KokushiMD‑10 is a multilingual benchmark for ten Japanese healthcare professions, offering text‑only and image‑based single‑choice, multiple‑choice, calculation, and fill‑in‑the‑blank questions with chain‑of‑thought explanations, available in separate Japanese, English, or mixed splits.
Description in other languages
Statistics
Statistics as of Nov 16, 2026
Hugging Face downloads (last 30 days)
327
Hugging Face likes
8
Listed
Jul 1, 2025
Downloads (30-day window) over time
Show as a table
| Month | DL (30d) |
|---|---|
| Dec 2025 | 905 |
| Jan 2026 | — |
| Feb 2026 | — |
| Mar 2026 | — |
| Apr 2026 | 1,000 |
| May 2026 | 313 |
| Jun 2026 | — |
| Jul 2026 | — |
| Aug 2026 | 155 |
| Sep 2026 | 170 |
| Oct 2026 | 239 |
| Nov 2026 | 327 |
Downloads over the 30 days before the last snapshot of each month.
Popular in the same category
- JMMMUJMMMU3kJMMMU is a Japanese multimodal benchmark expanded over tenfold to 1,320 culturally diverse questions (720 culture‑agnostic, 600 culture‑specific) translated by native subject experts, now featuring a public leaderboard.
- JMMMU-ProJMMMU1kJMMMU‑Pro is an image‑based Japanese multimodal benchmark created by generating visual questions with a realistic model and human verification, revealing that current open‑source LMMs perform poorly on it and offering a cost‑effective method for future VQA benchmark development.
- vntl-leaderboardlmg-anon857A leaderboard that ranks large language models by their semantic accuracy in translating Japanese visual novels into English, using cosine similarity over 256 samples and reporting chrF scores for comparison with tools like Sugoi Translator, Google Translate, Naver Papago, and Alibaba Translate.
- JAMMEvalllm-jp830JAMMEval is a distilled benchmark of seven Japanese VQA datasets, refined with two rounds of human annotation to remove ambiguities and non‑visual questions, delivering reliable evaluation of vision‑language models on multimodal Japanese tasks.
- JA-VG-VQA-500SakanaAI520JA‑VG‑VQA‑500 is a 500‑sample subset of the Japanese Visual Genome VQA dataset, licensed CC BY 4.0, used to benchmark EvoVLM‑JP‑v1‑7B.
- Japanese-Heron-Benchturing-motors316Japanese‑Heron‑Bench is a Japanese VLM benchmark comprising 21 images from seven subcategories, each paired with 3‑category questions (Conversation, Detail, Complex) for a total of 102 queries under CC BY licenses.
Resources in similar research fields
cameraCyberAgentAILab26CAMERA (CyberAgent Multimodal Evaluation for Ad Text GeneRAtion) is the Japanese ad text generation dataset.GitHubShared: Corpora & datasets・Evaluation & benchmarks
huggingface-datasets_CAMERAcreative-graphic-design3CAMERA (CyberAgent Multimodal Evaluation for Ad Text GeneRAtion) for huggingface datasetsGitHubShared: Corpora & datasets・Evaluation & benchmarks- Cauldron-JAturing-motors7kCauldron‑JA is a Japanese vision‑language dataset of 44 sub‑datasets translated from The Cauldron using the DeepL API, available via HuggingFace’s datasets library and licensed identically to the original set, with prompts released under CC‑BY‑4.0.Shared: Corpora & datasets・Vision & multimodal
lm-evaluation-harnessEleutherAI14kA framework for few-shot evaluation of language models.MultilingualShared: Corpora & datasets・Evaluation & benchmarks- Galgame-VisualNovel-Reuploadjoujiboi5kRestructured reupload of the Galgame VisualNovel dataset (OOPPEENN/56697375616C4E6F76656C5F44617461736574) for efficient Hugging Face datasets loading, preserving all original audio/text and providing an extraction script with multiple game‑subset options.Shared: Corpora & datasets・Vision & multimodal
- STAIR-Captionsshunk0312kSTAIR‑Captions, released in 2017, offers 820,310 Japanese captions for caption generation, multimodal retrieval, and image generation, complete with detailed annotations, metadata, and a Creative Commons BY‑4.0 license.Shared: Corpora & datasets・Vision & multimodal