MIA 1: our first Medical Intelligent Agent
Today we're launching MIA 1, our Medical Intelligent Agent: a clinical reasoning model built on the open Qwen3.8-27B. Research release.
Today we're launching MIA 1, our Medical Intelligent Agent.
Our goal at Dr. Max Health is ambitious: AI that helps clinicians reason through real clinical cases. MIA 1 is our first step.
MIA 1 builds on the open Qwen3.8-27B model with our clinical reasoning harness. It does not change the model's weights: it gives the model instructions written for clinicians and an answer step that drafts, checks the draft against what a complete answer needs, and tightens it.
Built for clinicians: 54.1 on HealthBench Professional, up from 41.3 for Qwen3.8-27B on its own, with answers less than half as long on average. Claude Opus 5.5, run by us on the same questions, scores 65.1.
Hard cases: 39.7 on a 100-question sample of HealthBench Hard, against 37.6 for Qwen3.8-27B and 43.8 for Claude Opus 5.5.
Compact: 27 billion parameters.
Clinical calculations: Separately, our Qwen-based calculator-enabled configuration scored 86.6% on MedCalc-Bench Verified (75.7% without tools; Claude Opus 5.5 88.2% without tools). It is a different configuration from the MIA 1 setup evaluated on HealthBench above.
Research release. Hospitals, clinics and research partners: contact us via drmaxhealth.de.
This is just the beginning.
How we evaluated: HealthBench Professional (325 examples held out from our development selection) and HealthBench Hard (100-question sample): scores are length-adjusted following the HealthBench Professional paper and are the mean of two blind model graders (Qwen 27B and Claude Opus 5.5) using the official rubrics; per-grader and raw scores will be in the technical report. MedCalc-Bench Verified (1,100 test items): one pre-registered scoring rule for every model; the calculator-enabled Qwen3.8-27B configuration uses calculator tools, and its score and the score of Qwen3.8-27B without tools are averages over 8 answers per question; Claude Opus 5.5 answers once per question, without tools. All models were run by Dr. Max Health on the same questions. These internal results are not comparable to official HealthBench or MedCalc-Bench numbers.
MIA 1 is a research model, not a medical device; not for diagnosis or treatment decisions.
Built on Qwen3.8-27B.
A technical report will follow.