PreScam — leaderboard
Metric: AHit (self-reported). Source: benchmarklist.com. 5 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.5 | 79.36 |
| 2 | DeepSeek V3.2 | 75.8 |
| 3 | Llama 3.3 70B Instruct | 74.8 |
| 4 | GPT-5 Chat | 71.84 |
| 5 | GPT-4o Mini | 65.15 |
Interactive version: theaggregate.ai/benchmark?slug=prescam · How the rankings work · Data refreshed daily, snapshot 2026-07-22.