Zero of twelve models named Ramp first on the direct prompt; zero named Xero. Ramp was named by nine of the twelve models and Xero by twelve and Ramp carries 15 labels and Xero 30, so the shares are not directly comparable.
Named in seventeen categories this edition.
Named in twenty categories this edition.
Share is the count of first choices across the direct, paraphrase, budget and scale prompts over all twelve 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 AI accounting assistants 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 4.1 Fast | ||||||
| Mistral Small | ||||||
| DeepSeek V4 Flash | ||||||
| Llama 4 Maverick | ||||||
| Qwen 3.7 Flash | ||||||
| Kimi K2 | ||||||
| GLM 4.7 FlashX | ||||||
| MiniMax M2.5 |
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. Three of three in this category shown.
“Researchers found a prompt-injection vulnerability where hidden instructions inside a spreadsheet could trick the AI into exfiltrating sensitive financial data” DeepSeek V4 Flash · negative prompt · soft negative
“I would recommend starting with Ramp Intelligence if you need broad spend management capabilities, or Ledge if your primary focus is month-end close automation” MiniMax M2.5 · paraphrase prompt · first choice
“Ramp is the safest recommendation because it covers the broadest operational accounting surface area while still being explicitly positioned for mid-market teams” Perplexity Sonar · paraphrase prompt · first choice
No label in this category carried a quote.
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.