# Medical Question Answering on HealthBench Overall Source: [Medical Question Answering on HealthBench Overall]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:54:34.134Z Evaluation of model performance on the HealthBench Overall dataset for Medical Question Answering, measured using a general score metric. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Medical Question Answering | | Dataset (including any stated split) | HealthBench Overall | | Metric | Overall Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 16 of 16 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Overall Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Overall Score | Result date | Report paper | | --- | --- | --- | --- | | Baichuan-M2-32B | 60.1 | Not recorded | 698c0d57c97a0b3e3b5e13a3 | | o3 | 59.8 | Not recorded | 698c0d57c97a0b3e3b5e13a3 | | Qwen3-30B-A3B-Instruct + More Query Rubrics | 59.5 | Not recorded | 698c0d57c97a0b3e3b5e13a3 | | Qwen3-4B-Instruct + More Query Rubrics | 52.9 | Not recorded | 698c0d57c97a0b3e3b5e13a3 | | Gemini-2.5-Pro | 52 | Not recorded | 698c0d57c97a0b3e3b5e13a3 | | Qwen3-4B-Instruct + Principle Rubrics | 51.1 | Not recorded | 698c0d57c97a0b3e3b5e13a3 | | Qwen3-4B-Instruct + Doctor Rubrics | 51 | Not recorded | 698c0d57c97a0b3e3b5e13a3 | | Qwen3-235B-Instruct | 50 | Not recorded | 698c0d57c97a0b3e3b5e13a3 | | GPT-4.1 | 47.9 | Not recorded | 698c0d57c97a0b3e3b5e13a3 | | HuatuoGPT-o1-72B | 47.9 | Not recorded | 698c0d57c97a0b3e3b5e13a3 | | Deepseek-R1 | 47.4 | Not recorded | 698c0d57c97a0b3e3b5e13a3 | | Qwen3-4B-Instruct + Draft Rubrics | 46.9 | Not recorded | 698c0d57c97a0b3e3b5e13a3 | | Qwen3-30B-A3B-Instruct | 46.8 | Not recorded | 698c0d57c97a0b3e3b5e13a3 | | Qwen3-32B | 46.1 | Not recorded | 698c0d57c97a0b3e3b5e13a3 | | Qwen3-4B-Instruct | 40.6 | Not recorded | 698c0d57c97a0b3e3b5e13a3 | | Claude-3.7-Sonnet | 34.6 | Not recorded | 698c0d57c97a0b3e3b5e13a3 | ### Baichuan-M2-32B Overall Score: 60.1. Result ID: 6995f6c85698665ec42ab240. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"Specialized LLM"}. This record does not assert independent reproduction. ### o3 Overall Score: 59.8. Result ID: 6995f6c85698665ec42ab23c. [Reporting paper]() Recorded evaluation configuration: {"Type":"Closed-source LLM"}. This record does not assert independent reproduction. ### Qwen3-30B-A3B-Instruct + More Query Rubrics Overall Score: 59.5. Result ID: 6995f6c85698665ec42ab248. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"backbone":"Qwen3-30B-A3B-Instruct","supervision":"More Query Rubrics"}. This record does not assert independent reproduction. ### Qwen3-4B-Instruct + More Query Rubrics Overall Score: 52.9. Result ID: 6995f6c85698665ec42ab246. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"backbone":"Qwen3-4B-Instruct","supervision":"More Query Rubrics"}. This record does not assert independent reproduction. ### Gemini-2.5-Pro Overall Score: 52. Result ID: 6995f6c85698665ec42ab23e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"Closed-source LLM"}. This record does not assert independent reproduction. ### Qwen3-4B-Instruct + Principle Rubrics Overall Score: 51.1. Result ID: 6995f6c85698665ec42ab245. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"backbone":"Qwen3-4B-Instruct","supervision":"Principle Rubrics"}. This record does not assert independent reproduction. ### Qwen3-4B-Instruct + Doctor Rubrics Overall Score: 51. Result ID: 6995f6c85698665ec42ab244. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"backbone":"Qwen3-4B-Instruct","supervision":"Doctor Rubrics"}. This record does not assert independent reproduction. ### Qwen3-235B-Instruct Overall Score: 50. Result ID: 6995f6c85698665ec42ab23a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"Open-source LLM"}. This record does not assert independent reproduction. ### GPT-4.1 Overall Score: 47.9. Result ID: 6995f6c85698665ec42ab23f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"Closed-source LLM"}. This record does not assert independent reproduction. ### HuatuoGPT-o1-72B Overall Score: 47.9. Result ID: 6995f6c85698665ec42ab241. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"Specialized LLM"}. This record does not assert independent reproduction. ### Deepseek-R1 Overall Score: 47.4. Result ID: 6995f6c85698665ec42ab239. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"Open-source LLM"}. This record does not assert independent reproduction. ### Qwen3-4B-Instruct + Draft Rubrics Overall Score: 46.9. Result ID: 6995f6c85698665ec42ab243. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"backbone":"Qwen3-4B-Instruct","supervision":"Draft Rubrics"}. This record does not assert independent reproduction. ### Qwen3-30B-A3B-Instruct Overall Score: 46.8. Result ID: 6995f6c85698665ec42ab247. [Reporting paper]() Recorded evaluation configuration: {"Type":"Our Method baseline"}. This record does not assert independent reproduction. ### Qwen3-32B Overall Score: 46.1. Result ID: 6995f6c85698665ec42ab23b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"Open-source LLM"}. This record does not assert independent reproduction. ### Qwen3-4B-Instruct Overall Score: 40.6. Result ID: 6995f6c85698665ec42ab242. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"Our Method baseline"}. This record does not assert independent reproduction. ### Claude-3.7-Sonnet Overall Score: 34.6. Result ID: 6995f6c85698665ec42ab23d. [Reporting paper]() Recorded evaluation configuration: {"Type":"Closed-source LLM"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.