Medical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
60.8Accuracy
7
Jun 26, 2026
55.5Accuracy
7
Jun 26, 2026
61.5Accuracy
7
Jun 26, 2026
63.3Accuracy
7
Jun 26, 2026
51.8Accuracy
7
Jun 26, 2026
68.3Accuracy
7
Apr 13, 2026
67Accuracy
7
Apr 13, 2026
64.4Accuracy
7
Apr 13, 2026
86.6Accuracy
7
Apr 13, 2026
66.2Accuracy
7
Apr 13, 2026
63.6Accuracy
7
Apr 13, 2026
80.8Accuracy
7
Apr 13, 2026
53.9Accuracy
7
Feb 26, 2026
62.3Accuracy
7
Feb 26, 2026
20.8Accuracy
7
Feb 26, 2026
74.3Perception Presence
6
Jun 11, 2026
16.4Best-of-16 Delta (Δ)
6
Apr 24, 2026
0.76ROUGE Score
5
Apr 1, 2026
0.71ROUGE
5
Apr 1, 2026
64ROUGE
5
Apr 1, 2026
71ROUGE
5
Apr 1, 2026
67ROUGE
5
Apr 1, 2026
64ROUGE Score
5
Apr 1, 2026
90.8Quality
4
Jun 26, 2026
55.91Accuracy
4
Jun 11, 2026