Gray Swan IPI — Combined Attack Set A

AI benchmark · Safety

Publisher
Google Gemini 3 8 Flash Launch
Domains
Safety Cybersecurity
Tier
A why
Snapshot

Full listing name: Gray Swan IPI — Combined Attack Set, Transfer Only, No Computer Use

What is Gray Swan IPI — Combined Attack Set?

Indirect prompt-injection robustness evaluation using Gray Swan's combined attack set in transfer-only mode without computer use. It reports attack success rate after 15 attempts; lower is better.

Tier A

A

Widely used: a lab reports it, or 50 or more models are scored on it.

How much stands behind a tier: usage, who backs it, a confirmed line from its own site or paper, and a clear read on X. High with three of the four, medium with two, low otherwise.

  • 19 models scored
  • reported by Google
  • in curated RL directories (1 pt)
How we got to tier A
  1. Adoption: 19 models scored; reported by Google. Tier A.
  2. On X: unclear, none buzz No move.
  3. In curated RL directories: 1 point, a floor of none.
  4. Not yet confirmed by a line from its own site or paper.

A clear view on X moves a tier one step up or down; most entries don't move. How tiers work.

Not on the map yet: no line from its own site or paper places it in a domain.

More Safety AI benchmarks

Next: browse all benchmarks. Entry from the RL Research daily scrape of public sources, 2026-10-11 snapshot.