Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Agent Safety Evaluation on Agent-SafetyBench
Loading...
72.3
Agent-SafetyBench Score
gpt-4o + GBT-SE
18.012
32.106
46.2
60.294
Jan 30, 2026
Agent-SafetyBench Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Agent-SafetyBench Score
gpt-4o + GBT-SE
Base Model=gpt-4o, Saf...
2026.01
72.3
llama-3-8b + GBT-SE
Base Model=llama-3-8b,...
2026.01
70.8
gpt-4o + GBT-Basic
Base Model=gpt-4o, Saf...
2026.01
60.2
gpt-4o + Global guardrail only
Base Model=gpt-4o, Saf...
2026.01
56.8
llama-3-8b + GBT-Basic
Base Model=llama-3-8b,...
2026.01
55.4
llama-3-8b + Global guardrail only
Base Model=llama-3-8b,...
2026.01
50.4
gpt-4o (native)
Base Model=gpt-4o, Saf...
2026.01
44.2
llama-3-8b (native)
Base Model=llama-3-8b,...
2026.01
20.1
Feedback
Search any
task
Search any
task