Medical Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
94.2Score
2
Jun 23, 2026
47Overall Score
2
Jun 23, 2026
10SC@10 Score
2
May 8, 2026
100Accuracy under Attack
2
Apr 28, 2026
0.36Log-likelihood Score
2
Apr 2, 2026
0.385Log-likelihood Score
2
Apr 2, 2026
67.05CUS Score
2
Apr 1, 2026
66CUS Score
2
Apr 1, 2026
31CUS
2
Apr 1, 2026
25.53Accuracy
2
Feb 26, 2026
73.7Accuracy (MedB-4)
2
Feb 26, 2026
70.15Accuracy
2
Feb 26, 2026
72.39Accuracy
2
Feb 26, 2026
53.07Accuracy
2
Feb 26, 2026
70.55Accuracy
2
Feb 26, 2026
89.3Query Intent Fulfillment
2
Feb 26, 2026
0.736Accuracy
1
Feb 26, 2026