Support

Settings

Theme

Explore themes

Mode

Library

Looks borrowed from benchmark sites and products. Themes with a light and a dark version follow your mode.

Bring your own theme

Upload a Priors theme file, or have your agent make one: copy the prompt, tell it the look you want, and upload what it returns. With the Priors skill installed it already knows the format.

Custom themes stay in this browser. They travel inside shared chart links and a page's theme, so others see them as you do.

For the builder, Explore and model pages on this device. Published pages keep the theme their owner picked.

Mode

Update notices

A note when a benchmark one of your indexes uses gets a new version, with a one-click upgrade.

Benchmarks · Safety & security · Agents & computer use

FrontierBreach

How easily an agent is hijacked during long enterprise tasks. Attacks hidden in the material it works with try to cause ransomware, data theft, phishing and similar harm. The share of test cases breached within five attempts, at medium effort. Lower is better.

22 models · 22 results · data as of 2026-11-18 · promptarmor.com ↗

Leaderboard

Gemini 4 Carbon medium

All results

22 rows
#ModelEffortFrontierBreach
1Gemini 4 Carbonmedium2.4% ±2.2
2Gemini 4 Argonmedium4.3% ±2.9
3GPT-6 Astramedium7.6% ±3.8
4Fable 5.2medium10.0% ±4.2
5Opus 5medium10.0% ±4.2
6Muse Wondermedium15.2% ±5.1
7Gemini 3.6 Flashmedium22.4% ±5.9
8Inkling 2 Smallmedium30.0% ±6.5
9Qwen 3.8 Maxmedium30.5% ±6.5
10Kimi K3medium31.4% ±6.6
11GPT-5.6 Solmedium33.3% ±6.7
12Grok 4.7medium33.3% ±6.7
13Qwen 3.7 Maxmedium36.2% ±6.8
14GLM 5.3medium37.1% ±6.8
15Muse Spark 1.1medium38.6% ±6.9
16GLM 5.2medium39.0% ±6.9
17Inklingmedium39.0% ±6.9
18DeepSeek V4 Flash 0731medium49.5% ±7.1
19Kimi K3.1medium50.0% ±7.1
20DeepSeek V4 Pro 0813medium51.4% ±7.1
21Beam 1.0medium72.9% ±6.3
22Grok 4.5medium91.4% ±4.0