Medical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
86Accuracy
72
Jun 30, 2026
92.8Accuracy
61
Jun 30, 2026
74.6Accuracy
56
Mar 24, 2026
79.23Accuracy
48
Jul 7, 2026
40.74Accuracy
41
Jun 9, 2026
75.2MedQA Score
40
Apr 27, 2026
81.44Accuracy
38
Jun 9, 2026
83.37Accuracy (DDXPlus)
36
May 18, 2026
70.41Accuracy
36
May 19, 2026
98.37Accuracy
30
May 15, 2026
85.33Accuracy
30
May 15, 2026
83.76Accuracy
30
May 15, 2026
72.5Accuracy
28
Apr 2, 2026
48.2Basic Accuracy
28
Mar 4, 2026
57.5Average Performance
25
Jun 26, 2026
48.2Basic Accuracy
22
Mar 4, 2026
42.33Recall
22
Feb 26, 2026
46.13Recall
22
Feb 26, 2026
42.9Accuracy
20
Jul 3, 2026
84.87Accuracy (MedBullets)
18
Apr 21, 2026
80.7Accuracy
18
Jun 26, 2026
54.22MedBullets Score
15
Mar 25, 2026
19.3Accuracy
14
Jun 26, 2026
80Symptoms Accuracy
13
Apr 14, 2026
80.8Accuracy
13
Apr 1, 2026