Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Privacy Verification on Email Leakage
Loading...
69
RDR
Beaver
12.84
27.42
42
56.58
Dec 5, 2025
RDR
Count (N)
Updated 1mo ago
Evaluation Results
Method
Method
Links
RDR
Count (N)
Beaver
Model=Llama3.3-70B
2025.12
69
99.07
Beaver
Model=Qwen2.5-14B
2025.12
68
100
Beaver
Model=Qwen3-4B
2025.12
67
77.83
Beaver
Model=Qwen3-30B-A3B
2025.12
66
73.58
RS
Model=Qwen2.5-14B
2025.12
20
100
RS
Model=Llama3.3-70B
2025.12
18
100
RS
Model=Qwen3-30B-A3B
2025.12
16
100
RS
Model=Qwen3-4B
2025.12
15
100
Feedback
Search any
task
Search any
task
