PreScam - Psychological Technique Prediction (Limited): leaderboard
Metric: PT HitRate (%): the share of gold psychological techniques of the future scammer actions recovered by the prediction, averaged over cases, for a zero-shot forecast of the scammer's remaining actions from the conversation prefix up to a boundary turn chosen per case, Limited setting (the model also receives the exact number of remaining scammer actions); GPT-4o-mini extracts structured labels from the predicted and gold actions; higher is better. Source: arxiv.org. Saturation forecast: Around 2030. 5 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 Chat | 50.91 |
| 2 | DeepSeek V3.2 | 49.67 |
| 3 | Llama 3.3 70B Instruct | 46.43 |
| 4 | GPT-4o Mini | 45.63 |
| 5 | Claude Sonnet 4.5 | 43.22 |
Interactive version: theaggregate.ai/benchmark?slug=prescam-psychological-technique-prediction-limited · How It Works · Data refreshed daily, snapshot 2026-10-07.