Zero of fourteen models named MITRE Caldera first on the direct prompt; zero named Infection Monkey. MITRE Caldera was named by nine of the fourteen models and Infection Monkey by nine and both carry 11 labels, so the shares below are directly comparable.
Named in one category this edition.
Named in one category this edition.
Share is the count of first choices across the direct, paraphrase, budget and scale prompts over all fourteen models, for a mid-market B2B company; rank is within the category; every quote names the model and the prompt it came from. Both figures come from the breach and attack simulation page.
Across every category in the November 2026 Edition, MITRE Caldera and Infection Monkey were named in the same answer twelve times, of the 21 answers naming MITRE Caldera and the 39 naming Infection Monkey. In those answers Infection Monkey took the first choice one time and MITRE Caldera six.
| Model | DirectMCIM | ParaphraseMCIM | ComparativeMCIM | Budget-constrainedMCIM | Scale-constrainedMCIM | NegativeMCIM |
|---|---|---|---|---|---|---|
| Claude Haiku 4.5 | MC | |||||
| GPT-5.4 mini | IM | |||||
| Gemini 3.5 Flash | MCIM | |||||
| Perplexity Sonar | MC | |||||
| Grok 4.20 | MCIM | MC | ||||
| Mistral Small | ||||||
| DeepSeek V4 Flash | MC | |||||
| Llama 4 Maverick | ||||||
| Qwen 3.7 Flash | ||||||
| Kimi K2 | MCIM | IM | ||||
| GLM 4.7 FlashX | MCIM | IM | ||||
| MiniMax M2.5 | MCIM | |||||
| GPT-6 Luna | ||||||
| Muse Glimmer 30B | MCIM |
Bold names in an answer are the products the judge labeled a first choice; a model naming several gives each of them that label. The full answer text for every row is in the record.
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Four of five in this category shown.
“Open-source alternatives (e.g., MITRE Caldera, Atomic Red Team) can supplement but usually lack the enterprise polish” Grok 4.20 · scale prompt · soft negative
“free and open-source BAS tools like MITRE Caldera and Prelude Operator offer powerful capabilities for simulating adversary behaviors without any licensing fees” Claude Haiku 4.5 · budget prompt · first choice
“MITRE Caldera (or a combination with Atomic Red Team) is the best breach and attack simulation (BAS) option for a company with a limited budget.” Grok 4.20 · budget prompt · first choice
“Start free: Deploy Atomic Red Team or MITRE Caldera to establish baseline testing” MiniMax M2.5 · budget prompt · first choice
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Four of five in this category shown.
“it's generally less polished and more DIY than commercial platforms” GPT-5.4 mini · budget prompt · soft negative
“Infection Monkey is the easiest free option for hands-on breach simulation and lateral movement mapping.” Muse Glimmer 30B · budget prompt · first choice
“Free for basic use; focuses on lateral movement, breach simulation, and self-propagation testing.” Grok 4.20 · budget prompt · alternative
“Cost: Free (GPL-3.0) ... Tests network segmentation and lateral movement” Kimi K2 · budget prompt · alternative
Comparisons are drawn for the top eight products in each category, each against each. The output is the models' output; nothing here is a recommendation by the index.