# Datasets with official train and test splits

Results on the official test split are comparable across papers. 22 entries.


- [Chinese Herbal Medicine Sentiment Analysis Dataset](https://mdexa.com/datasets/chinese-herbal-medicine-sentiment/) — Permissive · Link only · scraped · 2026-11-14
- [EgoExOR: An Egocentric–Exocentric Operating Room Dataset for Comprehensive Understanding of Surgical Activities](https://mdexa.com/datasets/egoexor/) — Permissive · Link only · 2026-11-14
- [LingLanMedBench Traditional Chinese Medicine Benchmark Dataset](https://mdexa.com/datasets/linglan/) — Permissive · Link only · exam-derived · 2026-11-14
- [HuatuoGPT2-SFT-GPT4-140K](https://mdexa.com/datasets/huatuogpt2-sft-gpt4-140k/) — Permissive · Link only · derived, model-generated · 2026-11-14
- [MedMCQA](https://mdexa.com/datasets/medmcqa/) — Permissive · Link only · exam-derived, scraped · 2026-11-14
- [medmcqa-es](https://mdexa.com/datasets/medmcqa-es/) — Permissive · Link only · 2026-11-14
- [MedQA (USMLE 4-option, US subset + English textbook corpus)](https://mdexa.com/datasets/medqa-2/) — Permissive · Link only · derived, exam-derived · 2026-11-14
- [PubMedCausal](https://mdexa.com/datasets/pubmedcausal/) — Permissive · Link only · 2026-11-14
- [tmmlu++](https://mdexa.com/datasets/tmmluplus/) — Permissive · Link only · 2026-11-14
- [TopU-LBVS: Multi-Target Benchmark for Ligand-Based Virtual Screening](https://mdexa.com/datasets/topu-lbvs/) — Permissive · Link only · derived · 2026-11-14
- [CMB (Chinese Medical Benchmark)](https://mdexa.com/datasets/cmb/) — Permissive · Link only · exam-derived · 2026-11-12
- [CMtMedQA](https://mdexa.com/datasets/cmtmedqa/) — Permissive · Link only · real-patient-text · 2026-11-12
- [jablonkagroup/chempile-lift](https://mdexa.com/datasets/chempile-lift/) — Restricted · Link only · 2026-11-14
- [PMC-Patients-ReCDS](https://mdexa.com/datasets/pmc-patients-recds/) — Restricted · Link only · derived, real-patient-text · 2026-11-14
- [THEMol: Torsion, Hessian, Energy of Molecules](https://mdexa.com/datasets/themol/) — Restricted · Link only · 2026-11-14
- [cMedQA2](https://mdexa.com/datasets/cmedqa2/) — Restricted · Link only · 2026-11-12
- [CMExam](https://mdexa.com/datasets/cmexam/) — Restricted · Link only · exam-derived · 2026-11-12
- [PromptCBLUE](https://mdexa.com/datasets/promptcblue/) — Restricted · Link only · derived · 2026-11-12
- [Therapeutics Data Commons](https://mdexa.com/datasets/tdc/) — Unstated · Pending · 2026-11-14
- [CBLUE](https://mdexa.com/datasets/cblue/) — Unstated · Pending · 2026-11-12
- [MLEC-QA](https://mdexa.com/datasets/mlec-qa/) — Unstated · Pending · exam-derived · 2026-11-12
- [MedDialog-CN](https://mdexa.com/datasets/meddialog-cn/) — Unverifiable · Pending · scraped, real-patient-text · 2026-11-12