EXTERNAL ASSESSMENT ·

AgentCyberRange official snapshot

Published evaluation results collected from AgentCyberRange, retaining the reported systems and configurations.

Published Not verified

Source version, extraction coverage and findings →

Web exploitation and post-exploitation are separate evaluations. Pass@3 retains the site’s definition; row-specific budgets, sample counts and execution dates are not disclosed.

Models covered

GPT-5.5 →Claude Opus 4.7 →DeepSeek V4 Pro →DeepSeek-V4-Flash →Kimi K3 →

capability · routes-B-0Mubrq.js::QR/1/level0/pass3

AgentCyberRange · Web exploitation · pass3

Protocol record →

Task success across web exploitation and post-exploitation settings; configurations must be checked per submission.

Web exploitation and post-exploitation are separate evaluations. Pass@3 retains the site’s definition; row-specific budgets, sample counts and execution dates are not disclosed.

External evaluation:

This section is catalogued; no precise numerical result has been extracted here. Open the original report for its figures and full findings.

capability · routes-B-0Mubrq.js::$R/1/level0/pass3

AgentCyberRange · Post exploitation · pass3

Protocol record →

Task success across web exploitation and post-exploitation settings; configurations must be checked per submission.

Web exploitation and post-exploitation are separate evaluations. Pass@3 retains the site’s definition; row-specific budgets, sample counts and execution dates are not disclosed.

External evaluation:

This section is catalogued; no precise numerical result has been extracted here. Open the original report for its figures and full findings.

Report coverage

Section	Source location	Treatment
AgentCyberRange · Web exploitation · pass3	routes-B-0Mubrq.js::QR/1/level0/pass3	reviewed-source-group Web exploitation and post-exploitation are separate evaluations. Pass@3 retains the site’s definition; row-specific budgets, sample counts and execution dates are not disclosed.
AgentCyberRange · Post exploitation · pass3	routes-B-0Mubrq.js::$R/1/level0/pass3	reviewed-source-group Web exploitation and post-exploitation are separate evaluations. Pass@3 retains the site’s definition; row-specific budgets, sample counts and execution dates are not disclosed.

References

Numerical results are reported by the cited authors.

[1] AgentCyberRange: Evaluate Agent Cyberattack Capabilities in Enterprise-like Cyber Ranges ; routes-B-0Mubrq.js::QR/1/level0/pass3; routes-B-0Mubrq.js::QR/2/level0/pass3; routes-B-0Mubrq.js::QR/3/level0/pass3