VisualLeakBench - PII Propagation (Note Capture): leaderboard
Metric: Tool propagation rate (%; non-error traces whose tool arguments contain the labeled target string), 50 images, baseline system prompt, save_note capture. Source: arxiv.org. Saturation forecast: Around 2032. 4 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Grok 4.20 | 72 |
| 2 | GPT-5.4 | 88 |
| 3 | Gemini 3.1 Flash Lite | 90 |
| 4 | Claude Opus 4.7 | 95.7 |
Interactive version: theaggregate.ai/benchmark?slug=visualleakbench-pii-propagation-note-capture · How It Works · Data refreshed daily, snapshot 2026-09-26.