SISS Cross Scale - SISS Round1: leaderboard

SISS measures changes in hidden-text recovery between native and aggressively downsampled images. That cross-scale shift is distinct from a web agent taking an attacker-directed action. Main, web-agent and defense experiments use separate protocols; conditional remaining attack success uses the publisher’s paired counts. This board reports cross-scale semantic shift success rate (%). Lower is better.

Metric: Cross-scale semantic shift success rate (%). Source: arxiv.org. Saturation forecast: Around May 2027. 4 models tracked. Updated 14 Nov 2026.

Top models

#ModelScoreOverall rank
1Gemini 3 Flash49#163
2Claude Sonnet 4.651.33#165
3GPT-4o54.67#744
4Qwen 3.5 Plus (02-15)60.33#367

No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.

Interactive version: theaggregate.ai/benchmark?slug=siss-cross-scale-siss-round1 · How It Works · Data refreshed daily, snapshot 2026-11-16.