Four of fourteen models named Freshservice with Freddy AI first on the direct prompt; zero named Intercom Fin. Freshservice with Freddy AI was named by eight of the fourteen models and Intercom Fin by nine and Freshservice with Freddy AI carries 10 labels and Intercom Fin 18, 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.
| Model | DirectFW | ParaphraseFW | ComparativeFW | Budget-constrainedFW | Scale-constrainedFW | NegativeFW |
|---|---|---|---|---|---|---|
| Claude Haiku 4.5 | ||||||
| GPT-5.4 mini | FW | |||||
| Gemini 3.5 Flash | ||||||
| Perplexity Sonar | FW | |||||
| Grok 4.20 | ||||||
| Mistral Small | FW | |||||
| DeepSeek V4 Flash | FW | |||||
| Llama 4 Maverick | FW | |||||
| Qwen 3.7 Flash | ||||||
| Kimi K2 | FW | |||||
| GLM 4.7 FlashX | ||||||
| MiniMax M2.5 | ||||||
| GPT-6 Luna | FW | |||||
| Muse Glimmer 30B | FW | FW |
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. Three of four in this category shown.
“Freshservice with Freddy AI is considered one of the top AI IT support agents, with a 9% share of first choices across various models.” Llama 4 Maverick · comparative prompt · first choice
“my default pick for a mid-market company starting fresh would be Freshservice with Freddy AI” GPT-6 Luna · direct prompt · first choice
“Freshservice with Freddy AI and Zendesk AI Agents are the top choices” Mistral Small · direct prompt · first choice
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Four of five in this category shown.
“Avoid vendors charging per-resolution or per-ticket AI fees (e.g., Intercom Fin at ~$0.99 per resolution)” Gemini 3.5 Flash · budget prompt · hard negative
“Intercom Fin is the strongest pure resolver in a 2026 B2B-weighted scoring” Muse Glimmer 30B · paraphrase prompt · first choice
“Intercom Fin—a strong resolver with broad channel coverage, but outcome-based pricing should be modeled carefully.” Perplexity Sonar · paraphrase prompt · alternative
“Best AI-First Resolution Rate ... Less suited for internal IT service management (ITSM) workflows.” DeepSeek V4 Flash · paraphrase 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.