Zero of fourteen models named Numeric first on the direct prompt; one named Prophix. Numeric was named by thirteen of the fourteen models and Prophix by nine and Numeric carries 44 labels and Prophix 17, so the shares are not directly comparable.
Named in four categories this edition.
Named in nine 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 financial close 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 4.1 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 four in this category shown.
“Noted as becoming expensive/unpredictable at scale (e.g., $360K+/month for thousands of users).” Grok 4.1 Fast · negative prompt · soft negative
“Smaller user community; fewer integrations compared with FloQast/Workiva. Still evolving” MiniMax M2.5 · direct prompt · soft negative
“Numeric – Can become expensive and unpredictable with thousands of users.” Mistral Small · negative prompt · soft negative
“Choose Numeric if you are a modern, fast-growing company that wants to leverage AI to automate transactional matching” Gemini 3.5 Flash · comparative 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.