Five of fourteen models named Microsoft Power Automate Process Mining first on the direct prompt; six named Apromore. Both were named by all fourteen models and Microsoft Power Automate Process Mining carries 47 labels and Apromore 46, 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 process mining page.
Across every category in the November 2026 Edition, Microsoft Power Automate Process Mining and Apromore were named in the same answer seventy-nine times, of the 124 answers naming Microsoft Power Automate Process Mining and the 128 naming Apromore. In those answers Apromore took the first choice twelve times and Microsoft Power Automate Process Mining twenty-three.
| Model | DirectMP | ParaphraseMP | ComparativeMP | Budget-constrainedMP | Scale-constrainedMP | NegativeMP |
|---|---|---|---|---|---|---|
| Claude Haiku 4.5 | MP | MP | MP | |||
| GPT-5.4 mini | MP | |||||
| Gemini 3.5 Flash | MP | MP | MP | MP | MP | |
| Perplexity Sonar | MP | MP | MP | |||
| Grok 4.20 | MP | MP | MP | MP | ||
| Mistral Small | MP | MP | MP | |||
| DeepSeek V4 Flash | MP | MP | MP | |||
| Llama 4 Maverick | MP | MP | ||||
| Qwen 3.7 Flash | MP | MP | MP | |||
| Kimi K2 | MP | MP | MP | MP | ||
| GLM 4.7 FlashX | MP | MP | MP | |||
| MiniMax M2.5 | MP | MP | MP | |||
| GPT-6 Luna | MP | MP | MP | MP | ||
| Muse Glimmer 30B | MP | MP |
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.
“Frequently called "terrible" in user forums for poor UX ... Alternatives if avoiding: Look at more robust options like Celonis or Apromore” Grok 4.20 · negative prompt · hard negative
“the most frequently criticized process mining tool in user communities” DeepSeek V4 Flash · negative prompt · hard negative
“check capacity and licensing carefully if you expect large analyses or many users” GPT-6 Luna · negative prompt · soft negative
“Best budget-friendly default: Microsoft Power Automate Process Mining—if your company already uses Microsoft’s Power Platform.” GPT-6 Luna · budget prompt · first choice
“Microsoft Power Automate Process Mining (part of the Power Platform) is often the best fit for a mid-market B2B company.” Grok 4.20 · direct prompt · first choice
“Microsoft Power Automate Process Mining and Apromore are widely considered the most cost-effective solutions.” Qwen 3.7 Flash · 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.
“notably high negative rate (27%) and is labeled as a "criticized challenger"” Mistral Small · negative prompt · hard negative
“I didn't pull a fresh official source here, so I'd want to verify current product positioning before making a strong recommendation.” GPT-5.4 mini · comparative prompt · soft negative
“it may require additional technical expertise to manage effectively, and limitations in support and ease of use” Claude Haiku 4.5 · negative prompt · soft negative
“the best process mining tools for a mid-market B2B company are generally considered to be Apromore, UiPath Process Mining, and ABBYY Timeline” Mistral Small · direct prompt · first choice
“The best process mining tool for a company with a limited budget is Apromore, as it is an open-source tool that offers a free Community Edition” Llama 4 Maverick · budget prompt · first choice
“Apromore stands out as the top open-source option with a free Community Edition, making it ideal for starting on a small budget” Mistral Small · 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.