uni-medical/GMAI-MMBench

GMAI-MMBench: A Comprehensive Multimodal Evaluation Benchmark Towards General Medical AI.

29
/ 100
Experimental

This project provides a comprehensive benchmark for evaluating the performance of multimodal AI models in a medical context. It takes various medical images and clinical data as input and assesses how accurately AI models can answer questions related to diagnoses, prognoses, and treatments. Healthcare AI researchers and developers can use this to rigorously test and compare their AI systems.

No commits in the last 6 months.

Use this if you are developing or researching medical AI models and need a standardized, comprehensive way to evaluate their ability to interpret diverse medical images and answer clinical questions.

Not ideal if you are an end-user clinician seeking a ready-to-use diagnostic tool, as this is a benchmark for evaluating AI models, not a clinical application.

medical-imaging clinical-diagnosis-support healthcare-AI-evaluation multimodal-AI diagnostic-accuracy
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 4 / 25

How are scores calculated?

Stars

82

Forks

2

Language

License

Apache-2.0

Last pushed

Dec 17, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/uni-medical/GMAI-MMBench"

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