Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Dataset Diversity and Coverage Evaluation on AgentHazard full
Loading...
0.93
Goal-text Entropy
AgentHazard (full)
0.8835
0.90675
0.93
0.95325
May 27, 2026
Goal-text Entropy
CLIP Pairwise Distance (per-base)
Action Coverage
Updated 6d ago
Evaluation Results
Method
Method
Links
Goal-text Entropy
CLIP Pairwise Distance (per-base)
Action Coverage
AgentHazard (full)
n=2,520
2026.05
0.93
0.563
3
Feedback
Search any
task
Search any
task
