Diagnostic Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
66.2Reasoning Recall
10
Apr 28, 2026
72.14Final Accuracy
9
Apr 10, 2026
54.6CT Score
7
Jun 8, 2026
66.5Reasoning Recall
4
Apr 28, 2026
24.2Top-1 Accuracy
3
May 29, 2026