Awesome-LLM-Patient-Simulators ✨

This repository provides a curated collection of research papers on Large Language Models (LLMs) for patient simulation in healthcare, covering:

• 🏥 Virtual patient interactions
• 🎓 Clinical training applications
• 🔍 Diagnostic reasoning systems
• 🧠 Mental health simulations

Table of Contents 📋

• Fundamental Research
  • Virtual Patient Development (Historical Context)
• Methodology
  • Agent Systems & Simulation Environments
  • NLP & Dialogue Systems
  • Generative Models & Data Integration
  • Prompt Engineering & Chatbots
  • Frameworks, Platforms & Workflows
• Applications
  • General Medical Education
  • Nurse Training
  • Psychiatric Medicine
  • Clinical Decision Support
  • Patient Communication Simulation
• Evaluation Methods & Effects
• Challenges & Limitations
  • Bias & Ethical Considerations
• Datasets

---

🔍 Fundamental Research 📚

Paper	Published in	Focus Area	Description	Data/Demo
Simulator Limitations and Their Effects on Decision-Making	Sage 1996/10	High-Fidelity Simulation Principles	Outlines core principles of high-fidelity patient simulation (dynamic case design, structured feedback, and behavioral assessment) that remain foundational for modern LLM-based patient simulation systems in medical education.	-
Lessons Learned from the Usability Evaluation of a Simulated Patient Dialogue System	Springer Link 2021/05	Virtual Patient Dialogue System Usability	Developed a virtual patient dialogue system for medical students to practice.	Data | Demo
The simulated patient method: Design and application in health services research	Science Direct 2021/12	Simulated Patient Method Design (Health Services)	Explores the design and application of the simulated patient method in health services research, particularly in pharmacy practice.	-
Patient-Drama: A Literature Review of Simulated Patient Experiences in Medical Education and Training	Lesley 2022/04	Simulated Patient Experience	Examines simulated patient experiences through the lens of drama therapy. Four specific types of simulated patient experiences are examined- peer role play, peer simulation, standardized patient experiences, and clinical scenario drama.	-
The Role of ChatGPT, Generative Language Models, and Artificial Intelligence in Medical Education	JMIR Med Educ 2023/03	LLMs in Medical Education	Explores the potential application of ChatGPT and other generative language models in medical education, including virtual patient simulation.	-
ChatGPT and Other Large Language Models in Medical Education — Scoping Literature Review	Springer 2024/11	LLMs in Medical Education	A scoping review of the first-year research on the application of large language models (LLMs) in medical education was conducted, and a total of 145 studies were included. The results indicated that most studies focused on the ability of LLMs to pass medical examinations. A few discussed the teaching uses of LLMs such as in simulated patient cases. The number of studies that truly implemented teaching experiments was very limited.	-
From ChatGPT to DeepSeek: Can LLMs Simulate Humanity?	arXiv 2025/02	LLM Human Simulation Capabilities	Analyses LLMs' ability to simulate human behavior, discussing key limitations (e.g., bias, lack of incentives) and future alignment strategies.	Data(Appendix)

🤒 Virtual Patient Development (Historical Context)

Paper	Published in	Focus Area	Description
Virtual Patient Simulation at U.S. and Canadian Medical Schools	ResearchGate (Orig. Acad Med) 2007	VP Adoption in Medical Schools	Examines the adoption, implementation, and educational impact of virtual patient simulations in medical schools across the U.S. and Canada.
High-fidelity patient simulation: considerations for effective learning.	ResearchGate (Orig. J Contin Educ Health Prof) 2010/09	High-Fidelity Simulation Design	Examines high-fidelity patient simulation in medical education, emphasizing key design and implementation factors that optimize learning outcomes.
Virtual patient simulation: knowledge gain or knowledge loss?	BMC Medical Education 2010/09	VP Effectiveness (Clinical Skills)	Explores the use of virtual patient simulations in medical education, demonstrating their effectiveness in improving clinical decision-making skills.
Virtual patient simulation: what do students make of it? A focus group study	BMC Medical Education 2010/12	VP Effectiveness (Student Perspective)	Evaluates the effectiveness of virtual patient simulations in medical education, finding that they enhance clinical reasoning skills among students.
Effectiveness of patient simulation in nursing education: meta-analysis.	Nurse Education Today 2015/01	VP Effectiveness (Nursing Meta-Analysis)	Identify the best available evidence about the effects of patient simulation in nursing education through a meta-analysis.
Guidelines for the design of a virtual patient for psychiatric interview training	Springer Link 2020/07	VP Design Guidelines (Psychiatry)	Specific guidelines for designing psychiatric virtual patients... can be directly applied to LLM-driven patient simulation systems...

---

🛠️ Methodology ⚙️

This section categorizes papers based on their core methodological contribution to LLM-based patient simulation.

🤖 Agent Systems & Simulation Environments

Focus on systems using multiple interacting agents or complex agent behaviors.

Paper	Submitted in	Description	Method	Code/Project/Data
Towards Conversational Diagnostic AI	arXiv 2024/01	Introduces AMIE, an AI-driven system powered by LLMs that simulates virtual patient-doctor interactions for clinical education...	LLM, Agent (Implicit), Dialogue System	Resource
Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents	arXiv 2024/05	Introduce a simulacrum of hospital called Agent Hospital that simulates the entire process of treating illness... all patients, nurses, and doctors are LLM-powered autonomous agents.	LLM, Agent System, Simulation Environment	Dataset_MedQA
AI Hospital: Benchmarking Large Language Models in a Multi-agent Medical Interaction Simulator	arXiv 2024/06 (Revised)	Introduces AI Hospital, a multi-agent framework for evaluating large language models in simulated medical interactions.	LLM, Agent System, Benchmark, Evaluation Framework	Project | Dataset_MVME | Dataset_MedQA | Dataset_PubMedQA | Dataset_MedMCQA
Towards a Client-Centered Assessment of LLM Therapists by Client Simulation	arXiv 2024/06	Proposes ClientCAST, a novel LLM-based client simulation framework to assess the performance of AI therapists...	LLM, Agent (Client Simulation), Evaluation Framework	Project | Dataset_AnnoMI
AIPatient: Simulating Patients with EHRs and LLM Powered Agentic Workflow	arXiv 2024/10	Presents a novel agentic workflow combining EHR knowledge graphs with Reasoning-RAG architecture.	LLM, Agent System, RAG, Knowledge Graph, EHR Integration	Code | Data (MIMIC-III)
LLMs Can Simulate Standardized Patients via Agent Coevolution	arXiv 2024/12	Introduces the EvoPatient framework, which utilizes multi-agent coevolution to enable LLMs to simulate standardized patients...	LLM, Agent System, Coevolution	Project
Scaffolding Empathy: Training Counselors with Simulated Patients and Utterance-level Performance Visualizations	arXiv 2025/02	Introduces a LLM-based multi-agent system (SimPatient) with dynamic cognitive modeling and real-time feedback to enhance motivational interviewing (MI) training...	LLM, Agent System, Cognitive Modeling, Feedback Visualization	-
Self-Evolving Multi-Agent Simulations for Realistic Clinical Interactions	arXiv 2025/03	introduce MedAgentSim, an open-source simulated clinical environment with doctor, patient, and measurement agents designed to evaluate... LLM performance...	LLM, Agent System, Simulation Environment, Evaluation	Dataset_MedQA

🗣️ NLP & Dialogue Systems

Focus on natural language processing techniques and the architecture of dialogue systems, including hybrid approaches.

Paper	Submitted in	Description	Method	Code/Project/Data
Artificial intelligence in virtual standardized patients: Combining natural language understanding and rule based dialogue management...	Medical Teacher 2022/11	Developed a novel hybrid dialogue system using ASR, hybrid AI, and automated speech generation, enabling artificially intelligent VSPs...	NLP, Dialogue System, Rule-based AI, ASR, Speech Generation	-

🧬 Generative Models & Data Integration

Focus on the use of generative models for tasks like data augmentation, image generation, or integrating structured data.

Paper	Submitted in	Description	Method	Code/Project/Data
Automated Generation of High-Quality Medical Simulation Scenarios Through Integration of Semi-Structured Data and Large Language Models	arXiv 2024/05	Introduces a semi-structured data and LLM-integrated framework to automate the generation of medical simulation scenarios...	LLM, Structured Data Integration, RAG (Implicit), Scenario Generation	-
MedDiT: A Knowledge-Controlled Diffusion Transformer Framework for Dynamic Medical Image Generation in Virtual Simulated Patient	arXiv 2024/08	Introduces MedDiT, a knowledge-controlled diffusion transformer framework designed to dynamically generate medical images for virtual simulated patients.	Transformer, Diffusion Models, Generative Models, Knowledge Control, Image Generation	-
Augmenting Insufficiently Accruing Oncology Clinical Trials Using Generative Models: Validation Study	JMIR 2025/03	Explores the use of generative models to augment oncology clinical trials with insufficient patient accrual, validating their effectiveness in simulating additional patient data to improve trial outcomes.	Generative Models, Data Augmentation	Data (Appendix)

💬 Prompt Engineering & Chatbots

Focus on the direct application of LLMs via carefully crafted prompts or chatbot interfaces as the primary contribution.

Paper	Submitted in	Description	Method	Code/Project/Data
A Generative Pretrained Transformer (GPT)–Powered Chatbot as a Simulated Patient to Practice History Taking...	JMIR 2024/01	Employs a GPT-powered chatbot as a simulated patient, using meticulously crafted prompts to replicate realistic clinical interactions...	LLM, Prompt Engineering, Chatbot	Data(Appendix)
Application of Large Language Models in Medical Training Evaluation—Using ChatGPT as a Standardized Patient: Multimetric Assessment	JMIR 2025/01	Optimized ChatGPT for medical standardized patient simulation via prompt engineering, enhancing clinical accuracy and realism.	LLM, Prompt Engineering, Evaluation	Data(Appendix)

🏗️ Frameworks, Platforms & Workflows

Focus on integrated systems, platforms, specific workflows, or hardware integrations for patient simulation.

Paper	Submitted in	Description	Method	Code/Project/Data
Creating Virtual Patients using Robots and Large Language Models: A Preliminary Study with Medical Students	ACM 2024/03	Presents a virtual patient platform combining the social robot Furhat with LLMs (GPT-3.5-turbo) to enhance clinical reasoning training...	LLM, Generative Models, Robotics Integration, Dialogue System	-
Leveraging Large Language Model as Simulated Patients for Clinical Education	arXiv 2024/04	Introduces CureFun, an integrated framework that utilizes LLMs as simulated patients for clinical education, enhancing student-patient dialogues...	LLM, Framework, Evaluation	-
RasPatient Pi: A Low-Cost Customizable LLM-Based Virtual Standardized Patient Simulator	Springer Link 2025 (Year inferred)	Presents RasPatient Pi, a low-cost, customizable virtual standardized patient simulator based on Large Language Models (LLMs).	LLM, Hardware Integration (Raspberry Pi), Framework	Project

---

🏥 Applications 🩺

🩺 General Medical Education

Paper	Published in	Description	Key Feature/System	Code/Project/Data
Virtual patient simulation: what do students make of it? A focus group study.	BMC Med Educ 2010	Evaluates virtual patient simulations in medical training, concluding that they significantly improve clinical reasoning skills...	Virtual Patient Simulation	-
Using virtual standardized patients to accurately assess information gathering skills in medical students	Medical Teacher 2019/06	Developed a virtual standardized patient (VSP) system that allows students to practice their history taking skills and receive immediate feedback.	Virtual Standardized Patient (VSP) System, Automated Assessment	-
The Role of Large Language Models in Medical Education: Applications and Implications	JMIR 2023/08	Shows LLMs can simulate patient encounters for medical education but lack nonverbal communication and may exhibit biases.	LLM for Patient Encounters	-
Virtual Standardized LLM-AI Patients for Clinical Practice	Annual Review of CyberTherapy and Telemedicine 2024/01	Explores the use of virtual standardized AI patients powered by LLMs to enhance clinical practice and therapy training.	LLM-AI Patients	-
Increasing Realism and Variety of Virtual Patient Dialogues for Prenatal Counseling Education Through a Novel Application of ChatGPT: Exploratory Observational Study	JMIR 2024/02	Explored the effectiveness of generative AI (ChatGPT) in developing realistic virtual standardized patient dialogues to teach prenatal counseling skills.	Virtual Patient Dialogues	-
Enhancing communication and clinical reasoning in medical education: Building virtual patients with generative AI	Future Healthcare Journal 2024/04	Demonstrates the viability of using LLM technology, specifically GPT-3.5 and GPT-4, to create realistic virtual patients.	Generative AI (GPT-3.5, GPT-4) for VP Creation	-
Utilizing generative conversational artificial intelligence to create simulated patient encounters... anaesthesia training	Postgraduate Medical Journal 2024/04	Explores the use of generative conversational artificial intelligence to create simulated patients for medical education, ‘Convai’ was used...	Generative Conversational AI (Convai)	-
Simulating Diverse Patient Populations Using Patient Vignettes and Large Language Models	ACL Anthology 2024/05	Demonstrates how LLMs like GPT-4 can simulate diverse patient populations via role-prompted vignettes, enabling cost-effective testing...	LLM (GPT-4), Patient Vignettes, Role-Prompting	-
Roleplay-doh: Enabling Domain-Experts to Create LLM-simulated Patients via Eliciting and Adhering to Principles	arXiv 2024/07	Introduces Roleplay-doh, a tool that enables domain experts to collaboratively create realistic AI patient simulations by providing qualitative feedback.	Roleplay-doh Tool, Collaborative Creation, Qualitative Feedback	Project
Creating virtual patients using large language models: scalable, global, and low cost	PubMed (Cureus) 2024/07	Presents a low-cost, AI-driven virtual patient (LLM-VP) system using LLMs like GPT-4 for clinical reasoning training...	LLM-VP System (GPT-4 based)	-
A Language Model-Powered Simulated Patient With Automated Feedback for History Taking: Prospective Study	JMIR 2024/08	Presents a language model-powered simulated patient designed to enhance history-taking skills... providing automated feedback...	LLM Simulated Patient, Automated Feedback	-
Enhancing Medical Interview Skills Through AI-Simulated Patient Interactions: Nonrandomized Controlled Trial	JMIR 2024/09	Demonstrates that AI-simulated patient interactions effectively enhance medical interview skills in a nonrandomized controlled trial...	AI-Simulated Patient Interactions	-
Enhancing Patient-Centric Communication: Leveraging LLMs to Simulate Patient Perspectives (Note: Link uses original ID 2501)	arXiv 2025/01	Explores LLM-based patient simulation via persona prompts, showing higher accuracy for educated groups but biases against underserved populations.	LLM, Persona Prompts	-
MedSimAI: Simulation and Formative Feedback Generation to Enhance Deliberate Practice in Medical Education (Note: Link uses original ID 2503)	arXiv 2025/03	Introduces MedSimAI, an AI-driven platform designed to enhance medical education by providing realistic simulations and formative feedback.	MedSimAI Platform, Simulation, Formative Feedback	-

👩‍⚕️ Nurse Training

Paper	Published in	Description	Key Feature/System
Evaluation of Large Language Model Generated Dialogues for an AI Based VR Nurse Training Simulator	Springer Link 2024/06	Evaluates the efficacy of LLM-generated dialogues (GPT-3.5, Bard, ClaudeAI) for VR nurse training simulators	LLM (GPT-3.5, Bard, ClaudeAI), VR, Nursing
Assessing the efficacy of ChatGPT as a virtual patient in nursing simulation training: A study on nursing students' experience	Science Direct 2024/07	Assessed ChatGPT's effectiveness in nursing simulation, which holds promise in enriching clinical learning.	ChatGPT, VR, Nursing

🧠 Psychiatric Medicine

Paper	Published in	Description	Key Feature/System	Code/Project/Data
Embodied Virtual Patients as a Simulation-Based Framework for Training Clinician-Patient Communication Skills... Psychiatric and Geriatric Care	Frontiers 2022/06	The application of virtual patients in psychiatric and geriatric care is explored, especially for training doctor-patient communication skills.	Embodied Virtual Patients	-
LLM-empowered Chatbots for Psychiatrist and Patient Simulation: Application and Evaluation	arXiv 2023/05	Demonstrates ChatGPT's feasibility in powering psychiatric patient and doctor chatbots, validated through real clinician-patient evaluations...	LLM (ChatGPT), Chatbots (Patient & Doctor Simulation)	-
Feasibility assessment of using ChatGPT for training case conceptualization skills in psychological counseling	ScienceDirect 2024/8-12	Investigates the feasibility and effectiveness of using ChatGPT for training case conceptualization skills in psychological counseling(Psychological counseling case conceptualization refers to the comprehensive analysis and assessment of each client.)	LLM (ChatGPT), Assessment, Psychological counseling	-
PATIENT-Ψ: Using Large Language Models to Simulate Patients for Training Mental Health Professionals	arXiv 2024/10	Introduces PATIENT-Ψ, an LLM-based patient simulation system for training mental health professionals in cognitive behavioral therapy.	PATIENT-Ψ System, LLM, CBT Training	-
PSYCHE: A Multi-faceted Patient Simulation Framework for Evaluation of Psychiatric Assessment Conversational Agents	arXiv 2025/01	Presents PSYCHE, a multi-faceted patient simulation framework designed to evaluate psychiatric assessment conversational agents...	PSYCHE Framework, Evaluation Framework	-
A large language model digital patient system enhances ophthalmology history taking skills)	npj Digit. Med. 2025/04	Developed and evaluated an LLM-based digital patient system (LLMDP) via a randomized controlled trial, demonstrating significant improvements in history-taking skills and empathy for ophthalmology trainees.	LLM-SP, Eye manifestations, Education	-

⚕️ Clinical Medicine

Paper	Published in	Description	Key Feature/System	Data/Appendix
ChatGPT Interactive Medical Simulations for Early Clinical Education: Case Study	JMIR Med Educ. 2023/11	Models ChatGPT 3.5's ability to perform interactive clinical simulations and shows this tool's benefit to medical education.	LLM Patient Simulation, Structured Feedback	-
Large language models improve clinical decision making of medical students through patient simulation and structured feedback: a randomized controlled trial	PubMed Central (BMJ HCI) 2024/11	Demonstrates that AI-simulated medical history conversations, particularly when combined with structured feedback, can enhance clinical decision-making skills in medical students.	LLM Patient Simulation, Structured Feedback	Data(Appendix)
Virtual Patients Using Large Language Models: Scalable, Contextualized Simulation of Clinician-Patient Dialogue With Feedback	JMIR 2025/04	Show that VPs powered by large language models(LLMs) can generate authentic dialogues, accurately represent patient preferences, and provide personalized feedback on clinical performance.	LLM Patient Simulation, Evaluation	-

💬 Patient Communication Simulation

Paper	Published in	Description	Key Feature/System
Integrating GPT-Based AI into Virtual Patients to Facilitate Communication Training Among Medical First Responders: Usability Study of Mixed Reality Simulation	JMIR 2025/03	Proposes the use of Large Language Models (LLMs) to simulate authentic patient communication styles and these VPs are evaluated by medical professionals.	LLM, Authentic Communication Style Simulation
Beyond the Script: Testing LLMs for Authentic Patient Communication Styles in Healthcare	arXiv 2025/03	Study how the integration of GPT-based AI in a mixed reality (MR)–VP could support communication training of MFRs(medical first responders).	LLM, Mixed Reality
Modeling Challenging Patient Interactions: LLMs for Medical Communication Training (Note: Link uses original ID 2503)	arXiv 2025/03	Proposes the use of Large Language Models (LLMs) to simulate authentic patient communication styles, specifically personas derived from the Satir model... multilingual applicability.	LLM, Persona Simulation (Satir), Multilingual
AI Standardized Patient Improves Human Conversations in Advanced Cancer Care	arXiv 2025/05	Introduced an AI-based standardized patient system called SOPHIE (Standardized Online Patient for Healthcare Interaction Education) to improve the serious illness communication (SIC) capabilities of healthcare professionals in advanced cancer care.	LLM, Persona Simulation (Satir), Virtual Avatar

---

☑️ Evaluation Methods & Effects 🚨

Paper	Published in	Focus	Description	Project/Benchmark
ChatGPT: when the artificial intelligence meets standardized patients in clinical training	Journal of Translational Medicine 2023/07	Expert Evaluation(Human-Centric)	Collected 10 patient histories related to clinical training and education using ChatGPT, and evaluated them by senior physicians to verify the accuracy of the information generated by ChatGPT simulating SP.	-
Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena	arXiv 2023/10	LLM Evaluation	Explore using strong LLMs as judges to evaluate these models on more open-ended questions. We examine the usage and limitations of LLM-as-a-judge and propose solutions to mitigate some of them.	Data
Analyzing evaluation methods for large language models in the medical field: a scoping review	BMC Med Inform Decis Mak 2024/11	LLM Evaluation Review (Medical)	Reviews studies on LLM evaluations in the medical field and analyzes the research methods used in these studies.	-
NPHardEval: Dynamic Benchmark on Reasoning Ability of Large Language Models via Complexity Classes	arXiv 2024/02 (Revised)	LLM Reasoning Benchmark	Introduces NPHardEval, a dynamic benchmark grounded in computational complexity classes... to rigorously evaluate LLMs' reasoning abilities...	NPHardEval Project
NPHardEval4V: A Dynamic Reasoning Benchmark of Multimodal Large Language Models	arXiv 2024/03	Multimodal LLM Reasoning Benchmark	Introduces NPHardEval4V, a dynamic multimodal benchmark designed to evaluate the pure reasoning abilities of MLLMs... revealing significant gaps between MLLM and LLM reasoning...	NPHardEval4V Project
Assessing the efficacy of ChatGPT as a virtual patient in nursing simulation training...	ScienceDirect (Nurse Educ Pract) 2024/07	ChatGPT Effectiveness Assessment (Nursing)	Assessed ChatGPT's effectiveness in nursing simulation by collecting data of acceptability, accessibility, engagement ratings, and assessing students' interaction skills.	-
PersonaEval: Benchmarking LLMs on Role-Playing Evaluation Tasks	ICLR 2024/10	Role-Playing Evaluation, Benchmark	Introduce PersonaEval, a benchmark designed to assess the effectiveness of LLMs in role-playing evaluation tasks.	-
PingPong: A Benchmark for Role-Playing Language Models with User Emulation and Multi-Model Evaluation	arXiv 2025/04	Role-Playing Language Models Benchmark	Introduces a benchmark for evaluating the role-playing capabilities of language models.	Project

---

⚠️ Challenges & Limitations 🚨

Paper	Published in	Focus Area	Description
A Survey of Large Language Models in Medicine: Progress, Application, and Challenge	arXiv 2024/07 (Revised)	LLM in Medicine Survey	The applications of LLM in medicine are reviewed, covering the challenges of patient simulation (such as dynamic interaction and realism).

🎭 Bias & Ethical Considerations

Paper	Published in	Focus Area	Description
Ethical Considerations in the Use of Artificial Intelligence and Machine Learning in Health Care: A Comprehensive Review	PubMed Central (Cureus) 2024/06	AI/ML Ethics in Healthcare	Explored the multifaceted ethical considerations in the use of AI and ML in health care, including privacy, algorithmic bias, transparency, validation, and professional responsibility.

---

📊 Datasets 💾

This section lists datasets and project repositories mentioned in the papers that are either generated by the simulation process or used for evaluation and grounding. Note that project repositories may contain various resources including code, configuration files, and potentially simulation data or logs. Appendices often contain supplementary information like prompts or evaluation rubrics rather than reusable datasets.

Simulation Dialogue, Configuration & Resources

Dataset/Resource	Paper Year	Language	Data Type	Project/Code	Link
PG-logs-eval	2021/05	French	Dialogue Logs	-	Link
medicinenet-diseases.json	2024/01	English	Disease List	Code Repo	Link
ClientCAST Framework	2024/06	English	Simulation Framework	Project	Project Link
EvoPatient Framework	2023/12	English	Simulation Framework	Project	Project Link
RasPatient Pi	2025 (Year inferred)	English	Simulation Framework	Project	Project Link
Roleplay-doh Tool	2024/07	English	Simulation Tool	Project	Project Link
AIPatient Workflow	2024/10	English	Agentic Workflow	Code	Code Link

Evaluation & Grounding Datasets

Dataset	Task Type	Language	Access	Used In Paper (Year)	Link	Project (if applicable)
MIMIC-III	EHR Data	English	Restricted	2024/10 (AIPatient)	Link	-
MedQA (USMLE)	Medical QA	English	Public	2024/05, 2024/06, 2025/03	Link	AI Hospital
MVME	Medical Vision/Language	Multimodal	Public	2024/06 (AI Hospital)	Link	AI Hospital
PubMedQA	Biomedical QA	English	Public	2024/06 (AI Hospital)	Link	AI Hospital
MedMCQA	Medical QA (India)	English	Public	2024/06 (AI Hospital)	Link	AI Hospital
AnnoMI	Motivational Interviewing	English	Public	2024/06 (ClientCAST)	Link	ClientCAST
NPHardEval	LLM Reasoning Benchmark	English	Public	2024/02	Project Link	NPHardEval
NPHardEval4V	MLLM Reasoning Benchmark	Multimodal	Public	2024/03	Project Link	NPHardEval4V

---

⭐ Star History 📈