BiomedCLIP
Microsoft's biomedical vision-language model pretrained on 15M PubMed Central figure–caption pairs.
| Category | Clinical & biomedical LLMs |
|---|---|
| First public | 2023-03-02 (source) |
| Paper | https://doi.org/10.1056/AIoa2400640 · NEJM AI (2025) |
| License | MIT |
| Pricing | Open source |
| Tags | #vision-language#clip#medical-imaging |
| Last checked | 2026-10-16 |
Specs
| Modality | Biomedical images + text |
|---|---|
| Base model | PubMedBERT + ViT-B/16 (CLIP) |
| Parameters | — |
| Interface | — |
Specs come from each project's README, paper or official page · BiomedCLIP site · BiomedCLIP paper. “—” means we couldn't verify it.
Compare with…
Pick 1–3 other Clinical & biomedical LLMs tools to compare side by side with BiomedCLIP.
Related
Open medical LLMs (7B/70B) adapted from Llama 2 on curated medical corpora.
Clinical & biomedical LLMsOpen source#llm#medical
Google's open Gemma 3 variants for medical text and image comprehension.
Clinical & biomedical LLMsOpen source#llm#multimodal
Biomedical vision-language assistant trained on PubMed Central figure-caption data.
Clinical & biomedical LLMsOpen source (non-commercial)#vlm#medical-imaging