Refusal
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
97.81Alignment Probability
55
Jun 9, 2026
0ASR
42
Apr 28, 2026
91R-Acc
21
Jun 2, 2026
93.04Score
21
Feb 26, 2026
64.3BAS (Baseline)
6
Jul 7, 2026
1Average Appearance Score
2
Jun 8, 2026
0.91Avg Appearance Score
2
Jun 8, 2026