Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
DeFi supervision ticket quality evaluation on DeXposure-Bench (Frozen 2025)
Loading...
72
Precision
persist.+rules
56.4
60.45
64.5
68.55
Jun 17, 2026
Precision
Recall
F1 Score
FIR
Stability
Judge Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Precision
Recall
F1 Score
FIR
Stability
Judge Score
persist.+rules
Stack=persist.+rules,...
2026.06
72
0.4
0.76
-
51.4
-
FM+rules
Stack=FM+rules, Interv...
2026.06
60
1
1.9
-
25.7
-
FM+LLM+gate
Stack=FM+LLM+gate, Int...
2026.06
58
1.2
2.34
43.7
43.5
2.45
snapshot LLM
Stack=snapshot LLM, In...
2026.06
57.5
0.9
1.84
-
53.2
2.24
FM+LLM
Stack=FM+LLM, Interv.(...
2026.06
57
1.2
2.41
44.8
48.8
2.41
Feedback
Search any
task
Search any
task