Twelve of fourteen models named Amazon RDS first on the direct prompt; zero named Supabase. Amazon RDS was named by fourteen of the fourteen models and Supabase by twelve and Amazon RDS carries 72 labels and Supabase 24, so the shares are not directly comparable.
Named in one category this edition.
Named in three 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 managed relational databases page.
Across every category in the November 2026 Edition, Amazon RDS and Supabase were named in the same answer seventy-nine times, of the 200 answers naming Amazon RDS and the 95 naming Supabase. In those answers Supabase took the first choice twenty-six times and Amazon RDS twenty-one.
| 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.
“Some models explicitly recommend avoiding RDS for production core systems unless absolutely necessary.” Muse Glimmer 30B · negative prompt · hard negative
“Some models explicitly recommend avoiding RDS for production core systems unless absolutely necessary.” Llama 4 Maverick · negative prompt · hard negative
“AWS RDS – hidden markup, vendor lock‑in, limited operational control.” GLM 4.7 FlashX · negative prompt · hard negative
“AWS RDS or Azure SQL Database are solid default choices due to their maturity, reliability, compliance certifications, and strong support ecosystems” Claude Haiku 4.5 · paraphrase prompt · first choice
“Amazon's Relational Database Service offers a free tier for the first 12 months... AWS Lightsail is also budget-friendly for smaller workloads.” Claude Haiku 4.5 · budget prompt · first choice
“Broad engine choice and familiar database behavior... You're already on AWS, want a conventional engine, or need Oracle, SQL Server, or Db2.” GPT-6 Luna · comparative prompt · first choice
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Six of seven in this category shown.
“can be attractive depending on your architecture, but I'd be more cautious for core production systems” GPT-5.4 mini · paraphrase prompt · soft negative
“These are rising for mid-sized B2B but less "enterprise battle-tested" than the big three.” Grok 4.20 · paraphrase prompt · soft negative
“Supabase, for example, pauses free projects after inactivity” Perplexity Sonar · negative prompt · soft negative
“Go with Supabase or Neon if you are building a new web app, want a free tier that lasts months” Qwen 3.7 Flash · budget prompt · first choice
“Supabase (PostgreSQL) and Google Cloud SQL (PostgreSQL or MySQL) are your best bets” GLM 4.7 FlashX · budget prompt · first choice
“If you're just starting out: Use Neon (free tier) or Supabase (free tier).” Kimi K2 · 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.