Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Agent Authority Compliance and Proximity Monitoring on PAVE Environment Scenario 2: Fire + Officer
Loading...
94
Authority Compliance Rate (OCR)
PAVE
70.08
76.29
82.5
88.71
May 19, 2026
Authority Compliance Rate (OCR)
Proximity Violation Rate (Near)
Proximity Violation Rate (Far)
Updated 14d ago
Evaluation Results
Method
Method
Links
Authority Compliance Rate (OCR)
Proximity Violation Rate (Near)
Proximity Violation Rate (Far)
PAVE
Backbone=GPT-4o
2026.05
94
5
65
PAVE
Backbone=Claude-3.5 So...
2026.05
91
7
62
PAVE
Backbone=Llama-3-70B
2026.05
86
10
59
PAVE
Backbone=GPT-4o-mini
2026.05
71
18
51
Feedback
Search any
task
Search any
task
