Ten 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 nine and Amazon RDS carries 70 labels and Supabase 18, so the shares are not directly comparable.
Named in two categories 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 October 2026 Edition, Amazon RDS and Supabase were named in the same answer fifty-three times, of the 189 answers naming Amazon RDS and the 82 naming Supabase. In those answers Supabase took the first choice nineteen times and Amazon RDS 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 4.1 Fast | ||||||
| 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.” Mistral Small · negative prompt · hard negative
“are cautious with AWS RDS SQL Server for point-in-time restore expectations and with any RDS engine for globally distributed strong-consistency writes” Muse Glimmer 30B · negative prompt · soft negative
“It is widely used and legitimate, but multiple sources note that it can carry premium instance pricing, hidden ancillary costs” Perplexity Sonar · negative prompt · soft negative
“Amazon RDS, for example, supports MySQL, PostgreSQL, MariaDB, SQL Server, Oracle, and Amazon Aurora, and automates provisioning, patching, backups, and failover.” Llama 4 Maverick · comparative prompt · first choice
“Pick AWS RDS/Aurora for broadest engine breadth and ecosystem maturity, and for cloud-native Aurora performance with MySQL/PostgreSQL compatibility.” Muse Glimmer 30B · comparative prompt · first choice
“The top managed relational database services are Amazon RDS, Google Cloud SQL, Azure SQL Database, and Oracle Autonomous Database” Perplexity Sonar · comparative prompt · first choice
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Four of four in this category shown.
“you must be cautious about adopting it for long-term, enterprise-scale relational workloads” Gemini 3.5 Flash · negative prompt · soft negative
“If you're just starting and want a free tier that doesn't expire, Supabase or Neon are excellent.” GLM 4.7 FlashX · budget prompt · first choice
“Supabase or Neon (both serverless PostgreSQL) stand out as the best managed relational database services” Grok 4.1 Fast · budget prompt · first choice
“My overall pick: For most small companies with limited budgets, Supabase is the best value” DeepSeek V4 Flash · 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.