Zero of fourteen models named OpenCanary first on the direct prompt; one named Illusive Networks. OpenCanary was named by ten of the fourteen models and Illusive Networks by eight and OpenCanary carries 17 labels and Illusive Networks 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 | DirectOPIN | ParaphraseOPIN | ComparativeOPIN | Budget-constrainedOPIN | Scale-constrainedOPIN | NegativeOPIN |
|---|---|---|---|---|---|---|
| Claude Haiku 4.5 | OP | |||||
| GPT-5.4 mini | ||||||
| Gemini 3.5 Flash | OP | OP | IN | |||
| Perplexity Sonar | OP | OP | ||||
| Grok 4.1 Fast | OP | IN | OP | |||
| Mistral Small | OP | |||||
| DeepSeek V4 Flash | OPIN | OP | IN | |||
| Llama 4 Maverick | ||||||
| Qwen 3.7 Flash | ||||||
| Kimi K2 | IN | IN | OP | |||
| GLM 4.7 FlashX | IN | OP | ||||
| MiniMax M2.5 | IN | IN | ||||
| GPT-6 Luna | OP | OP | ||||
| Muse Glimmer 30B | OP | IN |
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 Canarytokens.org (free) + OpenCanary (free)” Kimi K2 · budget prompt · first choice
“For a genuinely limited budget, start with OpenCanary.” GPT-6 Luna · budget prompt · first choice
“Another strong open-source option is OpenCanary, also from Thinkst, which is free and supports multiple protocols.” Mistral Small · paraphrase prompt · alternative
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Six of eight in this category shown.
“Pure network-wide standalone deception from Illusive is essentially sunsetted” Gemini 3.5 Flash · negative prompt · hard negative
“Caution flags: Reviews note it is "heavily focused on Microsoft environments" and has "limited cloud-native capabilities."” DeepSeek V4 Flash · negative prompt · soft negative
“legacy Illusive installs should be treated as end-of-life from a vendor perspective” Muse Glimmer 30B · negative prompt · soft negative
“I recommend requesting demos from Illusive Networks and Acalvio specifically, as they appear most focused on the mid-market segment.” MiniMax M2.5 · direct prompt · first choice
“Often rated as the best overall deception platform for operational value.” Kimi K2 · comparative prompt · first choice
“excels at identity and credential deception, providing agentless decoys that disrupt lateral movement” GLM 4.7 FlashX · 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.