Persuasion Detection on Post-cutoff datasets (test)
80.8F1 ScoreGPT 4o mini
Evaluation results
| Method | Links | |
|---|---|---|
| GPT 4o miniCondition=Averaged over 3 base methods2025.06 | 80.8 | |
| Llama 3.3 70BCondition=Averaged over 3 base methods2025.06 | 75.2 | |
| Gemini 1.5 FlashCondition=Averaged over 3 base methods2025.06 | 71.9 | |
| Claude 3 HaikuCondition=Averaged over 3 base methods2025.06 | 67.7 | |
| Llama 3.1 8BCondition=Averaged over 3 base methods2025.06 | 64.9 | |
| BERTCondition=Averaged over 3 base methods2025.06 | 48.5 |