LLM Jailbreaking
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
0.707Hypervolume
21
Mar 23, 2026
0.691Hypervolume
21
Mar 23, 2026
59.1Hypervolume
21
Mar 23, 2026
0.696Hypervolume
21
Mar 23, 2026
77Hypervolume
21
Mar 23, 2026
0.708Hypervolume
21
Mar 23, 2026
93.75ASR-M
16
Apr 29, 2026
88.27ASR-M
16
Apr 29, 2026
1SRF
14
May 21, 2026
46.4Jailbreak Success Rate
8
Mar 4, 2026
61Success Rate First (SRF)
6
May 21, 2026
31SRF
6
May 21, 2026
70Success Rate First (SRF)
6
May 21, 2026
32Success Rate First (SRF)
6
May 21, 2026
71Success Rate First (SRF)
6
May 21, 2026
71Success Rate First (SRF)
6
May 21, 2026
58SRF
6
May 21, 2026
46SRF (Mistral-SU)
6
May 21, 2026
1SRF
6
May 21, 2026
71SRF
6
May 21, 2026
77Success Rate First (SRF)
6
May 21, 2026
98.9ASR
5
Mar 17, 2026
95.4ASR
5
Mar 17, 2026
97.3Attack Success Rate (ASR)
5
Mar 17, 2026
72Success Rate First (SRF)
4
May 21, 2026