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

Question Answering on PubMedQA (Acc, TNFT, Tokens, Delay)

73.6Accuracy

Vanilla

69.64870.67471.772.726May 12, 2026
Updated 21d ago

Evaluation Results

MethodLinks
2026.05
73.6404.671,420.1421.73
2026.05
73.50648.9613.8
2026.05
72.9389.61,323.7520.98
2026.05
70.50658.0110.96
2026.05
70.4404.671,422.9115.6
2026.05
69.8389.61,263.9114.2