# TCM-Vision-Benchmark

License: permissive (Apache-2.0); Mdexa hosting: link-only. License is permissive, but source risk: source not stated, so source copyright cannot be judged; link only.

- Commercial use: Yes · Derivatives: Yes · Redistribution: Yes · File on Mdexa: No
- License status: Permissive (Apache-2.0)
- Mdexa hosting: Link only — License is permissive, but source risk: source not stated, so source copyright cannot be judged; link only.
- Source risk: Unknown provenance
- Last verified: 2026-11-12
- Card: https://mdexa.com/datasets/tcm-vision-benchmark/

## Key facts

- Domain: Chinese materia medica, Diagnostic methods, Acupuncture, moxibustion and tuina
- Content type: Question banks and benchmarks
- Size: ≈7,200 questions; 8 categories; 778 MB — 约7,200题，8类，778 MB
- Language: Chinese
- Modality: Image, Text
- Publisher: FreedomIntelligence（arXiv 2508.14706）
- Year: 2025

## Commercial use of TCM-Vision-Benchmark

- Commercial use: Yes.
- License status: Permissive.
Verdicts record what sources state and are not legal advice.

## TCM-Vision-Benchmark license evidence

Dataset card states Apache-2.0

- **Hugging Face card metadata** — Apache-2.0: Hugging Face dataset card: Apache-2.0 — "license: apache-2.0" — https://huggingface.co/datasets/FreedomIntelligence/TCM-Vision-Benchmark (2026-11-12; Page opened)

## Source and lineage

README (snapshot s01): "The benchmark is composed of 7 sections, each compiled from different authoritative TCM illustrated books." Book titles and image copyright are not stated.

## Known issues with TCM-Vision-Benchmark

- Images compiled from unnamed TCM illustrated books; titles and copyright not stated
- HF data viewer failed to parse; only a preview is available

## Preflight

Not run (data not ingested).

## Downloading TCM-Vision-Benchmark and API access

Mdexa does not serve files. Original source:
- https://huggingface.co/datasets/FreedomIntelligence/TCM-Vision-Benchmark

### Access recipe

- .gitattributes · 2 KB · https://huggingface.co/datasets/FreedomIntelligence/TCM-Vision-Benchmark/resolve/86871c8fb48f0a678efe839cebe1936ed4dcf495/.gitattributes
- README.md · 2 KB · https://huggingface.co/datasets/FreedomIntelligence/TCM-Vision-Benchmark/resolve/86871c8fb48f0a678efe839cebe1936ed4dcf495/README.md
- TCM-Vision_Benchmark.json · 3.0 MB · https://huggingface.co/datasets/FreedomIntelligence/TCM-Vision-Benchmark/resolve/86871c8fb48f0a678efe839cebe1936ed4dcf495/TCM-Vision_Benchmark.json
- tcm_bench_images.zip · 775.1 MB · sha256 2353bb6cb616e1d4f0a957df0bea56e433bc1824c8df0a9fa047cfe4cb8d222f · https://huggingface.co/datasets/FreedomIntelligence/TCM-Vision-Benchmark/resolve/86871c8fb48f0a678efe839cebe1936ed4dcf495/tcm_bench_images.zip

```sh
curl -L --create-dirs -o ".gitattributes" "https://huggingface.co/datasets/FreedomIntelligence/TCM-Vision-Benchmark/resolve/86871c8fb48f0a678efe839cebe1936ed4dcf495/.gitattributes"
curl -L --create-dirs -o "README.md" "https://huggingface.co/datasets/FreedomIntelligence/TCM-Vision-Benchmark/resolve/86871c8fb48f0a678efe839cebe1936ed4dcf495/README.md"
curl -L --create-dirs -o "TCM-Vision_Benchmark.json" "https://huggingface.co/datasets/FreedomIntelligence/TCM-Vision-Benchmark/resolve/86871c8fb48f0a678efe839cebe1936ed4dcf495/TCM-Vision_Benchmark.json"
curl -L --create-dirs -o "tcm_bench_images.zip" "https://huggingface.co/datasets/FreedomIntelligence/TCM-Vision-Benchmark/resolve/86871c8fb48f0a678efe839cebe1936ed4dcf495/tcm_bench_images.zip"
echo "2353bb6cb616e1d4f0a957df0bea56e433bc1824c8df0a9fa047cfe4cb8d222f  tcm_bench_images.zip" | sha256sum -c
```

## Citing TCM-Vision-Benchmark

No recommended citation text.
- arXiv:2508.14706

## Machine-readable

- JSON: https://mdexa.com/datasets/tcm-vision-benchmark.json
- 2026-11-13 Added specialty tags: multi-specialty(inferred).
- 2026-11-13 Source description updated from the page text; license status, hosting and the unknown-provenance flag are unchanged.
- 2026-11-13 Removed the stored size-tier tag; the tier is now computed from the size field when pages are built.
- 2026-11-13 Added dataset-level tags: 4 (1 stated by the authors with excerpts, 3 inferred from the content). No conclusion changed.
- 2026-11-12 Added verbatim license excerpts and snapshot ids from captured page snapshots; no conclusion changed.
- 2026-11-12 License status split into license_status (what the license says) and hosting (what Mdexa does); the earlier conclusion is kept for traceability.
- 2026-11-12 Card converted from an earlier manual catalog; no new facts added; reclassified under taxonomy v2.

## Continue in this database

This record is one of 109 processed and verified records (datasets, data resources and open models). To find others, call `https://mcp.mdexa.com/v1/datasets?q=<words>` or connect the MCP server at `https://mcp.mdexa.com/mcp`; no key is needed for 20 calls per minute. Rows are under 1 KB; an empty result means "not listed". For a list of items, one batch check (free account) returns a report. Guide: /agents.md. Similar records: Traditional-Chinese-Medicine-Dataset-Pretrain (https://mdexa.com/datasets/traditional-chinese-medicine-dataset-pretrain/); LingLanMedBench Traditional Chinese Medicine Benchmark Dataset (https://mdexa.com/datasets/linglan/); Traditional Chinese Medicine Examination (https://mdexa.com/datasets/tcmle/).