Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Self-harm Classification on SHINES
Loading...
88
F1 Score
Llama-3.1-8B-Instruct
71.36
75.68
80
84.32
Jun 5, 2025
F1 Score
Updated 4d ago
Evaluation Results
Method
Method
Links
F1 Score
Llama-3.1-8B-Instruct
Protocol=Multitask Fin...
2025.06
88
Mental-Alpaca-7B
Protocol=Multitask Fin...
2025.06
86
Llama-3.1-8B-Instruct
Protocol=Fine-tuning,...
2025.06
86
MentaLLaMA-chat-7B
Protocol=Multitask Fin...
2025.06
85
Llama-3.1-8B-Instruct
Protocol=Multitask Fin...
2025.06
84
Llama-3.1-8B-Instruct
Protocol=Fine-tuning
2025.06
83
Mental-Alpaca-7B
Protocol=Multitask Fin...
2025.06
83
Mental-Alpaca-7B
Protocol=Fine-tuning,...
2025.06
83
Mental-Alpaca-7B
Protocol=Fine-tuning
2025.06
82
MentaLLaMA-chat-7B
Protocol=Multitask Fin...
2025.06
82
MentaLLaMA-chat-7B
Protocol=Fine-tuning,...
2025.06
82
MentaLLaMA-chat-7B
Protocol=Fine-tuning
2025.06
81
Mental-Alpaca-7B
Protocol=Few-shot Prom...
2025.06
80
Llama-3.1-8B-Instruct
Protocol=Few-shot Prom...
2025.06
79
MentaLLaMA-chat-7B
Protocol=Few-shot Prom...
2025.06
78
Mental-Alpaca-7B
Protocol=Zero-shot Pro...
2025.06
76
Llama-3.1-8B-Instruct
Protocol=Zero-shot Pro...
2025.06
74
MentaLLaMA-chat-7B
Protocol=Zero-shot Pro...
2025.06
72
Feedback
Search any
task
Search any
task