Three of fourteen models named Abnormal AI first on the direct prompt; two named IRONSCALES. Abnormal AI was named by fourteen of the fourteen models and IRONSCALES by twelve and Abnormal AI carries 43 labels and IRONSCALES 23, so the shares are not directly comparable.
Named in two categories this edition.
Named in two categories 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 email security page.
Across every category in the November 2026 Edition, Abnormal AI and IRONSCALES were named in the same answer forty-two times, of the 117 answers naming Abnormal AI and the 72 naming IRONSCALES. In those answers IRONSCALES took the first choice ten times and Abnormal AI five.
| 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.
“Avoid for Budget Scenarios - Abnormal Security - ... pricing starts at $25,000/year” MiniMax M2.5 · budget prompt · hard negative
“Abnormal Security — powerful but requires expensive add-ons” DeepSeek V4 Flash · budget prompt · hard negative
“without the complexity or high costs of tools like Abnormal Security (which starts at $25K+/year)” Grok 4.20 · budget prompt · soft negative
“Add Abnormal AI (or an equivalent AI-based layer) to catch the sophisticated BEC and social engineering threats that generic gateways miss” DeepSeek V4 Flash · direct prompt · first choice
“Consider modern platforms like Abnormal Security, Material Security, or Microsoft Defender for Office 365” DeepSeek V4 Flash · negative prompt · first choice
“My default pick: Abnormal AI for a mid-market B2B company using Microsoft 365 or Google Workspace” GPT-6 Luna · direct 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.
“significant drop in recommendation confidence (from 9% to 2%)... indicating potential issues with performance, reliability, or user satisfaction” Mistral Small · negative prompt · hard negative
“Best overall customer satisfaction / AI-native mailbox protection: IRONSCALES. High willingness to recommend and rapid API deployment.” Muse Glimmer 30B · direct prompt · first choice
“I'd suggest starting with either IRONSCALES or Check Point/Avanan” MiniMax M2.5 · direct prompt · first choice
“Start with Proofpoint, Microsoft Defender for Office 365, or IRONSCALES” GLM 4.7 FlashX · scale 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.