# HealthBench: Evaluating Large Language Models Towards Improved Human Health

arXiv: https://arxiv.org/abs/2505.08775 · HTML: https://mlsanity.com/paper/2505.08775/

## Key facts

- Cited by 429 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 52 references that are in the map.
- First posted on arXiv 13 May 2025.

## Builds on (most cited first, 27 of 27)

- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams](https://mlsanity.com/paper/2009.13081/) (2020)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [PubMedQA: A Dataset for Biomedical Research Question Answering](https://mlsanity.com/paper/1909.06146/) (2019)
- [Capabilities of GPT-4 on Medical Challenge Problems](https://mlsanity.com/paper/2303.13375/) (2023)
- [WildChat: 1M ChatGPT Interaction Logs in the Wild](https://mlsanity.com/paper/2405.01470/) (2024)
- [BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining](https://mlsanity.com/paper/2210.10341/) (2022)
- [LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset](https://mlsanity.com/paper/2309.11998/) (2023)
- [Med-Flamingo: a Multimodal Medical Few-shot Learner](https://mlsanity.com/paper/2307.15189/) (2023)
- [Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge](https://mlsanity.com/paper/2410.02736/) (2024)
- [Humans or LLMs as the Judge? A Study on Judgement Biases](https://mlsanity.com/paper/2402.10669/) (2024)
- [PaperBench: Evaluating AI's Ability to Replicate AI Research](https://mlsanity.com/paper/2504.01848/) (2025)
- [RadGraph: Extracting Clinical Entities and Relations from Radiology Reports](https://mlsanity.com/paper/2106.14463/) (2021)
- [Towards Generalist Biomedical AI](https://mlsanity.com/paper/2307.14334/) (2023)
- [Capabilities of Gemini Models in Medicine](https://mlsanity.com/paper/2404.18416/) (2024)
- [WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild](https://mlsanity.com/paper/2406.04770/) (2024)
- [MultiChallenge: A Realistic Multi-Turn Conversation Evaluation Benchmark Challenging to Frontier LLMs](https://mlsanity.com/paper/2501.17399/) (2025)
- [Almanac: Retrieval-Augmented Language Models for Clinical Medicine](https://mlsanity.com/paper/2303.01229/) (2023)
- [Large Language Models are Few-Shot Health Learners](https://mlsanity.com/paper/2305.15525/) (2023)
- [Towards Accurate Differential Diagnosis with Large Language Models](https://mlsanity.com/paper/2312.00164/) (2023)
- [MedAlign: A Clinician-Generated Dataset for Instruction Following with Electronic Medical Records](https://mlsanity.com/paper/2308.14089/) (2023)
- [A Toolbox for Surfacing Health Equity Harms and Biases in Large Language Models](https://mlsanity.com/paper/2403.12025/) (2024)
- [Evaluation of GPT-3.5 and GPT-4 for supporting real-world information needs in healthcare delivery](https://mlsanity.com/paper/2304.13714/) (2023)
- [Towards a Personal Health Large Language Model](https://mlsanity.com/paper/2406.06474/) (2024)
- [Scaling-up Empirical Risk Minimization: Optimization of Incomplete U-statistics](https://mlsanity.com/paper/1501.02629/) (2015)

## Built on by (most cited first, 30 of 429)

- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains](https://mlsanity.com/paper/2507.17746/) (2025)
- [Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning](https://mlsanity.com/paper/2506.07044/) (2025)
- [OpenRubrics: Towards Scalable Synthetic Rubric Generation for Reward Modeling and LLM Alignment](https://mlsanity.com/paper/2510.07743/) (2025)
- [Reinforcement Learning with Rubric Anchors](https://mlsanity.com/paper/2508.12790/) (2025)
- [MedHELM: Holistic Evaluation of Large Language Models for Medical Tasks](https://mlsanity.com/paper/2505.23802/) (2025)
- [PostTrainBench: Can LLM Agents Automate LLM Post-Training?](https://mlsanity.com/paper/2603.08640/) (2026)
- [Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning](https://mlsanity.com/paper/2508.16949/) (2025)
- [Rethinking Rubric Generation for Improving LLM Judge and Reward Modeling for Open-ended Tasks](https://mlsanity.com/paper/2602.05125/) (2026)
- [Sequential Diagnosis with Language Models](https://mlsanity.com/paper/2506.22405/) (2025)
- [Baichuan-M2: Scaling Medical Capability with Large Verifier System](https://mlsanity.com/paper/2509.02208/) (2025)
- [Every Step Evolves: Scaling Reinforcement Learning for Trillion-Scale Thinking Model](https://mlsanity.com/paper/2510.18855/) (2025)
- [Alternating Reinforcement Learning for Rubric-Based Reward Modeling in Non-Verifiable LLM Post-Training](https://mlsanity.com/paper/2602.01511/) (2026)
- [Chasing the Tail: Effective Rubric-based Reward Modeling for Large Language Model Post-Training](https://mlsanity.com/paper/2509.21500/) (2025)
- [VitaBench: Benchmarking LLM Agents with Versatile Interactive Tasks in Real-world Applications](https://mlsanity.com/paper/2509.26490/) (2025)
- [Online Rubrics Elicitation from Pairwise Comparisons](https://mlsanity.com/paper/2510.07284/) (2025)
- [Answer Matching Outperforms Multiple Choice for Language Model Evaluation](https://mlsanity.com/paper/2507.02856/) (2025)
- [A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers](https://mlsanity.com/paper/2508.21148/) (2025)
- [Beyond GPT-5: Making LLMs Cheaper and Better via Performance-Efficiency Optimized Routing](https://mlsanity.com/paper/2508.12631/) (2025)
- [DeepResearch Bench II: Diagnosing Deep Research Agents via Rubrics from Expert Reports](https://mlsanity.com/paper/2601.08536/) (2026)
- [Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges](https://mlsanity.com/paper/2604.13602/) (2026)
- [PRBench: Large-Scale Expert Rubrics for Evaluating High-Stakes Professional Reasoning](https://mlsanity.com/paper/2511.11562/) (2025)
- [STEP3-VL-10B Technical Report](https://mlsanity.com/paper/2601.09668/) (2026)
- [Auto-Rubric: Learning From Implicit Weights to Explicit Rubrics for Reward Modeling](https://mlsanity.com/paper/2510.17314/) (2025)
- [Beyond Seeing: Evaluating Multimodal LLMs on Tool-Enabled Image Perception, Transformation, and Reasoning](https://mlsanity.com/paper/2510.12712/) (2025)
- [A Novel Evaluation Benchmark for Medical LLMs: Illuminating Safety and Effectiveness in Clinical Domains](https://mlsanity.com/paper/2507.23486/) (2025)
- [RubricBench: Aligning Model-Generated Rubrics with Human Standards](https://mlsanity.com/paper/2603.01562/) (2026)
- [Real-World Doctor Agent with Proactive Consultation through Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2505.19630/) (2025)
- [AlgoTune: Can Language Models Speed Up General-Purpose Numerical Programs?](https://mlsanity.com/paper/2507.15887/) (2025)
- [Reinforcing Chain-of-Thought Reasoning with Self-Evolving Rubrics](https://mlsanity.com/paper/2602.10885/) (2026)

## Abstract (arXiv)

We present HealthBench, an open-source benchmark measuring the performance and safety of large language models in healthcare. HealthBench consists of 5,000 multi-turn conversations between a model and an individual user or healthcare professional. Responses are evaluated using conversation-specific rubrics created by 262 physicians. Unlike previous multiple-choice or short-answer benchmarks, HealthBench enables realistic, open-ended evaluation through 48,562 unique rubric criteria spanning several health contexts (e.g., emergencies, transforming clinical data, global health) and behavioral dimensions (e.g., accuracy, instruction following, communication). HealthBench performance over the last two years reflects steady initial progress (compare GPT-3.5 Turbo's 16% to GPT-4o's 32%) and more rapid recent improvements (o3 scores 60%). Smaller models have especially improved: GPT-4.1 nano outperforms GPT-4o and is 25 times cheaper. We additionally release two HealthBench variations: HealthBench Consensus, which includes 34 particularly important dimensions of model behavior validated via physician consensus, and HealthBench Hard, where the current top score is 32%. We hope that HealthBench grounds progress towards model development and applications that benefit human health.