Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Dog whistle discovery on FETCH! (Synthetic scenario)
Loading...
20.31
Precision
DIRECT Pipeline
14.4028
15.9364
17.47
19.0036
Dec 16, 2024
Precision
Data Potential Recall
F0.5 Score
Updated 4d ago
Evaluation Results
Method
Method
Links
Precision
Data Potential Recall
F0.5 Score
DIRECT Pipeline
Model=LLaMa 13B
2024.12
20.31
56.3
23.29
DIRECT Pipeline
Model=Mistral 7B
2024.12
18.26
58.82
21.18
DIRECT Pipeline
Model=LLaMa 8B
2024.12
14.63
46.64
16.95
Feedback
Search any
task
Search any
task