Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Phishing URL Detection on HP random balanced 1,000 URLs
Loading...
99
F1 Score
URLTran
78.876
84.1005
89.325
94.5495
Jan 28, 2026
F1 Score
Updated 4d ago
Evaluation Results
Method
Method
Links
F1 Score
URLTran
Description=BERT-based...
2026.01
99
Least-to-Most prompting framework
LLM Backbone=Gemini 2....
2026.01
96.58
One-shot classifier
LLM Backbone=Gemini 2....
2026.01
96.12
Least-to-Most prompting framework
LLM Backbone=GPT-4.1
2026.01
95.02
One-shot classifier
LLM Backbone=GPT-4.1
2026.01
94.88
Least-to-Most prompting framework
LLM Backbone=Gemma 3:12b
2026.01
88.72
Least-to-Most prompting framework
LLM Backbone=Llama 3.1:8b
2026.01
87.63
One-shot classifier
LLM Backbone=Gemma 3:12b
2026.01
85.34
One-shot classifier
LLM Backbone=Llama 3.1:8b
2026.01
79.65
Feedback
Search any
task
Search any
task