MedicalBenchmark

The definitive benchmark for evaluating Artificial Intelligence in medicine

About Us

MedicalBenchmark is an independent platform that evaluates and compares the performance of AI models on official Spanish medical exams, providing objective data for healthcare professionals and researchers.

Our Mission

To provide a rigorous, transparent, and independent evaluation of Artificial Intelligence model performance in the medical field, using official MIR exams as a standardized reference.

Evaluate AI models with scientific methodology
Offer objective and comparable data
Facilitate informed decision-making
Promote transparency in medical AI

Rigorous Methodology

Our evaluation is based on official MIR exams, ensuring a standard recognized and validated by the Spanish medical community.

Official MIR exams (2024-2026)
Zero-shot evaluation without prior training
Standardized and reproducible metrics
Continuous updates with new models
View full methodology

Contact

For inquiries, suggestions, or collaborations, feel free to contact us.