CounterCraft vs Fidelis Deception
One of fourteen models named CounterCraft first on the direct prompt; one named Fidelis Deception. CounterCraft was named by eleven of the fourteen models and Fidelis Deception by eight and CounterCraft carries 20 labels and Fidelis Deception 12, so the shares are not directly comparable.
CounterCraft
criticized challengerNamed 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 deception technology page.
By framing
Across every category in the November 2026 Edition, CounterCraft and Fidelis Deception were named in the same answer twenty times, of the 63 answers naming CounterCraft and the 33 naming Fidelis Deception. In those answers Fidelis Deception took the first choice zero times and CounterCraft zero.
Every model, every framing
| Model | DirectCO | ParaphraseCO | ComparativeCO | Budget-constrainedCO | Scale-constrainedCO | NegativeCO |
|---|---|---|---|---|---|---|
| Claude Haiku 4.5 | ||||||
| GPT-5.4 mini | CO | |||||
| Gemini 3.5 Flash | CO | CO | ||||
| Perplexity Sonar | | CO | CO | CO | ||
| Grok 4.20 | CO | CO | CO | |||
| Mistral Small | ||||||
| DeepSeek V4 Flash | CO | |||||
| Llama 4 Maverick | | CO | ||||
| Qwen 3.7 Flash | ||||||
| Kimi K2 | CO | | ||||
| GLM 4.7 FlashX | CO | |||||
| MiniMax M2.5 | CO | |||||
| GPT-6 Luna | ||||||
| Muse Glimmer 30B |
Fidelis DeceptionCO first choiceCO named as an alternativeCO argued againstblank: not namedEach cell is one answer, CounterCraft on the left and Fidelis Deception on the right.The direct prompt
Both were the first choice
1 of 14 modelsThe answer named them together, and the judge labeled each a first choice.Neither was the first choice, one was named
2 of 14 modelsThe answer put something else first and named one of the two as an alternative.Neither was named
11 of 14 modelsThe answer made no first choice from these two in this category.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.
By buyer segment
Fidelis Deception0%#– of 15Fidelis Deception2%#8 of 16Fidelis Deception0%#11 of 13What the models said about CounterCraft
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 starting with broad enterprise platforms such as Acalvio, CounterCraft, or Zscaler Deception” Perplexity Sonar · budget prompt · hard negative
“Avoid overly complex enterprise suites like *Acalvio ShadowPlex* or *CounterCraft*” Gemini 3.5 Flash · direct prompt · hard negative
“often start at thousands of dollars per year ... making them unsuitable for tight budgets” Grok 4.20 · budget prompt · soft negative
“High-interaction decoys, strong across network/endpoint/identity/cloud/OT; praised for threat intel.” Grok 4.20 · negative prompt · first choice
“I would recommend Fidelis Security or CounterCraft as the top choices” MiniMax M2.5 · direct prompt · first choice
“Particularly strong for organizations that want deception as part of a broader threat intelligence program” DeepSeek V4 Flash · comparative prompt · alternative
What the models said about Fidelis Deception
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Four of four in this category shown.
“others (e.g., Acalvio, Fidelis) target Fortune 500 with more complexity” Kimi K2 · scale prompt · soft negative
“I would recommend Fidelis Security or CounterCraft as the top choices” MiniMax M2.5 · direct prompt · first choice
“More platform complexity than most mid-market buyers need” Perplexity Sonar · direct prompt · alternative
“Other options include ... Fidelis Deception” Llama 4 Maverick · direct 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.