Seven of fourteen models named SAP LeanIX first on the direct prompt; zero named Sparx Systems Enterprise Architect. SAP LeanIX was named by thirteen of the fourteen models and Sparx Systems Enterprise Architect by thirteen and SAP LeanIX carries 46 labels and Sparx Systems Enterprise Architect 26, 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 enterprise architecture tools page.
Across every category in the November 2026 Edition, SAP LeanIX and Sparx Systems Enterprise Architect were named in the same answer forty times, of the 143 answers naming SAP LeanIX and the 67 naming Sparx Systems Enterprise Architect. In those answers Sparx Systems Enterprise Architect took the first choice five times and SAP LeanIX thirteen.
| Model | DirectSL | ParaphraseSL | ComparativeSL | Budget-constrainedSL | Scale-constrainedSL | NegativeSL |
|---|---|---|---|---|---|---|
| Claude Haiku 4.5 | SL | |||||
| GPT-5.4 mini | ||||||
| Gemini 3.5 Flash | SL | SL | SL | |||
| Perplexity Sonar | SL | SL | SL | SL | ||
| Grok 4.20 | SL | SL | SL | SL | ||
| Mistral Small | SL | |||||
| DeepSeek V4 Flash | SL | SL | SL | SL | SL | |
| Llama 4 Maverick | SL | |||||
| Qwen 3.7 Flash | SL | SL | SL | |||
| Kimi K2 | SL | SL | SL | SL | ||
| GLM 4.7 FlashX | SL | SL | SL | |||
| MiniMax M2.5 | SL | SL | SL | SL | ||
| GPT-6 Luna | SL | SL | SL | SL | SL | |
| Muse Glimmer 30B | SL |
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.
“Avoid overkill: High-end tools like SAP LeanIX, Bizzdesign, or MEGA HOPEX ... can cost thousands per user/year—unnecessary for constrained budgets.” Grok 4.20 · budget prompt · hard negative
“Tools like SAP LeanIX, BiZZdesign HoriZZon, and MEGA HOPEX are comprehensive platforms, but they can be: Prohibitively expensive” MiniMax M2.5 · negative prompt · soft negative
“SAP LeanIX if you want to avoid a strategic commitment to SAP's ecosystem... the acquisition alone isn't a reason to reject it.” GPT-6 Luna · negative prompt · soft negative
“For a mid-sized B2B company, SAP LeanIX would be the strongest default recommendation for application portfolio management.” Perplexity Sonar · paraphrase prompt · first choice
“I recommend starting with SAP LeanIX if you have SAP investments, or Ardoq if you need strong collaboration features” GLM 4.7 FlashX · direct prompt · first choice
“Choose SAP LeanIX if: You're modernizing IT, need strong cloud/SaaS visibility, want intuitive stakeholder engagement” Kimi K2 · comparative 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.
“Verdict: Avoid for large, distributed teams; consider only for small technical teams with heavy modeling needs” Kimi K2 · negative prompt · hard negative
“Frequently cited as having the steepest learning curve and the highest number of negative labels among EA tools.” Mistral Small · negative prompt · hard negative
“Tools to Avoid ... Sparx Systems Enterprise Architect - Why to avoid: Extremely steep learning curve” GLM 4.7 FlashX · negative prompt · hard negative
“The standout "best value" answer for most small-to-mid companies is Sparx Enterprise Architect” DeepSeek V4 Flash · budget prompt · first choice
“Sparx Systems Enterprise Architect remains the most cost-effective solution on the market.” Gemini 3.5 Flash · budget prompt · first choice
“Sparx Systems Enterprise Architect is the strongest overall choice” Perplexity Sonar · budget 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.