Zero of twelve models named Convert first on the direct prompt; zero named GrowthBook. Convert was named by ten of the twelve models and GrowthBook by ten and Convert carries 17 labels and GrowthBook 26, 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 experimentation and personalization page.
Across every category in the September 2026 Edition, Convert and GrowthBook were named in the same answer twenty-five times, of the 53 answers naming Convert and the 71 naming GrowthBook. In those answers GrowthBook took the first choice three times and Convert three.
| 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. Three of four in this category shown.
“I would recommend Convert.com if you want a strong balance of reliability, privacy, and straightforward pricing” Perplexity Sonar · paraphrase prompt · first choice
“I would recommend Convert.com as the best A/B testing and personalization tool for a mid-sized B2B company” Llama 4 Maverick · paraphrase prompt · first choice
“Privacy-first (excellent GDPR), affordable (~$299+/month), up to 50 goals/test.” Grok 4.1 Fast · negative 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.
“But require devs (no visual editors), best if you have engineering resources.” Grok 4.1 Fast · budget prompt · soft negative
“the best overall choice is usually GrowthBook if you can self-host it, because it is open-source and "completely free"” Perplexity Sonar · budget prompt · first choice
“Open source + data ownership + cost control → GrowthBook” DeepSeek V4 Flash · comparative prompt · first choice
“Engineering-heavy, cost-conscious | $0 (self-hosted) + hosting | Open source, full control” Kimi K2 · scale 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.