Seven of fourteen models named Rippling first on the direct prompt; zero named Paychex Flex. Rippling was named by thirteen of the fourteen models and Paychex Flex by fourteen and Rippling carries 43 labels and Paychex Flex 35, so the shares are not directly comparable.
Named in twenty-nine 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 payroll software 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.
No label in this category carried a quote.
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Four of four in this category shown.
“Hidden fees — documented early termination fees of $1,500–$3,000 ... Missed payrolls and tax filing errors” DeepSeek V4 Flash · negative prompt · hard negative
“Recent class-action lawsuit over a 2024 data breach exposing names/SSNs due to negligence” Grok 4.1 Fast · negative prompt · hard negative
“I'd recommend ADP Workforce Now or Paychex Flex as top choices” Grok 4.1 Fast · paraphrase prompt · first choice
“Modular, strong payroll support, multi-state compliance, good for small to midsize businesses.” GLM 4.7 FlashX · comparative 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.