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

Medical Question Answering on MedQA (test)

92Accuracy

DrugClaw

45.418457.511769.60581.6983Mar 13, 2026Mar 26, 2026Apr 8, 2026Apr 21, 2026May 4, 2026May 17, 2026May 31, 2026
Updated 1d ago

Evaluation Results

MethodLinks
2026.05
92--
2026.05
91.7--
2026.05
91--
2026.05
90.2--
90.2--
2026.05
89.8--
2026.05
88.4--
88--
2026.03
66.14--
2026.03
65.2--
2026.03
65.04--
2026.03
64.41--
2026.03
62.14--
2026.03
59.07--
2026.03
49.8--
2026.03
49.25--
2026.03
48.7--
2026.03
48.39--
2026.03
48--
2026.03
47.21--
2025.03
-1.660.84
2025.03
-2.462.57
2025.03
-2.572.94
2025.03
-1.850.89
2025.03
-3.132.76
2025.03
-3.263
2025.03
-1.420.5
2025.03
-2.242.06
2025.03
-2.352.36
2025.03
-1.30.51
2025.03
-2.242.47
2025.03
-2.352.75
2025.09
--0.893
2025.09
--0.901
2025.09
--0.899