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

Medical Multiple-Choice Question Answering on m23k 750 samples (test)

57.3Average Score

Ours

53.45254.45155.4556.449Jun 25, 2026
Updated 29d ago

Evaluation Results

MethodLinks
2026.06
57.358.170.975.762.749.564.960.453.716.361.1
2026.06
55.356.769.674.962.145.959.157.548.716.461.8
2026.06
55.257.467.276.362.44662.154.549.515.761.2
2026.06
55.157.369.27661.848.26354.248.114.659.1
2026.06
5557.66775.762.847.162.356.748.21558.1
2026.06
53.656.765.775.359.84559.852.546.914.759.7