Two of fourteen models named Tracebit first on the direct prompt; one named Fortinet FortiDeceptor. Tracebit was named by ten of the fourteen models and Fortinet FortiDeceptor by seven and Tracebit carries 18 labels and Fortinet FortiDeceptor 10, 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, Tracebit and Fortinet FortiDeceptor were named in the same answer six times, of the 39 answers naming Tracebit and the 23 naming Fortinet FortiDeceptor. In those answers Fortinet FortiDeceptor took the first choice zero times and Tracebit one.
| Model | Direct | Paraphrase | Comparative | Budget-constrained | Scale-constrained | Negative |
|---|---|---|---|---|---|---|
| Claude Haiku 4.5 | ||||||
| GPT-5.4 mini | ||||||
| Gemini 3.5 Flash | ||||||
| Perplexity Sonar | ||||||
| Grok 4.1 Fast | ||||||
| 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 seven in this category shown.
“User reviews cite concerns about: Confusing, cluttered interface; Difficult navigation; False positives requiring manual review” Kimi K2 · negative prompt · soft negative
“G2 review summaries for Tracebit mention a confusing/cluttered interface, false positives, and a higher learning curve.” GPT-5.4 mini · negative prompt · soft negative
“While primarily focused on enterprise... check for the latest pricing and suitability for your scale.” Mistral Small · budget prompt · soft negative
“Lightweight / Token-Centric Deception (e.g., Thinkst Canary, Tracebit) ... Best For: Mid-market companies with small teams.” Gemini 3.5 Flash · scale prompt · first choice
“Top Recommendation: Tracebit” DeepSeek V4 Flash · direct prompt · first choice
“I'd shortlist Tracebit first” GPT-6 Luna · direct prompt · first choice
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Three of four in this category shown.
“Rapid7 or Fortinet FortiDeceptor are the most frequently cited value choices” Muse Glimmer 30B · direct prompt · first choice
“Platform-Integrated Deception (e.g., SentinelOne Singularity Deception, Fortinet FortiDeceptor)” Gemini 3.5 Flash · scale prompt · alternative
“Choose FortiDeceptor if your company is already a Fortinet shop or has OT/IoT exposure.” Perplexity Sonar · 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.