Stereotyping Evaluation on Counterfactual Open-Ended (OCF)
2.5Stereotype FractionGPT-4o-mini
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| GPT-4o-miniModel=GPT-4o-m2024.07 | 2.5 | 62 | 30.2 | |
| Gemini-ProModel=Gem-Pro2024.07 | 3.1 | 44.3 | 23.1 | |
| Gemini-FlashModel=Gem-Fl2024.07 | 4.3 | 38.9 | 25.5 | |
| Gemini-Flash-LiteModel=Gem-Fl-Lt2024.07 | 5.6 | 53.1 | 29.5 | |
| GPT-4oModel=GPT-4o2024.07 | 7.7 | 48.7 | 28.1 |