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

Question Answering on PubMedQA PQA-L (test)

78.2Accuracy

BioGPT

54.2860.4966.772.91Oct 19, 2022May 16, 2023Dec 11, 2023Jul 7, 2024Feb 1, 2025Aug 29, 2025Mar 27, 2026
Updated 20d ago

Evaluation Results

MethodLinks
2022.10
78.2
2024.03
76.8
2026.03
76.6
2026.03
76.4
2024.03
76.3
2026.03
75.8
2024.03
75.5
2024.03
75.4
2024.03
75.2
2024.03
75.1
2026.03
74.6
2024.03
74.4
2024.03
74.2
2024.03
74.2
2026.03
74.2
2026.03
74.2
2024.03
73.8
2024.03
73.6
2024.03
73.4
2024.03
73.4
2024.03
73.4
2026.03
73.2
2024.03
72.4
2026.03
72.4
2026.03
72.4
2022.10
72.2
2024.03
72.2
2026.03
71.8
2024.03
71.6
2026.03
71.4
2022.10
70.2
2024.03
70.2
2026.03
68.8
2026.03
68.2
2026.03
66.8
2026.03
64.4
2022.10
64.2
2024.03
64.2
2026.03
62
2026.03
56.2
2022.10
55.8
2024.03
55.8
2026.03
55.2