About Grand Rounds AI

Mission

Grand Rounds AI serves as the authoritative, aggregated leaderboard of medical AI model performance across published benchmarks. We aim to bring clarity to the rapidly evolving landscape of healthcare AI by providing researchers, developers, and healthcare professionals with a single source of truth for model capabilities.

Methodology

We aggregate publicly reported benchmark results from academic publications, official model cards, and verified sources. Each score entry includes its source, evaluation methodology, and any relevant caveats to ensure transparency and reproducibility.

Attribution

Grand Rounds AI does not own, operate, or maintain the benchmarks displayed on this platform, nor do we host or distribute the evaluated models. All benchmark scores are attributed to their original sources. For authoritative information about specific benchmarks or models, please refer to the original sources linked on each page.

Submit a Score

Have a published benchmark result that should be included? We welcome submissions from researchers and model developers. Please ensure you have a citable source for any scores submitted.

Submission form coming soon.

Contact

For corrections, questions, or feedback, please reach out to the Grand Rounds AI team.