Blog
-1.png?dpl=dpl_GycErdZXLJMxm5uSTkjBbSkZosyX)
Security without the Spectacle
Context Management for Agentic Security
Evaluating AI Agents in Security Operations (December 2025)
Which frontier model should you use for SecOps automation? We added the latest cohort of frontier models to our benchmark to find out.
Security without the Spectacle
Context Management for Agentic Security
Recently Added
Recently Added
Engineering Blogs
Research Blogs
Evaluating AI Agents in Security Operations (December 2025)
Which frontier model should you use for SecOps automation? We added the latest cohort of frontier models to our benchmark to find out.
Evaluating AI Agents in Security Operations
We benchmarked frontier AI models on realistic security operations (SecOps) tasks using Cotool’s agent harness and the Splunk BOTSv3 dataset. GPT-5 achieved the highest accuracy (63%), while Claude Haiku-4.5 completed tasks the fastest with strong accuracy. GPT-5 variants dominated the performance-cost frontier. These results provide practical guidance for model selection in enterprise SecOps automation.
Company Blogs
Attackers are scaling with tokens
Cotool helps defenders operate at machine speed. See how security teams are scaling Detection & Response.
Request a demo
All Reads
Design and implement software systems, conduct code reviews, optimize application performance.
Evaluating AI Agents in Security Operations (December 2025)
Which frontier model should you use for SecOps automation? We added the latest cohort of frontier models to our benchmark to find out.
Evaluating AI Agents in Security Operations
We benchmarked frontier AI models on realistic security operations (SecOps) tasks using Cotool’s agent harness and the Splunk BOTSv3 dataset. GPT-5 achieved the highest accuracy (63%), while Claude Haiku-4.5 completed tasks the fastest with strong accuracy. GPT-5 variants dominated the performance-cost frontier. These results provide practical guidance for model selection in enterprise SecOps automation.
Context Management for Agentic Security
How we are solving the LLM Security Data problem
Security without the Spectacle
Why would anyone want to start an AI security company?