Artisan vs Agent Frank
Two of twelve models named Artisan first on the direct prompt; zero named Agent Frank. Artisan was named by twelve of the twelve models and Agent Frank by eight and Artisan carries 36 labels and Agent Frank 10, 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 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 AI SDR agents page.
By framing
ArtisanFirst choices, of twelve modelsAgent Frank
Across every category in the September 2026 Edition, Artisan and Agent Frank were named in the same answer fourteen times, of the 102 answers naming Artisan and the 28 naming Agent Frank. In those answers Agent Frank took the first choice one time and Artisan one.
Every model, every framing
| 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 | | | | |
Artisan Agent Frank first choice named as an alternative argued againstblank: not namedEach cell is one answer, Artisan on the left and Agent Frank on the right.The direct prompt
Artisan first, Agent Frank not the choice
2 of 12 modelsAgent Frank was named in the answer but not as the choice, or not at all.Neither was the first choice, one was named
3 of 12 modelsThe answer put something else first and named one of the two as an alternative.Neither was named
7 of 12 modelsThe answer made no first choice from these two in this category.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.
By buyer segment
Agent Frank9%#3 of 8Artisan0%#7 of 8Artisan13%#2 of 11Agent Frank2%#7 of 11Artisan7%#6 of 11Agent Frank—not namedWhat the models said about Artisan
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Six of eight in this category shown.
“Avoid fully autonomous AI SDRs with annual lock-in contracts, no trials, and documented quality problems (Artisan, 11x.ai especially)” DeepSeek V4 Flash · negative prompt · hard negative
“Artisan - LinkedIn restricted their automated outreach in early 2026... G2 rating of 3.8/5 (lowest among reviewed platforms)” MiniMax M2.5 · negative prompt · hard negative
“Artisan was temporarily banned by LinkedIn in late 2025/early 2026 due to platform compliance and data-scraping violations.” Gemini 3.5 Flash · negative prompt · hard negative
“unless your team specifically wants an AI SDR that books meetings more autonomously, in which case Artisan is the better fit” Perplexity Sonar · paraphrase prompt · first choice
“Artisan"s AI agent, Ava, is highly regarded for mid-market companies that want a fully autonomous out-of-the-box solution.” Gemini 3.5 Flash · direct prompt · first choice
“or Artisan/Ava if you want more autonomous outbound prospecting with built-in contact data.” Claude Haiku 4.5 · paraphrase prompt · first choice
What the models said about Agent Frank
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Three of four in this category shown.
“Top Pick: Agent Frank (Salesforge) - $499/month” GLM 4.7 FlashX · budget prompt · first choice
“If you want a highly scalable, fully autonomous email worker: Go with Agent Frank at $499/month.” Gemini 3.5 Flash · budget prompt · alternative
“Agent Frank at $416/mo (on annual billing) is the cheapest turnkey solution with proven ROI” Qwen 3.7 Flash · budget 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.