Three of twelve models named Make first on the direct prompt; zero named Tray.ai. Make was named by twelve of the twelve models and Tray.ai by eight and Make carries 48 labels and Tray.ai 23, so the shares are not directly comparable.
Named in four categories this edition.
Named in one category 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 workflow automation and ipaas page.
Across every category in the September 2026 Edition, Make and Tray.ai were named in the same answer thirty-five times, of the 151 answers naming Make and the 44 naming Tray.ai. In those answers Tray.ai took the first choice three times and Make eight.
| 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. Six of eight in this category shown.
“powerful and often better value, but it is still best suited to app-to-app automation; if you need strong governance ... it may not be the right fit” Perplexity Sonar · negative prompt · soft negative
“only for lightweight, low-volume, non-critical automations; they're not designed for complex, high-volume B2B data integration” DeepSeek V4 Flash · paraphrase prompt · soft negative
“Strong value for mid-complexity workflows... Avoid for long-running processes or data-sensitive industries.” DeepSeek V4 Flash · negative prompt · soft negative
“Choose Make if you are cost-conscious, manage complex agency workflows, or need to process hundreds of records at once cheaply.” Qwen 3.7 Flash · comparative prompt · first choice
“Complex Logic on a Budget | Make | Allows loops, deep branching, and data arrays at a fraction of Zapier's cost.” Gemini 3.5 Flash · comparative prompt · first choice
“4. Make (Best Value) ... For most small businesses with limited budgets, Make or n8n offer the best balance” GLM 4.7 FlashX · budget prompt · first choice
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Six of seven in this category shown.
“Avoid MuleSoft, Workato, and Tray.io (unless you are a major enterprise)” Gemini 3.5 Flash · negative prompt · hard negative
“powerful, but often overkill for smaller teams, and pricing/implementation complexity can be a major caution” Perplexity Sonar · negative prompt · soft negative
“Entirely quote-based pricing with no self-serve option—estimated $595+/month starting point” Kimi K2 · negative prompt · soft negative
“Tier 1 Middleware platforms (like Workato, Tray.io, or Microsoft Fabric)” Qwen 3.7 Flash · scale prompt · first choice
“Default choice: Workato or Tray.ai” Kimi K2 · scale prompt · first choice
“Choose Workato/Tray.io if you are a large company connecting CRMs to ERPs, require audit trails” Qwen 3.7 Flash · 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.