Zero of fourteen models named Archi first on the direct prompt; zero named LeanIX. Archi was named by fourteen of the fourteen models and LeanIX by eleven and Archi carries 24 labels and LeanIX 19, so the shares are not directly comparable.
Named in one category this edition.
Named in three categories 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 enterprise architecture tools page.
Across every category in the November 2026 Edition, Archi and LeanIX were named in the same answer eighteen times, of the 77 answers naming Archi and the 61 naming LeanIX. In those answers LeanIX took the first choice one time and Archi eight.
| Model | DirectAR | ParaphraseAR | ComparativeAR | Budget-constrainedAR | Scale-constrainedAR | NegativeAR |
|---|---|---|---|---|---|---|
| Claude Haiku 4.5 | AR | AR | ||||
| GPT-5.4 mini | AR | |||||
| Gemini 3.5 Flash | AR | |||||
| Perplexity Sonar | AR | |||||
| Grok 4.20 | AR | AR | AR | |||
| Mistral Small | AR | AR | ||||
| DeepSeek V4 Flash | AR | |||||
| Llama 4 Maverick | AR | |||||
| Qwen 3.7 Flash | AR | |||||
| Kimi K2 | AR | AR | ||||
| GLM 4.7 FlashX | AR | |||||
| MiniMax M2.5 | AR | AR | ||||
| GPT-6 Luna | AR | |||||
| Muse Glimmer 30B | AR |
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 eight in this category shown.
“Archi lacks enterprise-grade features of commercial tools including no cloud collaboration, limited integrations... This makes it unsuitable for organizations requiring robust enterprise support.” Claude Haiku 4.5 · negative prompt · hard negative
“Limitations: No enterprise features like workflow governance, role-based access, or automated discovery” MiniMax M2.5 · comparative prompt · soft negative
“it can become problematic when organizations try to scale it for complex needs” Mistral Small · negative prompt · soft negative
“starting with Archi for pure ArchiMate work, or Essential Open Source for a self-hosted EA knowledge base, gives the most capability for zero license cost” Muse Glimmer 30B · budget prompt · first choice
“I'd suggest beginning with open-source tools like Archi combined with free collaboration tools” Claude Haiku 4.5 · budget prompt · first choice
“Archi (free and open-source) is often the best choice for a company with a limited budget.” Grok 4.20 · budget prompt · first choice
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Six of eight in this category shown.
“What to Avoid on a Tight Budget ... Priced per application, typically $30K–$100K+/year” DeepSeek V4 Flash · budget prompt · hard negative
“Avoid starting with LeanIX, Bizzdesign, HOPEX, or ServiceNow” Perplexity Sonar · budget prompt · hard negative
“rather than trying to use a full-scale repository tool (like ServiceNow TOWER or LeanIX) which can cost tens of thousands of dollars a year” Qwen 3.7 Flash · budget prompt · soft negative
“LeanIX: Cloud-native, collaborative, strong automation and SaaS focus. Excellent for mid-market; integrates well with ServiceNow/Jira. High usability; AI-driven insights.” Grok 4.20 · scale prompt · first choice
“Best for: Fast time-to-value, SaaS/Cloud discovery, straightforward Application Portfolio Management (APM).” Gemini 3.5 Flash · scale prompt · first choice
“Target Instead: Modern, cloud-native EA platforms (e.g., LeanIX, Ardoq, Avolution ABACUS, BOC ADOIT)” Gemini 3.5 Flash · negative prompt · first choice
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.