题库 JSON 数据集Traditional Chinese Medicine ExaminationMedMCQAmedmcqa-esCMBCMExam+2 - 8
Data reviewed by clinicians or experts
BindingDBLingLanMedBench Traditional Chinese Medicine Benchmark DatasetPubMedCausalTCM-LadderCMKGTCMBench+2 - 22
Datasets with official train and test splits
Chinese Herbal Medicine Sentiment Analysis DatasetEgoExOR: An Egocentric–Exocentric Operating Room Dataset for Comprehensive Understanding of Surgical ActivitiesLingLanMedBench Traditional Chinese Medicine Benchmark DatasetHuatuoGPT2-SFT-GPT4-140KMedMCQAmedmcqa-es+16 - 12
Benchmarks with a leaderboard or a human baseline
LingLanMedBench Traditional Chinese Medicine Benchmark DatasetMedMCQAPubMedQAR2MED Benchmarktmmlu++CMB+6 - 11
Datasets in Pharmacy
BindingDBChEMBLTopU-LBVS: Multi-Target Benchmark for Ligand-Based Virtual ScreeningATC/DDD IndexDDInterClinPGx/PharmGKB+5 - 3
Datasets in Chinese materia medica and formulas
中医药多维知识图谱HERBTCM-NER