Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Red-teaming on AdvBench current (full)
Loading...
87.3
ASR (%)
OTTER-MLM
-2.764
20.618
44
67.382
Jun 19, 2026
ASR (%)
ASR 95% CI Lower Bound
Updated 1mo ago
Evaluation Results
Method
Method
Links
ASR (%)
ASR 95% CI Lower Bound
OTTER-MLM
Model=GPT-3.5-turbo
2026.06
87.3
84.2
OTTER-RV
Model=avg.
2026.06
84
-
GPT-4o paraphrase
Model=avg.
2026.06
77
-
OTTER-MLM
Model=Avg.
2026.06
75.6
-
OTTER-MLM
Model=GPT-4o-mini
2026.06
74.2
70.2
OTTER-MLM
Model=GPT-4-turbo
2026.06
71.3
67
OTTER-MLM
Model=GPT-4o
2026.06
69.8
65.9
Direct prompt
Model=GPT-3.5-turbo
2026.06
13.1
10.3
Direct prompt
Model=GPT-4o-mini
2026.06
7.4
5
Direct prompt
Model=Avg.
2026.06
7
-
Direct prompt
Model=GPT-4o
2026.06
6.6
4.4
Direct prompt
Model=GPT-4-turbo
2026.06
0.7
0
Feedback
Search any
task
Search any
task