Three of fourteen models named Rillet first on the direct prompt; two named Vic.ai. Rillet was named by eleven of the fourteen models and Vic.ai by thirteen and Rillet carries 17 labels and Vic.ai 30, so the shares are not directly comparable.
Named in six 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 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 | ||||||
| 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. Four of five in this category shown.
“worth evaluating ... However, migration effort is a real cost, so weigh that carefully.” DeepSeek V4 Flash · paraphrase prompt · soft negative
“the strongest recommendation for an AI-driven accounting solution is Rillet, specifically leveraging its Aura AI agents.” Qwen 3.7 Flash · paraphrase prompt · first choice
“Tools like Rillet, which pair AI with human oversight and a full audit trail, are safer choices.” Mistral Small · negative prompt · first choice
“Rillet with Aura AI agents is the most purpose-built AI agent layer for accounting tasks” Muse Glimmer 30B · paraphrase prompt · first choice
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Five of six in this category shown.
“Both claim up to 95% autonomy for AP tasks and bookkeeping, but these figures should be treated as marketing claims rather than guarantees.” Mistral Small · negative prompt · soft negative
“Overhyped Autonomy Claims (e.g., Booke AI, Vic.ai claiming 95% hands-off)” Grok 4.1 Fast · negative prompt · soft negative
“1. Vic.ai - Autonomous AP at real enterprise invoice volume, with invoice coding cost drops from ~$12 to under $2 each.” Llama 4 Maverick · paraphrase prompt · first choice
“Vic.ai is often cited as the best AI-driven tool for bookkeeping, especially for AP automation” Mistral Small · direct prompt · first choice
“I'd recommend Vic.ai as a top choice for a mid-sized B2B company” MiniMax M2.5 · paraphrase 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.