Medical Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
4.4ECE
9
Feb 26, 2026
4.6ECE
9
Feb 26, 2026
4.3ECE
9
Feb 26, 2026
4.8ECE
9
Feb 26, 2026
4.8ECE
9
Feb 26, 2026
4.3ECE
9
Feb 26, 2026
5.1ECE
9
Feb 26, 2026
78.69CMB Accuracy
8
Jun 30, 2026
82.72Accuracy
8
Jun 16, 2026
0.807Accuracy
8
Jun 15, 2026
22F1 Score
8
May 26, 2026
21.94UCCR
8
May 22, 2026
20.7UCCR
8
May 22, 2026
87Cumulative Score (CS)
8
Mar 10, 2026
53.9Accuracy
8
Feb 26, 2026
27.66Accuracy
8
Feb 26, 2026
83.95Accuracy
8
Feb 26, 2026
28.55ROUGE-1
8
Feb 26, 2026
19.83ROUGE-1
8
Feb 26, 2026
90.2Accuracy
8
Feb 26, 2026
62.7Score
7
May 26, 2026
54.6Accuracy (OOD Text-only)
7
Apr 8, 2026
64.89Task Performance
7
Feb 26, 2026
75.1Accuracy
7
Feb 26, 2026
75.1Accuracy
7
Feb 26, 2026