One of fourteen models named Rippling Spend first on the direct prompt; one named Brex. Rippling Spend was named by ten of the fourteen models and Brex by fourteen and Rippling Spend carries 15 labels and Brex 37, so the shares are not directly comparable.
Named in five categories this edition.
Named in twelve 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 expense management 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. Two of two in this category shown.
“The Best "All-in-One" Platform: Rippling ... Rippling has become the preferred choice for mid-market companies” Qwen 3.7 Flash · direct prompt · first choice
“Navan / Rippling Spend is the safest default from the mid-market trust data” Muse Glimmer 30B · paraphrase prompt · first choice
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. One of one in this category shown.
“Some AI models and budget-conscious users advise avoiding Brex's standard per-user plans due to their pricing structure” Mistral Small · negative prompt · hard negative
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.