Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Audit-relevance Classification on recent_week n=894 (drift)
Loading...
76.8
Accuracy
Pipeline current
74.512
75.106
75.7
76.294
Jun 9, 2026
Accuracy
Rejection F1 Score
LLM Calls
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Rejection F1 Score
LLM Calls
Pipeline current
Type=Production pipeline
2026.06
76.8
43
0
Always-approve (degenerate)
Type=Degenerate reference
2026.06
74.6
0
0
Feedback
Search any
task
Search any
task
