What is Garrulus-Agent?

Garrulus-Agent is a Source-Grounded Cybersecurity AI Agent: an AI agent for cybersecurity knowledge that checks its answers against trusted sources. It was built by Emrah Dündar on his own initiative.

CS-Eval is an open evaluation of cybersecurity knowledge for large language models, with 4,369 questions across 11 domains and 42 subdomains. It was developed by researchers from Alibaba Group, Fudan University and the University of Chinese Academy of Sciences.

Where does Garrulus-Agent rank on CS-Eval?

As of 12 November 2026 it ranks first among 54 entries with a score of 99.38. It is the first model on CS-Eval to score a perfect 100 in six categories and the first to cross the 99 mark overall.

CS-EVAL CYBERSECURITY EVALUATION

Garrulus-Agent

Source-Grounded Cybersecurity AI Agent

1 / 54Overall rank

99.38Overall score

The first model to score a perfect 100 in six categories and cross the 99 mark overall.

See the official leaderboard See the evidence

Emrah Dündar

Six perfect scores, lowest category 98.54

CS-Eval: open evaluation by researchers from Alibaba Group, Fudan University and the University of Chinese Academy of Sciences. 11 domains, 42 subdomains, 4,369 questions.

100System and software
100Encryption
100AI and network
100Business continuity
100Security architecture
100Supply chain

CS-Eval category scores
Category	Score
System and software security basics	100
Encryption and key management	100
AI and network security	100
Business continuity and recovery	100
Security architecture design	100
Supply chain security	100
Data security and privacy	99.60
Infrastructure security	99.17
Threat detection and prevention	99.08
Access control and identity management	98.85
Vulnerability management and pentesting	98.54

First Among 54 Entries

CS-Eval Overall Ranking, Top 6 Results

1Garrulus-AgentEmrah Dündar · independent developer99.38
2RunjianMenshen98.49
3China Unicom Digital TechnologyMogong V3-Agent98.47
4China Telecom Security TechnologyJianwei Agent98.33
5QAXQGPT V5 QAgent98.26
6AntiyLandi N297.96

0.89 points ahead of second place, the widest gap between consecutive ranks in the top six.

Visualization: CS-Eval overall ranking, 12 November 2026

The official leaderboard

CS-Eval overall ranking screen, Garrulus-Agent first with a score of 99.38

cs-eval.com, 12 November 2026. Screenshots cropped, data unchanged. The Chinese Questions row is a language subset, not one of the 11 categories. English model names on the leaderboard screen are the site's automatic translation.

Leaderboard Paper Dataset

Quick questions

What is Garrulus-Agent?: Garrulus-Agent is a Source-Grounded Cybersecurity AI Agent: an AI agent for cybersecurity knowledge that checks its answers against trusted sources. It was built by Emrah Dündar on his own initiative.
What is CS-Eval?: CS-Eval is an open evaluation of cybersecurity knowledge for large language models, with 4,369 questions across 11 domains and 42 subdomains. It was developed by researchers from Alibaba Group, Fudan University and the University of Chinese Academy of Sciences.
Where does Garrulus-Agent rank on CS-Eval?: As of 12 November 2026 it ranks first among 54 entries with a score of 99.38. It is the first model on CS-Eval to score a perfect 100 in six categories and the first to cross the 99 mark overall.

With the right engineering, agent systems and disciplined evaluation, open-source models become high-performing, domain-focused AI solutions.

Emrah Dündar

Connect on LinkedIn