ReferralCandy vs Ambassador
Zero of fourteen models named ReferralCandy first on the direct prompt; one named Ambassador. ReferralCandy was named by fourteen of the fourteen models and Ambassador by eleven and ReferralCandy carries 46 labels and Ambassador 19, so the shares are not directly comparable.
Named in three categories 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 referral and partner programs page.
By framing
ReferralCandyFirst choices, of fourteen modelsAmbassador
Across every category in the November 2026 Edition, ReferralCandy and Ambassador were named in the same answer forty-two times, of the 204 answers naming ReferralCandy and the 108 naming Ambassador. In those answers Ambassador took the first choice two times and ReferralCandy one.
Every model, every framing
| Model | Direct | Paraphrase | Comparative | Budget-constrained | Scale-constrained | Negative |
|---|---|---|---|---|---|---|
| Claude Haiku 4.5 | | | | |||
| GPT-5.4 mini | | | ||||
| Gemini 3.5 Flash | | | | |||
| Perplexity Sonar | | | | | ||
| Grok 4.20 | | | | | | |
| Mistral Small | | | ||||
| DeepSeek V4 Flash | | | | |||
| Llama 4 Maverick | | | ||||
| Qwen 3.7 Flash | | | | | ||
| Kimi K2 | | | | |||
| GLM 4.7 FlashX | | | ||||
| MiniMax M2.5 | | | | |||
| GPT-6 Luna | | | | |||
| Muse Glimmer 30B | | | | | |
ReferralCandy Ambassador first choice named as an alternative argued againstblank: not namedEach cell is one answer, ReferralCandy on the left and Ambassador on the right.The direct prompt
Ambassador first, ReferralCandy not the choice
1 of 14 modelsReferralCandy was named in the answer but not as the choice, or not at all.Neither was the first choice, one was named
5 of 14 modelsThe answer put something else first and named one of the two as an alternative.Neither was named
8 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
ReferralCandy5%#4 of 9Ambassador0%#– of 9ReferralCandy6%#6 of 13Ambassador2%#8 of 13Ambassador16%#1 of 14ReferralCandy0%#14 of 14What the models said about ReferralCandy
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Six of seven in this category shown.
“Why to Avoid: If you sell high-ticket items (e.g., $1,000+ courses or furniture), paying a % commission can be incredibly expensive” Qwen 3.7 Flash · negative prompt · hard negative
“Avoid ReferralCandy (despite its popularity) if your margins are very thin” Qwen 3.7 Flash · budget prompt · hard negative
“Criticized for being consumer-first and unsuitable for B2B programs” Mistral Small · negative prompt · hard negative
“ReferralCandy is the "plug-and-play" standard for online stores... Extremely low maintenance; seamless dashboard for tracking payouts” Qwen 3.7 Flash · comparative prompt · first choice
“Shopify store and want the absolute lowest monthly cost: ReferralCandy $9/mo + success fee, or Joy free plan.” Muse Glimmer 30B · budget prompt · first choice
“For Small E-commerce: Start with ReferralCandy or Friendbuy—quick ROI with minimal effort.” Grok 4.20 · comparative prompt · first choice
What the models said about Ambassador
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Three of three in this category shown.
“Ambassador (lock-in/pricing practices)” Kimi K2 · negative prompt · hard negative
“often seen as more complex/expensive and scores lower on ease-of-use compared to Referral Factory” Grok 4.20 · direct prompt · soft negative
“Ambassador or Referral Factory would be the strongest choices” MiniMax M2.5 · direct 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.