Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Medical Question Answering on MedXpertQA OOD (test)

69.2Accuracy

Gemini-3-flash

20.42433.08745.7558.413Jul 7, 2025Aug 16, 2025Sep 26, 2025Nov 6, 2025Dec 17, 2025Jan 27, 2026Mar 9, 2026
Updated 11d ago

Evaluation Results

MethodLinks
2026.03
69.2
2025.07
67.5
2025.07
58.9
2026.03
54.4
2025.07
47.4
2026.03
46.6
2026.03
44.1
2026.03
40.4
2026.03
39.3
2026.03
36
2026.03
33.3
2025.07
29.8
2025.07
24.4
2026.03
23.9
2025.07
22.3