Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Hate speech classification on HateXplain (test)
Loading...
72
Macro-F1
Llama_Full
27.28
38.89
50.5
62.11
Sep 18, 2025
Macro-F1
F1 Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Macro-F1
F1 Score
Llama_Full
Training Paradigm=Full...
2025.09
72
100
T5_Full
Training Paradigm=Full...
2025.09
72
100
ModernBERT
Training Paradigm=Full...
2025.09
70
97
SMARTER (Llama_DPO-256)
Training Paradigm=DPO,...
2025.09
64
89
SMARTER (T5_DPO-256)
Training Paradigm=DPO,...
2025.09
62
86
GPT-5-chat
Training Paradigm=16-s...
2025.09
62
86
GPT-5-chat
Training Paradigm=Zero...
2025.09
56
78
GPT-4.1
Training Paradigm=Zero...
2025.09
55
76
Qwen-32B
Training Paradigm=16-s...
2025.09
55
76
Qwen-32B
Training Paradigm=Zero...
2025.09
54
75
GPT-4.1
Training Paradigm=16-s...
2025.09
52
72
GPT-4o-mini
Training Paradigm=Zero...
2025.09
50
69
GPT-4o-mini
Training Paradigm=16-s...
2025.09
29
40
Feedback
Search any
task
Search any
task