Medical Safety Evaluation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
1Safety Score (1-ASR)
8
Feb 26, 2026
0.785Safety Score (1-ASR)
8
Feb 26, 2026
100Safety Score (1-ASR)
8
Feb 26, 2026
100Safety Score (1-ASR)
8
Feb 26, 2026
100Safety Score
8
Feb 26, 2026
0.998Safety Score (1-ASR)
8
Feb 26, 2026
100Safety Score
8
Feb 26, 2026
0.552Kendall's tau_b
3
Apr 7, 2026
—
—Primary metric
0
May 28, 2026
—
—Primary metric
0
May 28, 2026