Two of fourteen models named Amazon Advertising first on the direct prompt; one named Criteo. Amazon Advertising was named by eight of the fourteen models and Criteo by eight and Amazon Advertising carries 11 labels and Criteo 10, so the shares are not directly comparable.
By Amazon, Seattle, United States, founded 1994. Named in one category this edition.
Paris, France, founded 2005. Named in two 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 retail media platforms page.
| 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 |
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. Five of six in this category shown.
“Experts advise avoiding this *unless* you are a heavy volume seller with robust unit economics.” Qwen 3.7 Flash · negative prompt · hard negative
“Amazon, Walmart, Instacart, and other networks may count the same shoppers, causing duplicated reach and over-attributed conversions” Perplexity Sonar · negative prompt · soft negative
“Market position: Undisputed leader... Amazon Advertising dominates the American retail media space, grabbing ~75% of marketers’ dollars” Muse Glimmer 30B · comparative prompt · first choice
“I recommend starting with Amazon Advertising as your primary platform for running and managing retail media ads” Grok 4.20 · paraphrase prompt · first choice
“For most mid-market B2B product companies, Amazon Business Ads is the single best starting point” Gemini 3.5 Flash · direct prompt · first choice
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Five of five in this category shown.
“Criteo: 30% of labels were negative, with 10 out of 14 models giving it a hard negative rating.” Llama 4 Maverick · negative prompt · hard negative
“Criteo: also flagged for significant invalid traffic exposure” Kimi K2 · negative prompt · soft negative
“I'd recommend Criteo as the best starting point” Kimi K2 · direct prompt · first choice
“Criteo — *Best for Commerce AI & Off-Site Reach*” DeepSeek V4 Flash · direct prompt · alternative
“implement a platform like Criteo or AdLib” Qwen 3.7 Flash · direct 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.