One of fourteen models named Starburst Galaxy first on the direct prompt; zero named Trino. Starburst Galaxy was named by nine of the fourteen models and Trino by eleven and Starburst Galaxy carries 14 labels and Trino 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 data virtualization page.
Across every category in the November 2026 Edition, Starburst Galaxy and Trino were named in the same answer twenty-one times, of the 62 answers naming Starburst Galaxy and the 57 naming Trino. In those answers Trino took the first choice four times and Starburst Galaxy seven.
| 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. Four of five in this category shown.
“Starburst Galaxy at 2% first-choice share with 36% negative rate, 11 labels, “criticized challenger”” Muse Glimmer 30B · negative prompt · soft negative
“Appears to be a leading choice with approximately 17% first-choice selection rate among AI models for small B2B companies with budget considerations” MiniMax M2.5 · budget prompt · first choice
“Starburst Galaxy’s free plan is an excellent starting point—no infrastructure to manage” GLM 4.7 FlashX · budget prompt · first choice
“I recommend starting with CData Virtuality or Starburst Galaxy” Kimi K2 · direct prompt · first choice
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Five of six in this category shown.
“Trino’s documentation says its default access control allows all authenticated users, so authorization must be deliberately configured.” GPT-6 Luna · scale prompt · soft negative
“Avoid hosting self-managed Trino, Presto, or Apache Drill clusters unless you have dedicated platform engineers.” Gemini 3.5 Flash · paraphrase prompt · soft negative
“Trino is the best choice if you have even modest technical talent on your team — it's completely free, proven, and widely used” DeepSeek V4 Flash · budget prompt · first choice
“Best starting point: Trino is widely recommended as "the open-source default and the one most teams should try first."” Kimi K2 · budget prompt · first choice
“If you want the most active open-source community and pure SQL federation: start with Trino. It's free, well documented” Muse Glimmer 30B · budget prompt · first choice
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.