Medical Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
79.36BERTScore Precision
7
Feb 26, 2026
72Accuracy
7
Feb 26, 2026
0.98Macro Delta
6
Jul 1, 2026
61.8Accuracy
6
Jun 26, 2026
55.8Accuracy
6
Jun 26, 2026
63.5Accuracy
6
Jun 26, 2026
49.6Accuracy
6
Jun 26, 2026
65.3Accuracy
6
Jun 26, 2026
40.25Score
6
Apr 1, 2026
83.3Acc/EM
6
Feb 26, 2026
0.645AUROC
6
Feb 26, 2026
100Diversity & Integrity Win Rate
6
Feb 26, 2026
4.364Prometheus 2 Score
5
Jul 3, 2026
61.5Accuracy
5
Jun 11, 2026
56.95Accuracy
5
Jun 4, 2026
1,395Length
5
Mar 18, 2026
0.671Average Score
5
Feb 26, 2026
68.1Accuracy (IT)
5
Feb 26, 2026
91.1MedQuAD Score
5
Feb 26, 2026
81Accuracy
4
Jul 7, 2026
57.5MCQ Accuracy
4
Jun 23, 2026
77.6Accuracy
4
Jun 16, 2026
79.8Accuracy (Letter Match)
4
May 12, 2026
92.8Accuracy
4
Apr 15, 2026
12.2CUS Score
4
Apr 1, 2026