Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
LLM behavior monitoring on SHADE-Arena (test)
Loading...
75.2
Accuracy
Agent-ToM (external memory, Stage 1–2)
61.992
65.421
68.85
72.279
May 22, 2026
Accuracy
F1 Score
Recall
Precision
Updated 9d ago
Evaluation Results
Method
Method
Links
Accuracy
F1 Score
Recall
Precision
Agent-ToM (external memory, Stage 1–2)
Learning Strategy=exte...
2026.05
75.2
78.2
74.8
81.8
Sequential Ensemble
Monitoring Architectur...
2026.05
72.5
72.7
61.8
88.4
Agent-ToM (external memory, Stage 1)
Learning Strategy=exte...
2026.05
69.3
71.7
65.5
79.2
Agent-ToM (Prompt-level learning)
Learning Strategy=Prom...
2026.05
69
68.6
57
85.9
Agent-Auditor (nearest neighbor retrieval)
Evaluation Protocol=ne...
2026.05
66.3
69.7
65.3
74.8
ToM (zeroshot)
Evaluation Protocol=ze...
2026.05
65.9
61.5
45.7
93.7
LLM-Judge (zeroshot)
Evaluation Protocol=ze...
2026.05
63.5
59.6
45.4
86.9
Async Ensemble (Majority Vote)
Monitoring Architectur...
2026.05
62.5
76.1
99
61.7
Feedback
Search any
task
Search any
task