Skip to content
The Aggregate

Unified LLM rankings, daily

Models Task Explorer Subscriptions What's New Trends Benchmarks Builder Guesswork
How It Works Daily brief
The Aggregate
Loading data...

CyberSecEval-3 Cyberattack Compliance: leaderboard

Metric: Attack compliance (%). Source: arxiv.org. 6 models tracked.

Top models

#ModelScore
1Llama 3.1 405B38
2GPT-4 Turbo42
3Qwen 2 72B Instruct47
4Llama 3 70B78
5Mixtral 8x22B80
6Gemini 1.0 Pro92

Interactive version: theaggregate.ai/benchmark?slug=cyberseceval-3-cyberattack-compliance · How It Works · Data refreshed daily, snapshot 2026-10-09.

Built by Mikhail Doroshenko — AI researcher, co-author of Humanity’s Last Exam. Independent project; no affiliation with any AI lab.
A

Your Aggregate

Sign in to keep your work

Save custom rankings and get 50 free task analyses each day.

Continue with Google Continue with GitHub

No password to remember. Your public profile identifies saved work.

Your Aggregate

Account

  • Saved custom aggregate views
  • 50 free task analyses per day
Sign out