Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Agent Security Evaluation on ASB (Agent Security Benchmark)
Loading...
7
ASR-d (ASB)
gpt-4o + GBT-SE
4.704
20.202
35.7
51.198
Jan 30, 2026
ASR-d (ASB)
Response Rate (RR) (ASB)
PNA-d (ASB)
Updated 1mo ago
Evaluation Results
Method
Method
Links
ASR-d (ASB)
Response Rate (RR) (ASB)
PNA-d (ASB)
gpt-4o + GBT-SE
Base Model=gpt-4o, Saf...
2026.01
7
78.4
70.4
llama-3-8b + GBT-SE
Base Model=llama-3-8b,...
2026.01
7.4
77
51.8
gpt-4o + GBT-Basic
Base Model=gpt-4o, Saf...
2026.01
8.6
73.8
70.1
llama-3-8b + GBT-Basic
Base Model=llama-3-8b,...
2026.01
8.7
72.2
51.6
llama-3-8b + Global guardrail only
Base Model=llama-3-8b,...
2026.01
10.9
61.6
50.8
gpt-4o + Global guardrail only
Base Model=gpt-4o, Saf...
2026.01
13.1
63.2
69
llama-3-8b (native)
Base Model=llama-3-8b,...
2026.01
20.4
4.9
52
gpt-4o (native)
Base Model=gpt-4o, Saf...
2026.01
64.4
8.8
71.3
Feedback
Search any
task
Search any
task