Understand this story
The UK AI Security Institute evaluated the multi-step attack capabilities of frontier AI agents on a self-built cyber range, assessing seven models released between August 2024 and February 2026. The institute said that under a fixed token budget, each generation of models outperformed the previous one: in a 32-step enterprise network attack range, with a 10M token budget, the average number of completed steps rose from 1.7 steps for GPT-4o to 9.8 steps for Opus 4.6. Increasing inference compute from 10M to 100M tokens brought gains of up to 59% with no plateau observed; at current prices, a single 100M token attempt with Opus 4.6 costs about 80 USD. In a 7-step industrial control system range, model progress was limited: at 10M tokens most models completed zero steps, and at 100M tokens Opus 4.6 averaged 1.4 steps.
AI-generated from public reports
Latest development · Report
UK AISI evaluates frontier AI agents' performance in multi-step cyberattack scenariosDevelopments
1 confirmed developments
UK AISI evaluates frontier AI agents in a simulated cyber range
Source:English text is being prepared.
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Oct 23
UK AI Security Institute: BlogFirst-partySelected
UK AISI evaluates frontier AI agents' performance in multi-step cyberattack scenarios
The UK AI Security Institute evaluated seven models released between August 2024 and February 2026 on a self-built cyber range, finding that each generation of models outperformed the previous one under a fixed token budget: in a 32-step enterprise cyberattack range, the average number of completed steps under a 10M token budget rose from 1.7 steps for GPT-4o to 9.8 steps for Opus 4.6. Raising inference compute from 10M to 100M tokens yielded gains of up to 59% with no plateau observed, and at current prices a single 100M token attempt with Opus 4.6 costs about 80 USD. In a 7-step industrial control system range, model progress was limited: under 10M tokens most models completed zero steps, and under 100M tokens Opus 4.6 averaged 1.4 steps.