One of fourteen models named Zendesk AI Agents first on the direct prompt; one named Workativ. Zendesk AI Agents was named by eleven of the fourteen models and Workativ by ten and Zendesk AI Agents carries 31 labels and Workativ 15, so the shares are not directly comparable.
Named in one category this edition.
Named in two 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 IT support agents page.
Across every category in the November 2026 Edition, Zendesk AI Agents and Workativ were named in the same answer fifteen times, of the 78 answers naming Zendesk AI Agents and the 43 naming Workativ. In those answers Workativ took the first choice three times and Zendesk AI Agents one.
| Model | Direct | Paraphrase | Comparative | Budget-constrained | Scale-constrained | Negative |
|---|---|---|---|---|---|---|
| Claude Haiku 4.5 | ||||||
| GPT-5.4 mini | ||||||
| Gemini 3.5 Flash | ||||||
| Perplexity Sonar | ||||||
| Grok 4.20 | ||||||
| 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. Six of eight in this category shown.
“still have a notable negative label share (14%) and are flagged by several AI models as problematic for IT support tasks” Mistral Small · negative prompt · soft negative
“Unlike competitors (such as NinjaOne, ConnectWise, or Zendesk) that charge per endpoint or per ticket” Gemini 3.5 Flash · budget prompt · soft negative
“tools like ServiceNow AI, Freshservice AI, or Zendesk AI when configured for full actions” Grok 4.20 · negative prompt · soft negative
“I would recommend Zendesk AI Agents or Freshdesk AI Agent as the top choices” Mistral Small · paraphrase prompt · first choice
“Freshservice with Freddy AI and Zendesk AI Agents are the top choices” Mistral Small · direct prompt · first choice
“Zendesk AI Agents — *Best Overall Choice*” MiniMax M2.5 · paraphrase prompt · first choice
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Six of six in this category shown.
“also recommended for teams that want to get started without a sales call, though their starting prices are higher” Mistral Small · budget prompt · soft negative
“starts around $349/month, so it is less suitable for very small budgets” Perplexity Sonar · budget prompt · soft negative
“Starts ~$349/month; ... Good for SMBs but higher entry than eesel.” Grok 4.20 · budget prompt · soft negative
“The best AI agent for IT support in a mid-market B2B company ... is Workativ.” Grok 4.20 · direct prompt · first choice
“If you want a quick, cheap, no-code pilot → Workativ is the most accessible.” DeepSeek V4 Flash · comparative prompt · alternative
“For those wanting a fast, no-code solution, Workativ is worth considering.” Mistral Small · direct 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.