Medical Diagnosis
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
78.33Accuracy
54
Mar 4, 2026
18.34Rounds
25
Feb 26, 2026
9.11Rounds
25
Feb 26, 2026
2.058Mean Prediction Set Size
20
Jun 5, 2026
0.684Similarity (Sim)
20
May 11, 2026
70Accuracy
18
Jun 15, 2026
72Accuracy
18
Jun 15, 2026
66Accuracy
18
Jun 15, 2026
68Accuracy
18
Jun 15, 2026
24.21Robust Accuracy
18
Feb 26, 2026
69.49Baseline Accuracy
18
Feb 26, 2026
83F1 Score
16
Feb 26, 2026
53DL Score
13
Feb 26, 2026
55.31Strict DA
12
Jun 9, 2026
62.6Similarity Score
12
May 11, 2026
96.6Similarity
12
May 11, 2026
78Top-1 Accuracy
12
Apr 23, 2026
88.76Accuracy
12
Jun 4, 2026
78.3Accuracy
10
Mar 17, 2026
71.26Precision for Edema
10
Mar 4, 2026
82Diag. Acc.
9
May 11, 2026
81Diagnostic Accuracy
9
May 11, 2026
31.88Match (LLM-as-a-Judge)
9
Mar 24, 2026
74.67Average Outcome Reward
9
Mar 13, 2026
17.91Rounds
9
Feb 26, 2026