Pattern Labs cyberoffensive challenges
Only in system cards
Agents attempt evasion, network attack simulation and vulnerability exploitation challenges at easy, medium and hard levels. Scored as success rate per type.
Third-party evaluation reported in OpenAI cards. Results are per challenge type with no overall number.
Made by Pattern Labs (now Irregular) Released Apr 2025 Capture-the-flag challenges Tasks kept private Last in a system card Aug 2025
Last model added Aug 2025
- Level
- Expert Specialists with years of training, often over hours of work
- Scored
- Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
- Answers
- Agent task Many steps in a terminal, browser, desktop, app, game or robot.
3
System cards report it, from 1 lab
No scores here yet
No lab, leaderboard or Epoch AI run has reported a score for Pattern Labs cyberoffensive challenges yet.
Labs report it only in system cards
We read the headline results of 479 launch posts from 51 labs, and none of them list this benchmark. Some system cards do, below.
3 system cards report it, from 1 lab
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| 7 Aug 2025 | GPT-5 system card | Pattern Labs challenges, average success rate Evasion 51%, Vulnerability Discovery and Exploitation 35%, Network Attack Simulation 49%, no overall score (5.1.2.3) | Cyber risk | |
| 16 Apr 2025 | o4-mini system card | Pattern Labs cyberoffensive challenges, success rates for evasion, network attack simulation and vulnerability discovery, no overall score (3.9.3) | Cyber risk | |
| 16 Apr 2025 | o3 system card | Pattern Labs cyberoffensive challenges, success rates for evasion, network attack simulation and vulnerability discovery, no overall score (3.9.3) | Cyber risk |
More in Cybersecurity
- ExploitGym In use 869 real-vulnerability exploit-development tasks (userspace, V8, Linux kernel). Success means capturing a flag through the intended vulnerability. GPT-6 Astra 42.4%
- ExploitBench In use 41 recent V8 JavaScript-engine N-day vulnerabilities. Progress measured by 16 grader-verified capability flags across five tiers. GPT-6 Astra 100%
- CWE-bench In use Agents audit a repository and write a patch for a security flaw, without being told where the bug is. Covers six programming languages.
Gemini 4 Carbon 71% - Real-world vulnerability discovery In use Agents search popular open-source codebases to rediscover about 1,200 recent confirmed vulnerabilities across many languages. Reports share discovered. Gemini 4 Argon 86%
- Artificial Analysis Cyber Index In use Agents do enterprise cyber defense tasks from three benchmarks, CWE-Bench-AA, DeepsecBench-AA and CyberGym-E2E-AA, combined into one success rate.
Mistral Large 4 (Le Chonk, open weights) 51% - Big Sleep Evaluation (Google) In use Agents search large real codebases such as Chrome and Safari for critical, hard to find vulnerabilities. Scored by pass@1 success rate, run without safety guardrails. Gemini 3.5 Flash Cyber 72%