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

Medical Question Answering on MedQA 4-option original (test)

95.1Accuracy

Gemini 3 Pro

48.92460.91272.984.888Jul 7, 2025Aug 21, 2025Oct 6, 2025Nov 20, 2025Jan 5, 2026Feb 19, 2026Apr 6, 2026
Updated 11d ago

Evaluation Results

MethodLinks
2026.04
95.1
2026.04
94.3
2025.07
93.3
2025.07
92.6
2025.07
92
2025.07
90.1
2025.07
87.7
2025.07
86.5
2026.04
85.3
2025.07
78.2
2026.04
76.8
2025.07
74.9
2025.07
73.3
2026.04
69.1
2025.07
64.4
2026.04
64.4
2025.07
61.4
2025.07
59
2025.07
51.1
2025.07
50.7