One of fourteen models named Microsoft Purview first on the direct prompt; one named Check Point AI Security. Microsoft Purview was named by eight of the fourteen models and Check Point AI Security by eleven and Microsoft Purview carries 11 labels and Check Point AI Security 17, so the shares are not directly comparable.
Named in eleven categories 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 AI security platforms page.
| 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.
No label in this category carried a quote.
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Five of six in this category shown.
“often better suited for larger enterprises or those already deeply invested in specific ecosystems” Mistral Small · direct prompt · soft negative
“may feel more enterprise-oriented” Grok 4.20 · direct prompt · soft negative
“Top Recommendation: Check Point AI Security” Grok 4.20 · paraphrase prompt · first choice
“Top Pick: Check Point (CloudGuard AI)” Qwen 3.7 Flash · direct prompt · first choice
“If you want to bundle this with your overall network security: Look at Check Point, Cisco, or Cato (with Aim).” Qwen 3.7 Flash · 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.