Zero of fourteen models named OpenCanary first on the direct prompt; zero named T-Pot. OpenCanary was named by ten of the fourteen models and T-Pot by nine and OpenCanary carries 17 labels and T-Pot 11, 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.
Across every category in the October 2026 Edition, OpenCanary and T-Pot were named in the same answer nineteen times, of the 40 answers naming OpenCanary and the 31 naming T-Pot. In those answers T-Pot took the first choice zero times and OpenCanary seven.
| Model | DirectOPTP | ParaphraseOPTP | ComparativeOPTP | Budget-constrainedOPTP | Scale-constrainedOPTP | NegativeOPTP |
|---|---|---|---|---|---|---|
| Claude Haiku 4.5 | OP | |||||
| GPT-5.4 mini | TP | |||||
| Gemini 3.5 Flash | OP | OPTP | ||||
| Perplexity Sonar | OP | OP | ||||
| Grok 4.1 Fast | OPTP | OP | ||||
| Mistral Small | OP | |||||
| DeepSeek V4 Flash | OP | OP | ||||
| Llama 4 Maverick | TP | |||||
| Qwen 3.7 Flash | TP | |||||
| Kimi K2 | OP | |||||
| GLM 4.7 FlashX | TP | OPTP | ||||
| MiniMax M2.5 | ||||||
| GPT-6 Luna | OP | OPTP | ||||
| Muse Glimmer 30B | TP | 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 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. Four of five in this category shown.
“High maintenance (Docker-heavy); better for labs than production.” Grok 4.1 Fast · paraphrase prompt · soft negative
“Pick `T-Pot` if you have ≥1 person who knows Linux, Docker, and log analysis, and you want maximum detection surface for $0.” Qwen 3.7 Flash · budget prompt · first choice
“2. T-Pot - an open-source honeypot platform that combines multiple protocol-specific honeypots and analytics tools.” Llama 4 Maverick · paraphrase prompt · alternative
“T-Pot is a strong option... but it has higher operational overhead and infrastructure requirements” GPT-5.4 mini · paraphrase 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.