Five of fourteen models named Artisan Ava first on the direct prompt; zero named Qualified Piper. Artisan Ava was named by fourteen of the fourteen models and Qualified Piper by eight and Artisan Ava carries 48 labels and Qualified Piper 13, so the shares are not directly comparable.
Named in one category 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 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 SDR agents page.
Across every category in the November 2026 Edition, Artisan Ava and Qualified Piper were named in the same answer thirty times, of the 143 answers naming Artisan Ava and the 41 naming Qualified Piper. In those answers Qualified Piper took the first choice zero times and Artisan Ava ten.
| 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.
“Be cautious about quality and value. A review describes it as having the lowest reported G2 score among the compared platforms” Perplexity Sonar · negative prompt · hard negative
“Artisan: Marketed autonomous SDR replacement but saw significant customer cohorts revert to human SDRs using AI as a tool.” Llama 4 Maverick · negative prompt · hard negative
“Vendors repeatedly cited for poor outcomes ... "Artisan reviewers mention generic, recognizably AI emails ..."” Muse Glimmer 30B · negative prompt · hard negative
“the data strongly points to Apollo.io and Artisan (Ava) as the top picks for mid-market B2B companies” DeepSeek V4 Flash · direct prompt · first choice
“Artisan Ava if you want bundled contacts + AI SDR at predictable pricing” MiniMax M2.5 · direct prompt · first choice
“Recommendation for a typical mid-sized B2B company: start with Artisan Ava.” Muse Glimmer 30B · paraphrase prompt · first choice
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Three of four in this category shown.
“If you want the lowest cost to start, pick Qualified.” GPT-5.4 mini · budget prompt · first choice
“If by "prospects" you mainly mean engaging people who visit your website, rather than cold outbound, I'd look at Qualified instead.” GPT-6 Luna · paraphrase prompt · alternative
“Choose Qualified (Piper) if your biggest bottleneck is capturing, qualifying, and converting visitors” Gemini 3.5 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.