R2MED Benchmark
Verified by Mdexa · Checked against the source text under public rules.How we check
- Commercial use
- Yes
- Derivatives
- Yes
- Redistribution
- Yes
- File on Mdexa
- NoLink only
first-hand data-scope statement(s) allow commercial use and redistribution
Cite this pageMdexa, R2MED Benchmark, https://mdexa.com/datasets/medqa-diag/, verified 2026-11-14.
Key facts
- Domain
- Clinical medicine Modern medicine
- Content
- Annotated corporaR2MED is a high-quality synthetic medical information retrieval dataset with 876 queries, three retrieval tasks, five medical scenarios and twelve body systems.
- Size
- —As stated: 10M<n<100M
- Language / modality
- English / Text
- Publisher
- R2MED
- Year
- 2025-05-21
- Expert review
- —
- Verification
- Verified: license text seen
Commercial use of R2MED Benchmark
Commercial use: Yes. License status: Permissive.
- Conditions
- Attribution
Quoted statements and their sources are in R2MED Benchmark license evidence.
Verdicts record what sources state and are not legal advice.
R2MED Benchmark license evidence 1
-
Hugging Face card metadataPage opened
CC-BY-4.0Third-party text · Hugging Face card metadata
license: cc-by-4.0
Statement found in snapshot s04 (readme)
Source and lineage
No upstream or downstream datasets recorded.
Known issues with R2MED Benchmark
—
Preflight
Not run Runs only on ingested data; says nothing about quality.
Downloading R2MED Benchmark and API access
No file on Mdexa (see the verdict). Get it from the source and confirm the terms there:
25 files · 60.0 MB
curl -L --create-dirs -o ".gitattributes" "https://huggingface.co/datasets/R2MED/MedQA-Diag/resolve/78b585990279cc01a493f876c1b0cf09557fba57/.gitattributes"
curl -L --create-dirs -o "README.md" "https://huggingface.co/datasets/R2MED/MedQA-Diag/resolve/78b585990279cc01a493f876c1b0cf09557fba57/README.md"
curl -L --create-dirs -o "corpus.jsonl" "https://huggingface.co/datasets/R2MED/MedQA-Diag/resolve/78b585990279cc01a493f876c1b0cf09557fba57/corpus.jsonl"
echo "2767063e36589bcda9ea87a898effd91529548838d645adccbc9e9c22bdd0f12 corpus.jsonl" | sha256sum -c
curl -L --create-dirs -o "hyde/gpt4/query_with_hydoc.jsonl" "https://huggingface.co/datasets/R2MED/MedQA-Diag/resolve/78b585990279cc01a493f876c1b0cf09557fba57/hyde/gpt4/query_with_hydoc.jsonl"
curl -L --create-dirs -o "hyde/huatuo-o1-70b/query_with_hydoc.jsonl" "https://huggingface.co/datasets/R2MED/MedQA-Diag/resolve/78b585990279cc01a493f876c1b0cf09557fba57/hyde/huatuo-o1-70b/query_with_hydoc.jsonl"
curl -L --create-dirs -o "hyde/llama-70b/query_with_hydoc.jsonl" "https://huggingface.co/datasets/R2MED/MedQA-Diag/resolve/78b585990279cc01a493f876c1b0cf09557fba57/hyde/llama-70b/query_with_hydoc.jsonl"
curl -L --create-dirs -o "hyde/o3-mini/query_with_hydoc.jsonl" "https://huggingface.co/datasets/R2MED/MedQA-Diag/resolve/78b585990279cc01a493f876c1b0cf09557fba57/hyde/o3-mini/query_with_hydoc.jsonl"
curl -L --create-dirs -o "hyde/qwen-32b/query_with_hydoc.jsonl" "https://huggingface.co/datasets/R2MED/MedQA-Diag/resolve/78b585990279cc01a493f876c1b0cf09557fba57/hyde/qwen-32b/query_with_hydoc.jsonl"
curl -L --create-dirs -o "hyde/qwen-72b/query_with_hydoc.jsonl" "https://huggingface.co/datasets/R2MED/MedQA-Diag/resolve/78b585990279cc01a493f876c1b0cf09557fba57/hyde/qwen-72b/query_with_hydoc.jsonl"
curl -L --create-dirs -o "hyde/qwen-7b/query_with_hydoc.jsonl" "https://huggingface.co/datasets/R2MED/MedQA-Diag/resolve/78b585990279cc01a493f876c1b0cf09557fba57/hyde/qwen-7b/query_with_hydoc.jsonl"
curl -L --create-dirs -o "hyde/qwq-32b/query_with_hydoc.jsonl" "https://huggingface.co/datasets/R2MED/MedQA-Diag/resolve/78b585990279cc01a493f876c1b0cf09557fba57/hyde/qwq-32b/query_with_hydoc.jsonl"
curl -L --create-dirs -o "hyde/r1-llama-70b/query_with_hydoc.jsonl" "https://huggingface.co/datasets/R2MED/MedQA-Diag/resolve/78b585990279cc01a493f876c1b0cf09557fba57/hyde/r1-llama-70b/query_with_hydoc.jsonl"
curl -L --create-dirs -o "hyde/r1-qwen-32b/query_with_hydoc.jsonl" "https://huggingface.co/datasets/R2MED/MedQA-Diag/resolve/78b585990279cc01a493f876c1b0cf09557fba57/hyde/r1-qwen-32b/query_with_hydoc.jsonl"
curl -L --create-dirs -o "lamer/gpt4/query_with_hydoc.jsonl" "https://huggingface.co/datasets/R2MED/MedQA-Diag/resolve/78b585990279cc01a493f876c1b0cf09557fba57/lamer/gpt4/query_with_hydoc.jsonl"
curl -L --create-dirs -o "lamer/qwen-72b/query_with_hydoc.jsonl" "https://huggingface.co/datasets/R2MED/MedQA-Diag/resolve/78b585990279cc01a493f876c1b0cf09557fba57/lamer/qwen-72b/query_with_hydoc.jsonl"
curl -L --create-dirs -o "lamer/qwen-7b/query_with_hydoc.jsonl" "https://huggingface.co/datasets/R2MED/MedQA-Diag/resolve/78b585990279cc01a493f876c1b0cf09557fba57/lamer/qwen-7b/query_with_hydoc.jsonl"
curl -L --create-dirs -o "qrels.jsonl" "https://huggingface.co/datasets/R2MED/MedQA-Diag/resolve/78b585990279cc01a493f876c1b0cf09557fba57/qrels.jsonl"
curl -L --create-dirs -o "query.jsonl" "https://huggingface.co/datasets/R2MED/MedQA-Diag/resolve/78b585990279cc01a493f876c1b0cf09557fba57/query.jsonl"
curl -L --create-dirs -o "query2doc/gpt4/query_with_hydoc.jsonl" "https://huggingface.co/datasets/R2MED/MedQA-Diag/resolve/78b585990279cc01a493f876c1b0cf09557fba57/query2doc/gpt4/query_with_hydoc.jsonl"
curl -L --create-dirs -o "query2doc/qwen-72b/query_with_hydoc.jsonl" "https://huggingface.co/datasets/R2MED/MedQA-Diag/resolve/78b585990279cc01a493f876c1b0cf09557fba57/query2doc/qwen-72b/query_with_hydoc.jsonl"
curl -L --create-dirs -o "query2doc/qwen-7b/query_with_hydoc.jsonl" "https://huggingface.co/datasets/R2MED/MedQA-Diag/resolve/78b585990279cc01a493f876c1b0cf09557fba57/query2doc/qwen-7b/query_with_hydoc.jsonl"
curl -L --create-dirs -o "search-o1/qwen3-32b/query_with_hydoc.jsonl" "https://huggingface.co/datasets/R2MED/MedQA-Diag/resolve/78b585990279cc01a493f876c1b0cf09557fba57/search-o1/qwen3-32b/query_with_hydoc.jsonl"
curl -L --create-dirs -o "search-o1/qwq-32b/query_with_hydoc.jsonl" "https://huggingface.co/datasets/R2MED/MedQA-Diag/resolve/78b585990279cc01a493f876c1b0cf09557fba57/search-o1/qwq-32b/query_with_hydoc.jsonl"
curl -L --create-dirs -o "search-r1/qwen-3b-ins/query_with_hydoc.jsonl" "https://huggingface.co/datasets/R2MED/MedQA-Diag/resolve/78b585990279cc01a493f876c1b0cf09557fba57/search-r1/qwen-3b-ins/query_with_hydoc.jsonl"
curl -L --create-dirs -o "search-r1/qwen-7b-ins/query_with_hydoc.jsonl" "https://huggingface.co/datasets/R2MED/MedQA-Diag/resolve/78b585990279cc01a493f876c1b0cf09557fba57/search-r1/qwen-7b-ins/query_with_hydoc.jsonl"Citing R2MED Benchmark
Mdexa, R2MED Benchmark, https://mdexa.com/datasets/medqa-diag/, verified 2026-11-14.
More citation details
The source gives no citation text; the line above cites this card.
Machine-readable
medqa-diag.jsonmedqa-diag.mdcatalog.json
Change log 1
| 2026-11-14 | Added via the automated pipeline and passed all checks (gates, verbatim quotes, rule engine, two independent extractions). |
Listed in
Datasets similar to R2MED Benchmark
PMC-Patients-ReCDSVerified by Mdexa RestrictedLink only —
License restricted: restrictions are read broadly: CC-BY-NC-SA-4.0. Risk flag(s): derived, Real patient text. Link only.
Clinical medicine · Biomedical literature · Annotated corpora · Clinical cases · Literature · Derived · Real patient text
Shared: Intended use Evaluation · Specialty Multi-specialty · Data format JSONL · Benchmark status Public leaderboard · domain Clinical medicine · content Annotated corpora
PromptCBLUEVerified by Mdexa RestrictedLink only 68.9K items
License is restricted: README prohibits commercial use; link only.
Clinical medicine · Question banks and benchmarks · Annotated corpora · Derived
Shared: Intended use Evaluation · Specialty Multi-specialty · Data format JSONL · Benchmark status Public leaderboard · domain Clinical medicine · content Annotated corpora
PubMedQAVerified by Mdexa PermissiveLink only —
License permissive: first-hand data-scope statement(s) allow commercial use and redistribution. Link only.
Biomedical literature · Clinical medicine · QA, dialogue and instruction data · Annotated corpora
Shared: Intended use Evaluation · Specialty Multi-specialty · Benchmark status Public leaderboard · domain Clinical medicine · content Annotated corpora
ESL-benchEvent-driven Synthetic Longitudinal BenchmarkVerified by Mdexa ConflictPending —
License conflict: the publisher's own statements contradict each other (permissive license vs restriction). Link only.
Clinical medicine · Question banks and benchmarks · Knowledge graphs
Shared: Intended use Evaluation · Specialty Multi-specialty · Data format JSONL · Benchmark status Public leaderboard · domain Clinical medicine
CBLUEVerified by Mdexa UnstatedPending 8 tasks
License unstated: Only a code repository license; no data license stated; link only until resolved.
Clinical medicine · Question banks and benchmarks · Annotated corpora
Shared: Intended use Evaluation · Specialty Multi-specialty · domain Clinical medicine · content Annotated corpora