Four of fourteen models named Millie first on the direct prompt; three named Groundswell. Millie was named by thirteen of the fourteen models and Groundswell by eleven and Millie carries 33 labels and Groundswell 20, 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 employee giving and volunteering page.
Across every category in the October 2026 Edition, Millie and Groundswell were named in the same answer thirty times, of the 85 answers naming Millie and the 86 naming Groundswell. In those answers Groundswell took the first choice three times and Millie five.
| Model | DirectMI | ParaphraseMI | ComparativeMI | Budget-constrainedMI | Scale-constrainedMI | NegativeMI |
|---|---|---|---|---|---|---|
| Claude Haiku 4.5 | MI | MI | MI | |||
| GPT-5.4 mini | MI | |||||
| Gemini 3.5 Flash | MI | MI | MI | MI | ||
| Perplexity Sonar | MI | MI | ||||
| Grok 4.1 Fast | MI | MI | ||||
| Mistral Small | MI | MI | MI | |||
| DeepSeek V4 Flash | MI | MI | MI | |||
| Llama 4 Maverick | MI | |||||
| Qwen 3.7 Flash | MI | MI | ||||
| Kimi K2 | MI | MI | MI | |||
| GLM 4.7 FlashX | ||||||
| MiniMax M2.5 | MI | MI | MI | |||
| GPT-6 Luna | MI | MI | MI | |||
| Muse Glimmer 30B | MI |
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. Four of five in this category shown.
“its volunteering component is relatively basic and may not meet the needs of organizations seeking robust volunteer management” Mistral Small · negative prompt · soft negative
“I'd suggest starting with Millie if you're already on Slack, as it's designed specifically for smaller businesses with cost in mind” MiniMax M2.5 · budget prompt · first choice
“look into modern, employee-experience-first platforms such as Deed, Groundswell, Uncommon Giving, or Millie” Gemini 3.5 Flash · negative prompt · first choice
“If you want the single best default choice, I'd start with Millie for a mid-market B2B company” Perplexity Sonar · direct prompt · first choice
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Four of five in this category shown.
“Platforms like Groundswell or Selflessly (~$2–$4.50+/user/month or $4,500+/year) add giving but exceed tight budgets.” Grok 4.1 Fast · budget prompt · soft negative
“Groundswell: A modern, mobile-first platform built specifically to make enterprise-grade giving and DAFs accessible to mid-market companies. Very low administrative burden.” Gemini 3.5 Flash · scale prompt · first choice
“look into modern, employee-experience-first platforms such as Deed, Groundswell, Uncommon Giving, or Millie” Gemini 3.5 Flash · negative prompt · first choice
“positioned specifically as a Benevity alternative, addressing fragmentation and disbursement concerns” DeepSeek V4 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.