One of fourteen models named Microsoft Defender External Attack Surface Management first on the direct prompt; zero named Tenable Attack Surface Management. Both were named by all fourteen models and Microsoft Defender External Attack Surface Management carries 56 labels and Tenable Attack Surface Management 22, 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 attack surface management page.
Across every category in the November 2026 Edition, Microsoft Defender External Attack Surface Management and Tenable Attack Surface Management were named in the same answer sixty-six times, of the 161 answers naming Microsoft Defender External Attack Surface Management and the 81 naming Tenable Attack Surface Management. In those answers Tenable Attack Surface Management took the first choice three times and Microsoft Defender External Attack Surface Management four.
| Model | Direct | Paraphrase | Comparative | Budget-constrained | Scale-constrained | Negative |
|---|---|---|---|---|---|---|
| Claude Haiku 4.5 | ||||||
| GPT-5.4 mini | ||||||
| Gemini 3.5 Flash | ||||||
| Perplexity Sonar | ||||||
| Grok 4.20 | ||||||
| Mistral Small | ||||||
| DeepSeek V4 Flash | ||||||
| Llama 4 Maverick | ||||||
| Qwen 3.7 Flash | ||||||
| Kimi K2 | ||||||
| GLM 4.7 FlashX | ||||||
| MiniMax M2.5 | ||||||
| GPT-6 Luna | ||||||
| Muse Glimmer 30B |
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.
“Better suited for organizations heavily invested in Microsoft stack” Kimi K2 · paraphrase prompt · hard negative
“Complex to configure (typical Microsoft complexity), generates significant false positives, requires existing Microsoft licensing” Kimi K2 · negative prompt · soft negative
“Strongly Azure/Microsoft-centric—poor fit if you're not heavily invested in their ecosystem” Grok 4.20 · negative prompt · soft negative
“If you already use CrowdStrike or Microsoft 365/Azure: Start a Proof of Concept (PoC) with Microsoft Defender EASM” Gemini 3.5 Flash · paraphrase prompt · first choice
“For most modern enterprises, CyCognito and Microsoft EASM are currently leading the market” Qwen 3.7 Flash · comparative prompt · first choice
“Microsoft Defender External Attack Surface Management is often the most pragmatic starting point” GLM 4.7 FlashX · paraphrase 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.
“economically attractive when you already use the corresponding ecosystem, but avoid assuming that an existing EDR or vulnerability-management deployment automatically provides complete external discovery” Perplexity Sonar · negative prompt · soft negative
“they can feel complex and expensive for mid-sized teams (better suited to enterprises with dedicated resources)” Grok 4.20 · paraphrase prompt · soft negative
“Users note room for improvement in integration with other tools” DeepSeek V4 Flash · negative prompt · soft negative
“I'd usually recommend Tenable One Attack Surface Management as the default starting point” GPT-5.4 mini · paraphrase prompt · first choice
“Tenable One Attack Surface Management link external findings to existing vulnerability and exposure management workflows” Muse Glimmer 30B · comparative prompt · alternative
“suits organizations that have already invested in the Tenable vulnerability management ecosystem” MiniMax M2.5 · comparative 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.