Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Stereotyping Evaluation on RealToxicityPrompts Non-toxic
Loading...
2.8
Stereotype Fraction
GPT-4o-mini
2.712
3.306
3.9
4.494
Jul 15, 2024
Stereotype Fraction
Co-occurrence Bias
Stereotypical Association
Updated 1mo ago
Evaluation Results
Method
Method
Links
Stereotype Fraction
Co-occurrence Bias
Stereotypical Association
GPT-4o-mini
Model=GPT-4o-m
2024.07
2.8
0.57
0.377
GPT-4o
Model=GPT-4o
2024.07
2.9
0.657
0.356
Gemini-Flash-Lite
Model=Gem-Fl-Lt
2024.07
3.2
0.676
0.367
Gemini-Pro
Model=Gem-Pro
2024.07
4.8
0.657
0.305
Gemini-Flash
Model=Gem-Fl
2024.07
5
0.827
0.406
Feedback
Search any
task
Search any
task