One of fourteen models named Microsoft Defender for IoT first on the direct prompt; one named Dragos Platform. Microsoft Defender for IoT was named by thirteen of the fourteen models and Dragos Platform by fourteen and Microsoft Defender for IoT carries 42 labels and Dragos Platform 46, so the shares are not 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 OT and IoT security page.
Across every category in the October 2026 Edition, Microsoft Defender for IoT and Dragos Platform were named in the same answer ninety times, of the 134 answers naming Microsoft Defender for IoT and the 136 naming Dragos Platform. In those answers Dragos Platform took the first choice thirteen times and Microsoft Defender for IoT twenty-four.
| Model | DirectMD | ParaphraseMD | ComparativeMD | Budget-constrainedMD | Scale-constrainedMD | NegativeMD |
|---|---|---|---|---|---|---|
| Claude Haiku 4.5 | MD | |||||
| GPT-5.4 mini | ||||||
| Gemini 3.5 Flash | MD | MD | MD | MD | MD | |
| Perplexity Sonar | MD | MD | ||||
| Grok 4.1 Fast | MD | MD | MD | MD | ||
| Mistral Small | MD | |||||
| DeepSeek V4 Flash | MD | MD | MD | |||
| Llama 4 Maverick | MD | |||||
| Qwen 3.7 Flash | MD | MD | ||||
| Kimi K2 | MD | MD | MD | MD | ||
| GLM 4.7 FlashX | MD | MD | ||||
| MiniMax M2.5 | MD | MD | ||||
| GPT-6 Luna | MD | MD | MD | |||
| Muse Glimmer 30B | MD | MD | MD |
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. Six of eight in this category shown.
“Avoid if budget is tight: Nozomi Networks and Microsoft Defender for IoT” Perplexity Sonar · budget prompt · hard negative
“I'd avoid starting a new deployment that depends on this console... That's a caution about the legacy console, not a blanket warning against Microsoft Defender for IoT.” GPT-6 Luna · negative prompt · soft negative
“These are IT-security vendors extending into OT. Their effectiveness depends on how well their OT findings integrate with your existing SOC” Mistral Small · negative prompt · soft negative
“For most mid-market B2B companies, Microsoft Defender for IoT (if you are a Microsoft shop) or Fortinet (if you use their network hardware) are the most successful starting points” Gemini 3.5 Flash · direct prompt · first choice
“For a small company with one OT site and up to 100 devices, I'd start by evaluating Microsoft Defender for IoT's XS site license.” GPT-6 Luna · budget prompt · first choice
“I'd suggest starting with Microsoft Defender for IoT ($70-250/month) as the most cost-effective commercial solution” Kimi K2 · budget prompt · first choice
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Six of eight in this category shown.
“What to Avoid (for Mid-Market) ... Premium pricing (~$100K+/year for single site) and complex deployments.” Kimi K2 · direct prompt · hard negative
“What to avoid on a tight budget: Claroty, Nozomi Networks, and Dragos” DeepSeek V4 Flash · budget prompt · hard negative
“Dragos is excellent but tends to lean toward highly complex, utility-grade environments with threat intelligence-heavy requirements.” Gemini 3.5 Flash · scale prompt · soft negative
“For OT threat intelligence depth → Dragos (especially if you want the best intelligence subscription and IR expertise)” DeepSeek V4 Flash · comparative prompt · first choice
“Recognized as a leader for its robust OT-specific threat detection, asset visibility, and risk management.” Mistral Small · direct prompt · first choice
“consider platforms purpose-built for industrial environments, such as Dragos, Nozomi Networks, or Claroty” Mistral Small · negative prompt · first choice
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.