Dies ist eine Übersichtsseite mit Metadaten zu dieser wissenschaftlichen Arbeit. Der vollständige Artikel ist beim Verlag verfügbar.
Assessing accuracy and legitimacy of multimodal large language models on Japan Diagnostic Radiology Board Examination
4
Zitationen
10
Autoren
2025
Jahr
Abstract
Recent multimodal LLMs, particularly o3 and Gemini 2.5 Pro, have demonstrated remarkable progress on JDRBE questions, reflecting their rapid evolution in diagnostic radiology. Eight multimodal large language models were evaluated on the Japan Diagnostic Radiology Board Examination. OpenAI's o3 and Google DeepMind's Gemini 2.5 Pro achieved high accuracy rates (72% and 70%) and received good legitimacy scores from human raters, demonstrating steady progress.
Ähnliche Arbeiten
Refinement and reassessment of the SERVQUAL scale.
1991 · 3.966 Zit.
Features and uses of high-fidelity medical simulations that lead to effective learning: a BEME systematic review
2005 · 3.757 Zit.
Radiobiology for the Radiologist.
1974 · 3.501 Zit.
International evidence-based recommendations for point-of-care lung ultrasound
2012 · 2.808 Zit.
Radiation Dose Associated With Common Computed Tomography Examinations and the Associated Lifetime Attributable Risk of Cancer
2009 · 2.428 Zit.