sb-ai-lab/MedBench

https://arxiv.org/abs/2201.06499

38
/ 100
Emerging

This project helps medical professionals, researchers, and data scientists evaluate how well AI models understand Russian medical texts and ECG signals. It takes raw medical text (like patient symptoms or complaints) and ECG data, then measures how accurately an AI can predict diagnoses, recommend symptoms, answer medical questions, identify key medical terms, or classify ECG pathologies. This is for anyone who needs to assess or improve AI systems working with Russian medical information.

Use this if you need to benchmark the performance of Natural Language Processing (NLP) models or machine learning models on specific medical tasks using Russian language data or ECG signals.

Not ideal if you are looking for a ready-to-use AI application for direct patient care or clinical decision support, as this is a benchmark for evaluating models.

medical-nlp clinical-diagnosis medical-research healthcare-ai biomedical-text-mining
No Package No Dependents
Maintenance 10 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 7 / 25

How are scores calculated?

Stars

11

Forks

1

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Feb 02, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/sb-ai-lab/MedBench"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.