datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
biosses-sts
BIOSSES
An MTEB dataset
Massive Text Embedding Benchmark
Biomedical Semantic Similarity Estimation.
Task category
t2t
Domains
Medical
Reference
https://tabilab.cmpe.boun.edu.tr/BIOSSES/DataSet.html
How to evaluate on this task
You can evaluate an embedding model on this dataset using the following code:
import mteb
task = mteb.get_tasks(["BIOSSES"])
evaluator = mteb.MTEB(task)
model = mteb.get_model(YOUR_MODEL)
evaluator.run(model)
To learn more… See the full description on the dataset page: https://huggingface.co/datasets/mteb/biosses-sts.bio-mqm-datasetThis dataset is compiled from the official Amazon repository (all respective licensing applies).
It contains system translations, multiple references, and their quality evaluation on the MQM scale. It accompanies the ACL 2024 paper Fine-Tuned Machine Translation Metrics Struggle in Unseen Domains.
Watch a brief 4 minutes-long video.
Abstract: We introduce a new, extensive multidimensional quality metrics (MQM) annotated dataset covering 11 language pairs in the biomedical domain. We use this… See the full description on the dataset page: https://huggingface.co/datasets/zouhar/bio-mqm-dataset.biorxiv-clustering-p2p
BiorxivClusteringP2P.v2
An MTEB dataset
Massive Text Embedding Benchmark
Clustering of titles+abstract from biorxiv across 26 categories.
Task category
t2c
Domains
Academic, Written
Reference
https://api.biorxiv.org/
How to evaluate on this task
You can evaluate an embedding model on this dataset using the following code:
import mteb
task = mteb.get_tasks(["BiorxivClusteringP2P.v2"])
evaluator = mteb.MTEB(task)
model = mteb.get_model(YOUR_MODEL)… See the full description on the dataset page: https://huggingface.co/datasets/mteb/biorxiv-clustering-p2p.daily-bio-newsbiorxiv-clustering-s2s
BiorxivClusteringS2S.v2
An MTEB dataset
Massive Text Embedding Benchmark
Clustering of titles from biorxiv across 26 categories.
Task category
t2c
Domains
Academic, Written
Reference
https://api.biorxiv.org/
How to evaluate on this task
You can evaluate an embedding model on this dataset using the following code:
import mteb
task = mteb.get_tasks(["BiorxivClusteringS2S.v2"])
evaluator = mteb.MTEB(task)
model = mteb.get_model(YOUR_MODEL)… See the full description on the dataset page: https://huggingface.co/datasets/mteb/biorxiv-clustering-s2s.Bioinformatics
🔭 Overview
R2MED: First Reasoning-Driven Medical Retrieval Benchmark
R2MED is a high-quality, high-resolution synthetic information retrieval (IR) dataset designed for medical scenarios. It contains 876 queries with three retrieval tasks, five medical scenarios, and twelve body systems.
Dataset
#Q
#D
Avg. Pos
Q-Len
D-Len
Biology
103
57359
3.6
115.2
83.6
Bioinformatics77
47473
2.9
273.8
150.5
Medical Sciences
88
34810
2.8
107.1
122.7
MedXpertQA-Exam
97… See the full description on the dataset page: https://huggingface.co/datasets/R2MED/Bioinformatics.biodiversity_heritage_library_filtered
Biodiversity Heritage Library
Description
The Biodiversity Heritage Library (BHL) is an open-access digital library for biodiversity literature and archives.
This dataset contains over 15 million public domain books and documents from the BHL collection.
These works were collected using the bulk data download interface provided by the BHL and were filtered based on their associated license metadata.
We use the optical character recognition (OCR)-generated text distributed… See the full description on the dataset page: https://huggingface.co/datasets/common-pile/biodiversity_heritage_library_filtered.biodiversity_heritage_library
Biodiversity Heritage Library
Description
The Biodiversity Heritage Library (BHL) is an open-access digital library for biodiversity literature and archives.
This dataset contains over 42 million public domain books and documents from the BHL collection.
These works were collected using the bulk data download interface provided by the BHL and were filtered based on their associated license metadata.
We use the optical character recognition (OCR)-generated text… See the full description on the dataset page: https://huggingface.co/datasets/common-pile/biodiversity_heritage_library.biomnibench-organized
BioMniBench DA — Reorganized
A clean, manifest-driven reorganization of the
BioMniBench DA (Data Analysis) task suite,
shaped for use with the
biomnibench-adapter evaluation
harness and the native skill-learning loop that ships with it.
This Hugging Face repository hosts the metadata, evaluation rubric and data manifest for
all 50 tasks. The raw input data files (which total ~77 GB and originate upstream from
GEO/TCGA/cBioPortal/etc.) are not redistributed here — see
Getting… See the full description on the dataset page: https://huggingface.co/datasets/starpacker52/biomnibench-organized.bioasq_7b_yesnogliner-biomed-pre-training
GLiNER-BioMed pre-training dataset
This dataset, used for the pre-training stage of the GLiNER-BioMed models, was introduced in the paper GLiNER-BioMed: a suite of efficient models for open biomedical named entity recognition.
Citation
If you use the GLiNER-BioMed models or datasets in your work, please cite:
@article{yazdani2026gliner,
author = {Yazdani, Anthony and Stepanov, Ihor and Teodoro, Douglas},
title = {{GLiNER-BioMed}: a suite of efficient… See the full description on the dataset page: https://huggingface.co/datasets/anthonyyazdaniml/gliner-biomed-pre-training.biopharma-bench
Biopharma Bench V0.1
Biopharma Bench is an evaluation suite measuring whether frontier AI agents can perform professional, regulated desk work in biopharmaceutical drug and medical device development.
Instead of testing models on isolated multiple-choice questions or pre-packaged single-document summaries, Biopharma Bench places agents into realistic employee seats across complete corporate operating environments.
Announcement: https://raycaster.ai/blog/biopharma-bench… See the full description on the dataset page: https://huggingface.co/datasets/raycasterai/biopharma-bench.BioHopR
BioHopR
Paper |
Description
We introduce BioHopR, a novel benchmark designed to evaluate multi-hop, multi-answer reasoning in structured biomedical knowledge graphs.Built from the comprehensive PrimeKG, BioHopR includes 1-hop and 2-hop reasoning tasks that reflect real-world biomedical complexities.
Prompt
We used the below to get the response of the open source LLMs.
def generate_single(model, tokenizer, question):
q="You are an expert biomedical… See the full description on the dataset page: https://huggingface.co/datasets/knowlab-research/BioHopR.Biology
🔭 Overview
R2MED: First Reasoning-Driven Medical Retrieval Benchmark
R2MED is a high-quality, high-resolution synthetic information retrieval (IR) dataset designed for medical scenarios. It contains 876 queries with three retrieval tasks, five medical scenarios, and twelve body systems.
Dataset
#Q
#D
Avg. Pos
Q-Len
D-Len
Biology
103
57359
3.6
115.2
83.6
Bioinformatics77
47473
2.9
273.8
150.5
Medical Sciences
88
34810
2.8
107.1
122.7
MedXpertQA-Exam
97… See the full description on the dataset page: https://huggingface.co/datasets/R2MED/Biology.gliner-biomed-post-training
GLiNER-BioMed post-training dataset
This dataset, used for the post-training stage of the GLiNER-BioMed models, was introduced in the paper GLiNER-BioMed: a suite of efficient models for open biomedical named entity recognition.
Citation
If you use the GLiNER-BioMed models or datasets in your work, please cite:
@article{yazdani2026gliner,
author = {Yazdani, Anthony and Stepanov, Ihor and Teodoro, Douglas},
title = {{GLiNER-BioMed}: a suite of efficient… See the full description on the dataset page: https://huggingface.co/datasets/anthonyyazdaniml/gliner-biomed-post-training.biomed_NER
Biomed NER
This dataset consists of 4,840 manually annotated text records drawn from PubMed abstracts, drug descriptions from the FDA, and patent abstracts. All entities are continuous, and there are no nested entities.
Dataset composition
The dataset contains 4,840 annotated text records distributed across three sources:
Source
Approx. records
Purpose
PubMed abstracts
~4,300
Core biomedical content
FDA drug descriptions
~430
Pharmaceutical text with dense… See the full description on the dataset page: https://huggingface.co/datasets/knowledgator/biomed_NER.chinese-biomedicine-and-genomics-open-intelligence
🔬 Chinese Biomedicine, Cell Therapy & Genomics Open Intelligence Dataset
Curated open intelligence dataset providing English briefs, clinical trial benchmarks, verified abstracts, and DOIs of frontier Chinese research in Cellular Therapeutics, Gene Editing, ADCs, and NMPA Clinical Approvals.
[!IMPORTANT]
Data Completeness & Research Authenticity Notice:
Included in this Hugging Face Open Dataset: English structured abstracts, core quantitative takeaways, author… See the full description on the dataset page: https://huggingface.co/datasets/simpleG2023/chinese-biomedicine-and-genomics-open-intelligence.agi-biospheric-10-constraints
AGI Biospheric — 10 Core Biospheric Constraints and 52 Interdependencies
Overview
AGI Biospheric is a bilingual (French / English) structured dataset modeling 10 core biospheric constraints and 52 direct interdependencies relevant to long-term reflection on AGI alignment, ecological limits, civilizational resilience, and the material conditions of intelligence.
This repository is the first public machine-readable release of the AGI Biospheric framework. It should… See the full description on the dataset page: https://huggingface.co/datasets/Cedre83/agi-biospheric-10-constraints.bio-overrefusal-v0.1
Bio Over-Refusal Dataset v0.1.0
Dataset Summary
The Bio Over-Refusal Dataset is a domain-expert-authored and tier-annotated benchmark of 201 legitimate biology research queries stratified by sensitivity tier. It is designed to measure the false-positive refusal rate (FPR) of large language models — specifically, the rate at which models refuse or hedge on questions that credentialed biology researchers would consider appropriate to answer.
The dataset does not… See the full description on the dataset page: https://huggingface.co/datasets/jang1563/bio-overrefusal-v0.1.BioHarness_Eval
BioHarness_Eval
This is the evaluation suite used in the BioHarness paper
(arXiv:2606.19396). It has ten biomedical
question-answering datasets with seven question types.
Paper version. This card follows the revised manuscript, which is not yet on
arXiv. arXiv v1 (June 2026) reports the earlier eight-dataset, 19,302-item suite
(BioHarness 71.0 against 65.9 for the strongest non-oracle baseline); its numbers do
not match the ten-dataset framing and
the table below. The link will… See the full description on the dataset page: https://huggingface.co/datasets/Shaow/BioHarness_Eval.OpenSciReasoning-Biology-20K
OpenSciReasoning-Biology-20K
Three-domain release derived from nvidia/OpenScienceReasoning-2 for
domain-specific reasoner training and cross-domain transfer experiments.
Each row preserves the stable source_row_id and has exactly one mutually
exclusive domain value: BIOLOGY. Domain acceptance was checked from the
question and choices with two independent question-only verifiers; answer and
source-ID gates were also replayed.
The audit records list any remaining source-output… See the full description on the dataset page: https://huggingface.co/datasets/TerryJCZhang/OpenSciReasoning-Biology-20K.bioasq-12b-rag
BioASQ 12B RAG Dataset
A processed version of the BioASQ 12B dataset optimized for Retrieval-Augmented Generation (RAG) applications in biomedical question answering.
This dataset contains two distinct subsets specifically designed for RAG applications:
A text corpus of PubMed abstracts ready for indexing and retrieval, containing detailed metadata and full abstract text.
An evaluation dataset consisting of biomedical questions, each paired with an ideal answer and a list of… See the full description on the dataset page: https://huggingface.co/datasets/mattmorgis/bioasq-12b-rag.BioDSBench
BioDSBench: Benchmarking LLMs for Biomedical Data Science Tasks
This repository contains the datasets for BioDSBench, a benchmark for evaluating Large Language Models (LLMs) on biomedical data science tasks.
Overview
BioDSBench evaluates whether LLMs can replace data scientists in biomedical research. The benchmark includes a diverse set of coding tasks in Python and R that represent real-world biomedical data analysis scenarios.
Dataset Structure
The… See the full description on the dataset page: https://huggingface.co/datasets/zifeng-ai/BioDSBench.BioWiCbioinstruct
Dataset Card for BioInstruct
GitHub repo: https://github.com/bio-nlp/BioInstruct
Dataset Summary
BioInstruct is a dataset of 25k instructions and demonstrations generated by OpenAI's GPT-4 engine in July 2023.
This instruction data can be used to conduct instruction-tuning for language models (e.g. Llama) and make the language model follow biomedical instruction better.
Improvements of Llama on 9 common BioMedical tasks are shown in the result section.
Taking… See the full description on the dataset page: https://huggingface.co/datasets/bio-nlp-umass/bioinstruct.bioreview-bench
BioReview-Bench v4.1.3 — public index
BioReview-Bench is a silver-standard resource for studying concern patterns
recorded in published biomedical peer review. This rights-minimized snapshot is
an index and label-distribution release. It is not a self-contained text
benchmark, a public test set, or an open leaderboard.
6,940 text-free article index rows
93,222 text-free train/validation label rows
8,647 test targets withheld
Audited Hugging Face history with no article/abstract… See the full description on the dataset page: https://huggingface.co/datasets/jang1563/bioreview-bench.repro-abc-bench-an-agentic-bio-capabilities-benchmark-for-biosecurity-traces
Agent traces
Agent sessions published from a Trackio Logbook.
MedQA-MM
MedQA-MM Identifier Release
Paper repository ·
Hugging Face dataset
MedQA-MM is a 1,000-item shortcut-mitigated medical multimodal multiple-choice benchmark constructed from MedThinkVQA, MedXpertQA-MM, and the Health and Medicine portion of MMMU. This public release is intentionally identifier-only.
It does not contain source questions, answer choices, gold answers, images, clinical text, or repaired payloads. It provides stable source locators, pinned source revisions, and a… See the full description on the dataset page: https://huggingface.co/datasets/bio-nlp-umass/MedQA-MM.raw_biorxivGlobMed_BioNLI
🌍 GlobMed: BioNLI
GlobMed_BioNLI covers 20 languages, including 13 high-resource languages (Arabic, Chinese, English, French, German, Hindi, Indonesian, Japanese, Korean, Portuguese, Russian, Spanish, and Thai) and 7 low-resource languages (Bengali, Malay, Swahili, Urdu, Wolof, Yoruba, and Zulu).
Code
ar
bn
zh
en
fr
de
hi
id
ja
ko
ms
pt
ru
es
sw
th
ur
woyo
zu
Language
Arabic
Bengali
Chinese
English
French
German
Hindi
Indonesian
Japanese
Korean
Malay
Portuguese
Russian… See the full description on the dataset page: https://huggingface.co/datasets/ruiyang-medinfo/GlobMed_BioNLI.