One of fourteen models named Censys ASM first on the direct prompt; zero named Cortex Xpanse. Censys ASM was named by thirteen of the fourteen models and Cortex Xpanse by twelve and Censys ASM carries 30 labels and Cortex Xpanse 31, 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, Censys ASM and Cortex Xpanse were named in the same answer forty-five times, of the 80 answers naming Censys ASM and the 119 naming Cortex Xpanse. In those answers Cortex Xpanse took the first choice eleven times and Censys ASM zero.
| 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.
“Censys ASM is a platform that several sources explicitly advise caution about or even avoid for certain use cases” Mistral Small · negative prompt · hard negative
“delivers best-in-class internet scanning as a data layer but offers no validation, making it a strong input rather than a standalone program” Llama 4 Maverick · negative prompt · soft negative
“The interface and workflow can feel more technical; pricing isn't published and may scale beyond mid-market comfort zones.” DeepSeek V4 Flash · direct prompt · soft negative
“If your budget is tight, Censys ASM is usually the best first place to look.” GPT-5.4 mini · budget prompt · first choice
“Censys ASM is probably the best default choice for a mid-market B2B company” GPT-5.4 mini · direct prompt · first choice
“My default recommendation: Censys ASM for a mid-sized B2B company” GPT-6 Luna · 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.
“What to Avoid ... Enterprise-focused; ~$95,000/year starting price” Kimi K2 · paraphrase prompt · hard negative
“Enterprise tools like Palo Alto Cortex Xpanse, Censys, and Mandiant ASM are powerful but often assume six-figure budgets” Kimi K2 · direct prompt · soft negative
“General high-cost or complex platforms (e.g., Cortex Xpanse, Mandiant ASM, CrowdStrike Falcon Exposure Management)” Grok 4.20 · negative prompt · soft negative
“Strong in automated discovery, risk prioritization, and response. Excellent for broad internet-facing assets and integrations.” Grok 4.20 · scale prompt · first choice
“A leading Cyber Asset Attack Surface Management (CAASM) tool, recognized as a Leader in Forrester's 2024 ASM Wave.” Mistral Small · comparative prompt · first choice
“Cortex Xpanse represents the enterprise benchmark for internet-scale external attack surface management” MiniMax M2.5 · comparative 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.