By working closely with physician experts and listening to feedback, Doximity has quietly built the best clinical AI in the industry. I'm incredibly proud of this team and couldn't be more excited for this next chapter.
Finally: an independent, head-to-head test of clinical AI models.
This week, Stanford's Arise Lab published one of the most comprehensive independent evaluations of clinical AI to date. The benchmark compared 24 frontier and clinical AI models, producing 12,747 expert rankings on their answers to real-world clinical questions.
We were excited to see Doximity Ask outperform
OpenEvidence, GPT-5.6, Claude Fable 5, Gemini 3.1 Pro, and other leading frontier AI models.
The bigger story, though, is that clinical AI is finally getting the kind of rigorous, independent benchmarking it needs.
NEW: Doximity and Dr. Eric Topol launch PeerCheck, a physician-led effort to bring peer review into clinical AI.
PeerCheck embeds expert review directly into DoxGPT, letting cited clinicians evaluate and improve AI answers for accuracy, evidence strength, and bias.
We can't let generative AI into the practice of medicine without human oversight. That's why Dr. @reginabenjamin and I are announcing an ambitious initiative today called PeerCheck, physician led peer review of medical information @doximity https://t.co/SiHedH3fU1
📊 Our Doximity Compensation Report found inflation outpaced physician salary growth for nearly half of all medical specialties over the past five years.
🔎 We explored the data to understand what specialties were affected.
Read the full report at: https://t.co/WnWVENEVNZ
Big Friday just in: +857K doses reported administered over yesterday's total (vs. 600K last Friday)! This includes 563K newly vaccinated, highest since July 1. Over 190M Americans with at least one dose. 69.6% of adults with at least one dose. Let's do this!
New on the blog: Building A Test Automation Pipeline for Data Science by Sam Hart.
Leveraging testing tools and techniques to improve confidence in your data pipelines
https://t.co/GkES9tKMbI