SecCodePLT - Attack Collection: leaderboard
Metric: Attack step success (%). Source: arxiv.org. Saturation forecast: Estimated already saturated. 3 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude 3.5 Sonnet | 92 |
| 2 | GPT-4o | 86 |
Interactive version: theaggregate.ai/benchmark?slug=seccodeplt-attack-collection · How It Works · Data refreshed daily, snapshot 2026-10-09.