Groundswell vs Deed
Three of fourteen models named Groundswell first on the direct prompt; zero named Deed. Groundswell was named by eleven of the fourteen models and Deed by eight and Groundswell carries 20 labels and Deed 16, so the shares are not directly comparable.
Named in one category this edition.
Deed
accepted challengerNamed 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.
By framing
GroundswellFirst choices, of fourteen modelsDeedAcross every category in the October 2026 Edition, Groundswell and Deed were named in the same answer twelve times, of the 86 answers naming Groundswell and the 38 naming Deed. In those answers Deed took the first choice zero times and Groundswell two.
Every model, every framing
| Model | DirectDE | ParaphraseDE | ComparativeDE | Budget-constrainedDE | Scale-constrainedDE | NegativeDE |
|---|---|---|---|---|---|---|
| Claude Haiku 4.5 | | DE | | DE | ||
| GPT-5.4 mini | DE | | ||||
| Gemini 3.5 Flash | DE | DE | DE | DE | ||
| Perplexity Sonar | DE | DE | ||||
| Grok 4.1 Fast | | |||||
| Mistral Small | ||||||
| DeepSeek V4 Flash | | | | |||
| Llama 4 Maverick | DE | |||||
| Qwen 3.7 Flash | | | ||||
| Kimi K2 | | DE | DE | |||
| GLM 4.7 FlashX | | |||||
| MiniMax M2.5 | ||||||
| GPT-6 Luna | ||||||
| Muse Glimmer 30B | DE |
GroundswellDE Deed first choice named as an alternative argued againstblank: not namedEach cell is one answer, Groundswell on the left and Deed on the right.The direct prompt
Groundswell first, Deed an alternative
3 of 14 modelsDeed was named in the answer but not as the choice, or not at all.Neither was the first choice, one was named
1 of 14 modelsThe answer put something else first and named one of the two as an alternative.Neither was named
10 of 14 modelsThe answer made no first choice from these two in this category.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.
By buyer segment
Groundswell2%#5 of 11What the models said about Groundswell
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
What the models said about Deed
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Five of six in this category shown.
“Benevity, YourCause, and Deed are specifically called out for issues such as long distribution timelines, limited mobile support, or heavy administrative burden” Perplexity Sonar · negative prompt · hard negative
“the platform leaves a ton of administrative paperwork for HR staffers, and customer service can also be slow to respond” Claude Haiku 4.5 · negative prompt · soft negative
“look into modern, employee-experience-first platforms such as Deed, Groundswell, Uncommon Giving, or Millie” Gemini 3.5 Flash · negative prompt · first choice
“I'd generally recommend Deed or Millie” GPT-5.4 mini · paraphrase prompt · first choice
“enterprise social impact software platform designed to make workplace giving and volunteering engaging and easy for employees” Llama 4 Maverick · paraphrase 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.