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

Multiple-choice Question Answering on PubMedQA (Accuracy)

63.62Accuracy

DS2-INSTRUCT

12.97226.12139.2752.419Mar 13, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
63.62
2026.03
62.15
2026.03
61.47
2026.03
60.89
2026.03
60.34
2026.03
48.56
2026.03
39.11
2026.03
31.48
2026.03
28.35
2026.03
27.41
2026.03
26.83
2026.03
25.34
2026.03
24.92
2026.03
24.77
2026.03
14.92