Zero of fourteen models named OpenCanary first on the direct prompt; one named Fidelis Deception. OpenCanary was named by thirteen of the fourteen models and Fidelis Deception by eight and OpenCanary carries 22 labels and Fidelis Deception 12, 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 deception technology page.
| Model | DirectOP | ParaphraseOP | ComparativeOP | Budget-constrainedOP | Scale-constrainedOP | NegativeOP |
|---|---|---|---|---|---|---|
| Claude Haiku 4.5 | OP | |||||
| GPT-5.4 mini | OP | |||||
| Gemini 3.5 Flash | OP | OP | ||||
| Perplexity Sonar | OP | |||||
| Grok 4.20 | OP | OP | ||||
| Mistral Small | OP | |||||
| DeepSeek V4 Flash | OP | |||||
| Llama 4 Maverick | ||||||
| Qwen 3.7 Flash | OP | OP | ||||
| Kimi K2 | OP | OP | ||||
| GLM 4.7 FlashX | OP | |||||
| MiniMax M2.5 | OP | |||||
| GPT-6 Luna | OP | OP | ||||
| Muse Glimmer 30B | OP | OP |
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. Three of four in this category shown.
“start with canary tokens and one OpenCanary host, because they cost almost nothing and produce alerts you can trust.” Muse Glimmer 30B · budget prompt · first choice
“For a very limited budget, start with OpenCanary.” GPT-6 Luna · budget prompt · first choice
“OpenCanary is the leading open-source network honeypot platform for teams that want low-overhead network-level deception” Claude Haiku 4.5 · budget prompt · alternative
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.