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

Medical Question Answering on MedQA (M-QA)

0.12Base Accuracy Std Dev

SAG (w/ CTDE)

0.010.75251.4952.2375Feb 8, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
0.120.240.190.36
2026.02
0.150.20.190.35
2026.02
0.330.680.560.78
2026.02
0.410.640.520.74
2026.02
0.811.161.041.38
2026.02
0.921.241.131.41
2026.02
1.821.952.142.45
2026.02
2.122.342.562.8
2026.02
2.283.072.733.31
2026.02
2.423.162.843.51
2026.02
2.452.682.923.15
2026.02
2.622.911.784.12
2026.02
2.873.843.414.16