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

Medical Question Answering on PubMedQA (Accuracy, F1, Avg. Accuracy)

82.8Accuracy

SafeLoRA

9.68828.66947.6566.631Mar 21, 2025May 29, 2025Aug 7, 2025Oct 16, 2025Dec 24, 2025Mar 4, 2026May 13, 2026
Updated 20d ago

Evaluation Results

MethodLinks
2025.03
82.8--
2026.04
81.8--
2026.04
81.6--
2025.03
80.3--
2025.03
80--
2025.03
79.6--
2025.03
79.5--
2025.03
79.2--
2026.04
79.2--
2025.03
79.1--
2025.03
79--
2025.03
78.8--
2025.03
78.8--
2025.03
78.5--
2025.03
78.5--
2026.03
78.476.881.4
2025.03
78.3--
2026.03
78.276.479.3
2026.04
78.2--
2026.04
77.7--
2025.03
77.6--
2025.03
77.4--
2026.04
77.4--
2026.04
77.3--
2026.04
77.2--
2026.04
77--
2026.03
76.875.180.3
2025.03
75.8--
2025.03
75.7--
2026.03
75.374.176.6
2026.04
74.9--
2026.04
74.7--
2025.03
74.4--
2025.03
74.2--
2026.03
73.872.174.1
2026.04
73.7--
2025.03
73.6--
2026.04
73.3--
2025.03
73.2--
2025.03
72.6--
2026.03
72.370.773.5
2025.03
72.2--
2026.03
72.170.673
2026.03
71.569.972.2
2025.03
71.4--
2025.03
71.2--
2026.03
70.769.272
2026.04
70.6--
2026.03
69.367.870.4
2026.04
67.4--
2025.03
64.5--
2025.03
57.1--
2025.03
55.2--
2026.05
45.5--
2026.05
38.5--
2026.05
35.8--
2026.05
32.8--
2026.05
32.5--
2026.05
31.3--
2026.05
30.8--
2026.05
30.3--
2026.05
28.5--
2026.05
28.2--
2026.05
26.2--
2026.05
12.5--