{"id":103411,"url":"https://github.com/freedomintelligence/awesome-ai4med","name":"awesome-ai4med","description":"A curated list of medical LLMs, multimodal systems, datasets, benchmarks, and more. 🏥","projects_count":81,"last_synced_at":"2026-10-06T11:00:21.165Z","repository":{"id":37712415,"uuid":"221641068","full_name":"FreedomIntelligence/Awesome-AI4Med","owner":"FreedomIntelligence","description":"A curated list of medical LLMs, multimodal systems, datasets, benchmarks, and more. 🏥","archived":false,"fork":false,"pushed_at":"2026-08-04T14:35:31.000Z","size":656,"stargazers_count":2893,"open_issues_count":2,"forks_count":497,"subscribers_count":55,"default_branch":"master","last_synced_at":"2026-10-02T05:44:21.846Z","etag":null,"topics":["awesome-lists","collection","datasets","medical","medical-imaging","medical-llms","medical-vlms","models"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/FreedomIntelligence.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2019-11-14T07:50:52.000Z","updated_at":"2026-09-30T06:30:30.000Z","dependencies_parsed_at":"2022-07-08T01:35:14.816Z","dependency_job_id":"34f0e9aa-141b-4f01-ba4d-a996c7c90244","html_url":"https://github.com/FreedomIntelligence/Awesome-AI4Med","commit_stats":null,"previous_names":["lrs1353281004/chinese_medical_nlp","freedomintelligence/awesome-ai4med","freedomintelligence/medical_nlp"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/FreedomIntelligence/Awesome-AI4Med","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FreedomIntelligence%2FAwesome-AI4Med","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FreedomIntelligence%2FAwesome-AI4Med/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FreedomIntelligence%2FAwesome-AI4Med/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FreedomIntelligence%2FAwesome-AI4Med/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/FreedomIntelligence","download_url":"https://codeload.github.com/FreedomIntelligence/Awesome-AI4Med/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FreedomIntelligence%2FAwesome-AI4Med/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":343170754,"owners_count":38081405,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-10-03T21:59:58.778Z","status":"online","status_checked_at":"2026-10-06T02:00:06.537Z","response_time":86,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"created_at":"2026-01-04T20:52:38.768Z","updated_at":"2026-10-06T11:00:21.166Z","primary_language":null,"list_of_lists":false,"displayable":true,"categories":["1. Medical LLMs","3. Datasets","2. Medical MLLMs","4. Benchmarks"],"sub_categories":["3.2 Multimodal","3.1 Text"],"readme":"# Awesome-AI4Med\n\n\u003e We have renamed *Medical_NLP* to *Awesome-AI4Med*. If you need to view the previous content, you can visit [backup](https://github.com/FreedomIntelligence/Medical_NLP/tree/master/backup)!\n\n\u003e [!TIP]\n\u003e **Awesome-AI4Med** aims to systematically curate research resources in the field of medical artificial intelligence (AI4Med), covering **🧠 Medical LLMs**, **🩺 Medical MLLMs**, **📚 datasets**, and **📊 benchmarks**. By automatically extracting trending models and datasets from a large corpus of research papers and open-source projects, this repository provides a **clean, structured, and easy-to-navigate** collection that helps researchers and developers **🚀 quickly track field progress**, **🔍 locate relevant resources**, and **accelerate innovation** in medical AI.\n\u003e\n\u003e 📣 You can view our repository on specialized disease LLMs at [FreedomIntelligence/Awesome-Specialized-Medical-LLMs](https://github.com/FreedomIntelligence/Awesome-Specialized-Medical-LLMs)!\n\n\u003cp\u003e\n  \u003ca href=\"https://github.com/FreedomIntelligence/Awesome-AI4Med\"\u003e\u003cimg src=https://cdn.rawgit.com/sindresorhus/awesome/d7305f38d29fed78fa85652e3a63e154dd8e8829/media/badge.svg \u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/FreedomIntelligence/Awesome-AI4Med\"\u003e\u003cimg src=https://img.shields.io/github/forks/FreedomIntelligence/Awesome-AI4Med.svg?style=social \u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/FreedomIntelligence/Awesome-AI4Med\"\u003e\u003cimg src=https://img.shields.io/github/stars/FreedomIntelligence/Awesome-AI4Med.svg?style=social \u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/FreedomIntelligence/Awesome-AI4Med\"\u003e\u003cimg src=https://img.shields.io/github/watchers/FreedomIntelligence/Awesome-AI4Med.svg?style=social \u003e\u003c/a\u003e\n\u003c/p\u003e\n\nTable of Contents:\n- [1. Medical LLMs](#1-medical-llms)\n- [2. Medical MLLMs](#2-medical-mllms)\n- [3. Datasets](#3-datasets)\n  - [3.1 Text](#31-text)\n  - [3.2 Multimodal](#32-multimodal)\n- [4. Benchmarks](#4-benchmarks)\n\n![](https://camo.githubusercontent.com/2722992d519a722218f896d5f5231d49f337aaff4514e78bd59ac935334e916a/68747470733a2f2f692e696d6775722e636f6d2f77617856496d762e706e67)\n\n## 1. Medical LLMs\n\n|**Model Name**|**Paper**|**Model Weight**|**Data**|**Code**|\n|:-|:-:|:-:|:-:|:-:|\n|`HuatuoGPT`|[[arXiv](https://arxiv.org/abs/2305.15075)]|[[HF (7B)](https://huggingface.co/FreedomIntelligence/HuatuoGPT-7B)][[HF (13B)](https://huggingface.co/FreedomIntelligence/HuatuoGPT-13b-delta)]|[[HF](https://huggingface.co/datasets/FreedomIntelligence/HuatuoGPT-sft-data-v1)]|[[Github](https://github.com/FreedomIntelligence/HuatuoGPT)]|\n|`Apollo`|[[arXiv](https://arxiv.org/abs/2403.03640)]|[[HF (7B)](https://huggingface.co/FreedomIntelligence/Apollo-7B)][[HF (34B)](https://huggingface.co/FreedomIntelligence/Apollo-34B)][[HF (72B)](https://huggingface.co/FreedomIntelligence/Apollo-72B)]|[[HF](https://huggingface.co/datasets/FreedomIntelligence/ApolloCorpus)]|[[Github](https://github.com/FreedomIntelligence/Apollo)]|\n|`HuatuoGPT-II`|[[arXiv](https://arxiv.org/abs/2311.09774)]|[[HF (7B)](https://huggingface.co/FreedomIntelligence/HuatuoGPT2-7B)][[HF (13B)](https://huggingface.co/FreedomIntelligence/HuatuoGPT2-13B)][[HF (34B)](https://huggingface.co/FreedomIntelligence/HuatuoGPT2-34B)]|[[HF (PT)](https://huggingface.co/datasets/FreedomIntelligence/HuatuoGPT2-Pretraining-Instruction)][[HF (SFT)](https://huggingface.co/datasets/FreedomIntelligence/HuatuoGPT2-SFT-GPT4-140K)]|[[Github](https://github.com/FreedomIntelligence/HuatuoGPT-II)]|\n|`HuatuoGPT-o1`|[[arXiv](https://arxiv.org/abs/2412.18925)]|[[HF (7B)](https://huggingface.co/FreedomIntelligence/HuatuoGPT-o1-7B)][[HF (8B)](https://huggingface.co/FreedomIntelligence/HuatuoGPT-o1-8B)][[HF (70B)](https://huggingface.co/FreedomIntelligence/HuatuoGPT-o1-70B)]|[[HF](https://huggingface.co/datasets/FreedomIntelligence/medical-o1-reasoning-SFT)]|[[Github](https://github.com/FreedomIntelligence/HuatuoGPT-o1)]|\n|`MMedLM`|[[arXiv](https://arxiv.org/abs/2402.13963)]|[[HF (8B)](https://huggingface.co/Henrychur/MMed-Llama-3-8B)][[HF (70B)](https://huggingface.co/Henrychur/MMed-Llama3.1-70B)]|[[HF](https://huggingface.co/datasets/Henrychur/MMedC)]|[[Github](https://github.com/MAGIC-AI4Med/MMedLM)]|\n|`PMC-LLaMA`|[[arXiv](https://arxiv.org/abs/2304.14454)]|[[HF (13B)](https://huggingface.co/axiong/PMC_LLaMA_13B)]|[[HF](https://github.com/allenai/s2orc)]|[[Github](https://github.com/chaoyi-wu/PMC-LLaMA)]|\n|`Med42-v2`|[[arXiv](https://arxiv.org/abs/2408.06142)]|[[HF (8B)](https://huggingface.co/m42-health/Llama3-Med42-8B)][[HF (70B)](https://huggingface.co/m42-health/Llama3-Med42-70B)]|-|[[Github](https://github.com/m42-health/med42)]|\n|`OpenBioLLM`|-|[[HF (8B)](https://huggingface.co/aaditya/Llama3-OpenBioLLM-8B)][[HF (70B)](https://huggingface.co/aaditya/Llama3-OpenBioLLM-70B)]|-|-|\n|`UltraMedical`|[[arXiv](https://arxiv.org/abs/2406.03949)]|[[HF (8B)](https://huggingface.co/TsinghuaC3I/Llama-3-8B-UltraMedical)][[HF (70B)](https://huggingface.co/TsinghuaC3I/Llama-3-70B-UltraMedical)]|[[HF](https://huggingface.co/datasets/TsinghuaC3I/UltraMedical)]|[[Github](https://github.com/TsinghuaC3I/UltraMedical)]|\n|`BioMistral`|[[arXiv](https://arxiv.org/abs/2402.10373)]|[[HF (7B)](https://huggingface.co/BioMistral/BioMistral-7B)]|-|[[Github](https://github.com/BioMistral/BioMistral)]|\n|`MediTron`|[[arXiv](https://arxiv.org/abs/2311.16079)]|[[HF (7B)](https://huggingface.co/epfl-llm/meditron-7b)][[HF (70B)](https://huggingface.co/epfl-llm/meditron-70b)]|[[HF](https://huggingface.co/datasets/togethercomputer/RedPajama-Data-1T)]|[[Github](https://github.com/epfLLM/meditron)]|\n|`Baichuan-M2`|[[arXiv](https://arxiv.org/abs/2509.02208)]|[[HF (32B)](https://huggingface.co/baichuan-inc/Baichuan-M2-32B)]|-|[[Github](https://github.com/baichuan-inc/Baichuan-M2-32B)]|\n|`Baichuan-M1`|[[arXiv](https://arxiv.org/abs/2502.12671)]|[[HF (14B)](https://huggingface.co/baichuan-inc/Baichuan-M1-14B-Instruct)]|-|[[Github](https://github.com/baichuan-inc/Baichuan-M1-14B)]|\n|`MedAlpaca`|[[arXiv](https://arxiv.org/abs/2304.08247)]|[[HF (7B)](https://huggingface.co/medalpaca/medalpaca-7b)][[HF (13B)](https://huggingface.co/medalpaca/medalpaca-13b)]|[[Github](https://github.com/kbressem/medAlpaca/blob/main/DATA_DESCRIPTION.md)]|[[Github](https://github.com/kbressem/medAlpaca)]|\n|`RadFM`|[[arXiv](https://arxiv.org/abs/2308.02463)]|[[HF (13B)](https://huggingface.co/chaoyi-wu/RadFM)]|[[Github](https://huggingface.co/datasets/chaoyi-wu/RadFM_data_csv)]|[[Github](https://github.com/chaoyi-wu/RadFM)]|\n|`MedReason`|[[arXiv](https://arxiv.org/abs/2504.00993)]|[[HF (8B)](https://huggingface.co/UCSC-VLAA/MedReason-8B)]|[[HF](https://huggingface.co/datasets/UCSC-VLAA/MedReason)]|[[Github](https://github.com/UCSC-VLAA/MedReason)]|\n|`AlphaMed`|[[arXiv](https://www.arxiv.org/abs/2505.17952)]|[[HF (7B)](https://huggingface.co/che111/AlphaMed-7B-instruct-rl)][[HF (8B)](https://huggingface.co/che111/AlphaMed-8B-instruct-rl)]|[[HF](https://huggingface.co/datasets/che111/AlphaMed19K)]|-|\n|`Fleming-R1`|[[arXiv](https://arxiv.org/abs/2509.15279)]|[[HF (7B)](https://huggingface.co/UbiquantAI/Fleming-R1-7B)][[HF (32B)](https://huggingface.co/UbiquantAI/Fleming-R1-32B)]|-|[[Github](https://github.com/UbiquantAI/Fleming-R1)]|\n|`MedGemma`|[[arXiv](https://arxiv.org/abs/2507.05201)]|[[HF (27B)](https://huggingface.co/google/medgemma-27b-text-it)]|-|[[Github](https://github.com/Google-Health/medgemma)]|\n|`AntAngelMed`|-|[[HF (100B)](https://huggingface.co/MedAIBase/AntAngelMed)]|-|[[Github](https://github.com/MedAIBase/AntAngelMed)]|\n|`Baichuan-M3`|-|[[HF (235B)](https://huggingface.co/baichuan-inc/Baichuan-M3-235B)]|-|-|\n|`MedPsy`|[Blog](https://huggingface.co/blog/qvac/medpsy)|[[HF (1.7B/4B)](https://huggingface.co/collections/qvac/medpsy)]|-|-|\n|`MediPhi`|[[arXiv](https://arxiv.org/abs/2505.10717)]|[[HF (4B)](https://huggingface.co/collections/microsoft/mediphi)]|-|-|\n\n\n\u003cdiv align=\"right\"\u003e\n  \u003cb\u003e\u003ca href=\"#contents\"\u003e↥ back to top\u003c/a\u003e\u003c/b\u003e\n\u003c/div\u003e\n\n\n## 2. Medical MLLMs\n\n|**Model Name**|**Paper**|**Model Weight**|**Data**|**Code**|\n|:-|:-:|:-:|:-:|:-:|\n|`HuatuoGPT-Vision`|[[arXiv](https://arxiv.org/abs/2406.19280)]|[[HF (7B)](https://huggingface.co/FreedomIntelligence/HuatuoGPT-Vision-7B)][[HF 34B](https://huggingface.co/FreedomIntelligence/HuatuoGPT-Vision-34B)]|[[HF](https://huggingface.co/datasets/FreedomIntelligence/PubMedVision)]|[[Github](https://github.com/FreedomIntelligence/HuatuoGPT-Vision)]|\n|`ShizhenGPT`|[[arXiv](https://arxiv.org/abs/2508.14706)]|[[HF (7B)](https://huggingface.co/FreedomIntelligence/ShizhenGPT-7B-Omni)][[HF (32B)](https://huggingface.co/FreedomIntelligence/ShizhenGPT-32B-VL)]|[[HF (PT)](https://huggingface.co/datasets/FreedomIntelligence/TCM-Pretrain-Data-ShizhenGPT)][[HF (SFT)](https://huggingface.co/datasets/FreedomIntelligence/TCM-Instruction-Tuning-ShizhenGPT)]|[[Github](https://github.com/FreedomIntelligence/ShizhenGPT)]|\n|`Lingshu`|[[arXiv](https://arxiv.org/abs/2506.07044)]|[[HF (7B)](https://huggingface.co/lingshu-medical-mllm/Lingshu-7B)][[HF 32B](https://huggingface.co/lingshu-medical-mllm/Lingshu-32B)]|-|-|\n|`LLaVA-Med`|[[arXiv](https://arxiv.org/abs/2306.00890)]|[[HF (7B)](https://huggingface.co/microsoft/llava-med-v1.5-mistral-7b)]|[[Github](https://github.com/microsoft/LLaVA-Med/tree/main/data)]|[[Github](https://github.com/microsoft/LLaVA-Med)]|\n|`BiMediX2`|[[arXiv](https://arxiv.org/abs/2412.07769v2)]|[[HF (8B)](https://huggingface.co/MBZUAI/BiMediX2-8B)][[HF (70B)](https://huggingface.co/MBZUAI/BiMediX2-70B)]|[[Github](https://github.com/microsoft/LLaVA-Med/tree/main/data)]|[[Github](https://github.com/mbzuai-oryx/BiMediX2)]|\n|`Hulu-Med`|[[arXiv](https://arxiv.org/abs/2510.08668)]|[[HF (4B)](https://huggingface.co/ZJU-AI4H/Hulu-Med-4B)][[HF (7B)](https://huggingface.co/ZJU-AI4H/Hulu-Med-7B)][[HF (14B)](https://huggingface.co/ZJU-AI4H/Hulu-Med-14B)][[HF (32B)](https://huggingface.co/ZJU-AI4H/Hulu-Med-32B)]||[[Github](https://github.com/ZJUI-AI4H/Hulu-Med)]|\n|`HealthGPT`|[[arXiv](https://arxiv.org/abs/2412.07769v2)]|[[HF (3.8B)](https://huggingface.co/lintw/HealthGPT-M3)]|[[HF](https://huggingface.co/datasets/lintw/VL-Health)]|[[Github](https://github.com/DCDmllm/HealthGPT)]|\n|`Med-Flamingo`|[[arXiv](https://arxiv.org/abs/2307.15189)]|[[HF (7B)](https://huggingface.co/med-flamingo/med-flamingo)]|-|[[Github](https://github.com/snap-stanford/med-flamingo)]|\n|`MedGemma`|[[arXiv](https://arxiv.org/abs/2507.05201)]|[[HF (4B)](https://huggingface.co/google/medgemma-4b-it)][[HF (27B)](https://huggingface.co/google/medgemma-27b-it)]|-|[[Github](https://github.com/Google-Health/medgemma)]|\n|`Med-R1`|[[arXiv](https://arxiv.org/abs/2503.13939)]|[[HF (2B)](https://huggingface.co/yuxianglai117/Med-R1)]|-|[[Github](https://github.com/Yuxiang-Lai117/Med-R1)]|\n|`BiomedGPT`|[[arXiv](https://arxiv.org/abs/2305.17100)]|[[HF (7B)](https://huggingface.co/PharMolix/BioMedGPT-LM-7B)]|[[Github](https://github.com/taokz/BiomedGPT/blob/main/datasets.md)]|[[Github](https://github.com/taokz/BiomedGPT)]|\n|`MedVLM-R1`|[[arXiv](https://arxiv.org/abs/2502.19634)]|[[HF (2B)](https://huggingface.co/JZPeterPan/MedVLM-R1)]|-|[[Github](https://github.com/JZPeterPan/MedVLM-R1)]|\n|`UniMedVL`|[[arXiv](https://arxiv.org/abs/2510.15710)]|[[HF (14B)](https://huggingface.co/General-Medical-AI/UniMedVL)]|-|[[Github](https://github.com/uni-medical/UniMedVL)]|\n|`Chiron-o1`|[[arXiv](https://arxiv.org/abs/2506.16962)]|[[HF (2B)](https://huggingface.co/manglu3935/Chiron-o1-2B)][[HF (8B)](https://huggingface.co/manglu3935/Chiron-o1-8B)]|-|[[Github](https://github.com/manglu097/Chiron-o1)]|\n|`MiniGPT-Med`|[[arXiv](https://arxiv.org/abs/2407.04106)]|[[HF](https://github.com/Vision-CAIR/MiniGPT-Med?tab=readme-ov-file#download-minigpt-med-trained-model-weights)]|[[Github](https://github.com/Vision-CAIR/MiniGPT-Med?tab=readme-ov-file#dataset)]|[[Github](https://github.com/Vision-CAIR/MiniGPT-Med)]|\n|`Fleming-VL`|[[arXiv](https://arxiv.org/abs/2511.00916)]|[[HF (8B)](https://huggingface.co/UbiquantAI/Fleming-VL-8B)][[HF (38B)](https://huggingface.co/UbiquantAI/Fleming-VL-38B)]|-|[[Github](https://github.com/UbiquantAI/Fleming-VL)]|\n|`VILA-M3`|[[arXiv](https://arxiv.org/abs/2411.12915)]|[[HF (3B)](https://huggingface.co/MONAI/Llama3-VILA-M3-3B)][[HF (8B)](https://huggingface.co/MONAI/Llama3-VILA-M3-8B)][[HF (13B)](https://huggingface.co/MONAI/Llama3-VILA-M3-13B)]|-|[[Github](https://github.com/Project-MONAI/VLM-Radiology-Agent-Framework)]|\n|`MedGemma-1.5`|[[Blog](https://research.google/blog/next-generation-medical-image-interpretation-with-medgemma-15-and-medical-speech-to-text-with-medasr/)]|[[HF (4B)](https://huggingface.co/google/medgemma-1.5-4b-it)]|-|[[Github](https://github.com/google-health/medgemma)]|\n|`MediX-R1`|[[arXiv](https://arxiv.org/abs/2602.23363)]|[[HF (2B)](https://huggingface.co/MBZUAI/MediX-R1-2B)][[HF (8B)](https://huggingface.co/MBZUAI/MediX-R1-8B)][[HF (30B)](https://huggingface.co/MBZUAI/MediX-R1-30B)]|[[HF](https://huggingface.co/datasets/MBZUAI/medix-rl-data)]|[[Github](https://github.com/mbzuai-oryx/MediX-R1)]|\n|`MedMO`|[[arXiv](https://arxiv.org/abs/2602.06965)]|[[HF (4B)](https://huggingface.co/MBZUAI/MedMO-4B)][[HF (8B)](https://huggingface.co/MBZUAI/MedMO-8B)][[HF (8B-Next)](https://huggingface.co/MBZUAI/MedMO-8B-Next)]|-|[[Github](https://github.com/genmilab/MedMO)]|\n|`MedGPT-oss`|[[arXiv](https://arxiv.org/abs/2603.00842)]|-|-|-|\n|`OctoMed`|[[arXiv](https://arxiv.org/abs/2511.23269)]|[[HF (7B)](https://huggingface.co/OctoMed/OctoMed-7B)]|-|-|\n|`QoQ-Med`|[[arXiv](https://arxiv.org/abs/2506.00711)]|[[HF (7B)](https://huggingface.co/ddvd233/QoQ-Med-VL-7B)][[HF (32B)](https://huggingface.co/ddvd233/QoQ-Med-VL-32B)]|-|[[Github](https://github.com/DDVD233/QoQ_Med)]|\n|`MedVLThinker`|[[arXiv](https://arxiv.org/abs/2508.02669)]|[[HF (3B/7B/32B)](https://huggingface.co/collections/UCSC-VLAA/medvlthinker)]|[[HF](https://huggingface.co/collections/UCSC-VLAA/medvlthinker-688f52224fb7ff7d965d581d)]|[[Github](https://github.com/UCSC-VLAA/MedVLThinker)]|\n|`Citrus-V`|[[arXiv](https://arxiv.org/pdf/2509.19090)]|[[HF (8B)](https://huggingface.co/jdh-algo/Citrus-V-8B-v1.0)]|[[HF](https://huggingface.co/datasets/jdh-algo/MeCoVQA-G-Plus)]|[[Github](https://github.com/jdh-algo/Citrus-V)]|\n|`ClinFusion`|[[arXiv](https://arxiv.org/abs/2607.24743)]|[[HF (8B)](https://huggingface.co/Alibaba-DAMO-Academy/ClinFusion-8B)][[HF (32B)](https://huggingface.co/Alibaba-DAMO-Academy/ClinFusion-32B)]|-|[[Github](https://github.com/alibaba-damo-academy/ClinFusion)]|\n\n\n\u003cdiv align=\"right\"\u003e\n  \u003cb\u003e\u003ca href=\"#contents\"\u003e↥ back to top\u003c/a\u003e\u003c/b\u003e\n\u003c/div\u003e\n\n## 3. Datasets\n\n### 3.1 Text\n\n|**Data Name**|**Paper**|**Link**|**Quantity**|\n|:-|:-:|:-:|:-:|\n|`Huatuo-26M`|[[arXiv](https://arxiv.org/abs/2305.01526)]|[[Github](https://github.com/FreedomIntelligence/Huatuo-26M)]|26,000,000|\n|`medical-o1-reasoning-SFT`|[[arXiv](https://arxiv.org/pdf/2412.18925)]|[[HF](https://huggingface.co/datasets/FreedomIntelligence/medical-o1-reasoning-SFT)]|25,000|\n|`ReasonMed`|[[arXiv](https://arxiv.org/abs/2506.09513)]|[[HF](https://huggingface.co/datasets/YuSun-AI/ReasonMed)]|370,000|\n|`Multilingual-Medical-Corpus`|[[arXiv](https://arxiv.org/abs/2404.07613)]|[[HF](https://huggingface.co/datasets/HiTZ/Multilingual-Medical-Corpus)]|3M|\n|`AI Medical Dataset`|[[arXiv](https://arxiv.org/abs/2404.07613)]|[[HF](https://huggingface.co/datasets/ruslanmv/ai-medical-dataset)]|27,000,000|\n|`AfriMed-QA`|[[Paper](https://aclanthology.org/2025.acl-long.96.pdf)]|[[HF](https://huggingface.co/datasets/intronhealth/afrimedqa_v2)]|15,275|\n\n\n\u003cdiv align=\"right\"\u003e\n  \u003cb\u003e\u003ca href=\"#contents\"\u003e↥ back to top\u003c/a\u003e\u003c/b\u003e\n\u003c/div\u003e\n\n### 3.2 Multimodal\n\n|**Data Name**|**Paper**|**Link**|**Quantity**|\n|:-|:-:|:-:|:-:|\n|`PubMedVision`|[[arXiv](https://arxiv.org/abs/2406.19280)]|[[HF](https://huggingface.co/datasets/FreedomIntelligence/PubMedVision)]|1,294,062|\n|`Med-MAT`|[[arXiv](https://arxiv.org/abs/2412.20070)]|[[HF](https://huggingface.co/datasets/FreedomIntelligence/Med-MAT)]|2,360,000|\n|`MedTrinity`|[[arXiv](https://arxiv.org/abs/2408.02900)]|[[HF](https://huggingface.co/datasets/UCSC-VLAA/MedTrinity-25M)]|25,000,000|\n|`OmniMedVQA`|[[arXiv](https://arxiv.org/pdf/2408.03361)]|[[OpenXLab](https://openxlab.org.cn/datasets/GMAI/OmniMedVQA)]|118,010|\n|`BioVFM`|[[arXiv](https://www.arxiv.org/abs/2505.09329)]|[[Github](https://github.com/JiarunLiu/BioVFM)]|21,000,000|\n|`SLAKE`|[[arXiv](https://arxiv.org/abs/2102.09542)]|[[Website](https://www.med-vqa.com/slake/)]|-|\n|`ChiMed-VL`|[[arXiv](https://arxiv.org/abs/2310.17956)]|[[HF](https://huggingface.co/datasets/williamliu/ChiMed-VL)]|580,014|\n|`BiomedParseData`|[[arXiv](https://arxiv.org/abs/2405.12971)]|[[HF](https://huggingface.co/datasets/microsoft/BiomedParseData)]|6,800,000|\n|`SA-Med2D`|[[arXiv](https://arxiv.org/abs/2311.11969)]|[[HF](https://huggingface.co/datasets/OpenGVLab/SA-Med2D-20M)]|20,000,000|\n|`IMIS`|[[arXiv](https://arxiv.org/pdf/2411.12814)]|[[HF](https://huggingface.co/datasets/General-Medical-AI/IMed-361M)]|361,000,000|\n|`PreCT`|[[arXiv](https://arxiv.org/abs/2410.09890)]|[[HF](https://huggingface.co/datasets/Luffy503/PreCT-160K)]|160,000|\n|`BIOMEDICA`|[[arXiv](https://arxiv.org/abs/2505.22787)]|[[HF](https://huggingface.co/datasets/BIOMEDICA/biomedica_webdataset_24M)]|24M|\n|`MedVision`|[[arXiv](https://arxiv.org/abs/2511.18676)]|[[HF](https://huggingface.co/datasets/YongchengYAO/MedVision)]|30.8M|\n|`OmniScience`|-|[[HF](https://huggingface.co/datasets/UniParser/OmniScience)]|1.5M|\n|`Open-PMC-18M`|[[arXiv](https://arxiv.org/abs/2506.02738)]|[[HF](https://huggingface.co/datasets/vector-institute/open-pmc-18m)]|18M|\n|`Project-Imaging-X`|[[Report](https://github.com/uni-medical/Project-Imaging-X/blob/main/project-imaging-x_dataset-survey.pdf)]|[[HF](https://huggingface.co/datasets/General-Medical-AI/Project-Imaging-X)]|1,000+ open-access medical image datasets|\n|`GMAI-VL-5.5M`|[[arXiv](https://arxiv.org/abs/2411.14522)]|[[HF](https://huggingface.co/datasets/General-Medical-AI/GMAI-VL-5.5M)]|5.5M|\n|`UniMed-5M`|[[arXiv](https://arxiv.org/abs/2510.15710)]|[[HF](https://huggingface.co/datasets/General-Medical-AI/UniMed-5M)]|5M|\n|`BreastStage`|[[arXiv](https://arxiv.org/abs/2606.04911)]|[[HF](https://www.modelscope.cn/datasets/YYangYang/BreastStage)]|1.86M|\n|`OpenMedReason`|[[arXiv](https://arxiv.org/pdf/2606.12169)]|[[HF](https://huggingface.co/datasets/neginb/OpenMedReason)]|193k|\n\n\n\u003cdiv align=\"right\"\u003e\n  \u003cb\u003e\u003ca href=\"#contents\"\u003e↥ back to top\u003c/a\u003e\u003c/b\u003e\n\u003c/div\u003e\n\n## 4. Benchmarks\n\n|**Evaluation Framework**|**Code**|**Supported Benchmark**|\n|:-|:-:|:-:|\n|`MedEvalKit`|[[Github](https://github.com/alibaba-damo-academy/MedEvalKit)]|**（1）Multimodal：**：`MMMU-Medical-test`, `MMMU-Medical-val`, `PMC_VQA`, `OmniMedVQA`, `IU XRAY`, `MedXpertQA-Multimodal`, `CheXpert Plus`, `MIMIC-CXR`, `VQA-RAD`, `SLAKE`, `PATH-VQA`, `MedFrameQA`；**（2）Text-only：**：`MedQA-USMLE`, `MedMCQA`, `PubMedQA`, `Medbullets-op4`, `Medbullets-op5`, `MedXpertQA-Text`, `SuperGPQA`, `HealthBench`, `CMB`, `CMExam`, `CMMLU`, `MedQA-MCMLE`；|\n|`MedBench`|[[Website](https://medbench.opencompass.org.cn/home)]|**Text-only：**：`Med-Exam`, `MedHC`, `MedMC`, `MedSpeQA`, `MedHG`, `MedDG`, `MedLitQA`, `IMCS-V2-MRG`, `DBMHG`, `CMB-Clin-extended`, `DDx-basic`, `DDx-advanced`, `MedTreat`, `CMeEE`, `CMeIE`, `CHIP-CDEE`, `CHIP-CDN`, `CHIP-CTC`, `SMDoc`, `MedSafety`, `DrugCA`, `CriID`|\n|`LiveClin`|[[Github](https://github.com/AQ-MedAI/LiveClin)]|-|\n|`Stanford MedHELM⁠`|[[Website](https://crfm.stanford.edu/helm/medhelm/latest/#/leaderboard)]|Holistic Evaluation of Language Models (HELM)|\n|`Medmarks v0.1⁠`|[[Website](https://sophont.med/blog/medmarks#introduction)]|-|\n|`HealthBench⁠`|[[Github](https://github.com/medicalsphere/HealthBench)]|`healthbench`, `healthbench_hard`, `healthbench_consensus`, `healthbench_meta`, `healthbench_professional`|\n\n\u003cdiv align=\"right\"\u003e\n  \u003cb\u003e\u003ca href=\"#contents\"\u003e↥ back to top\u003c/a\u003e\u003c/b\u003e\n\u003c/div\u003e\n","projects_url":"https://awesome.ecosyste.ms/api/v1/lists/freedomintelligence%2Fawesome-ai4med/projects"}