{"slug": "i-asked-6-ais-to-pick-a-database-430-times-postgres-wins-oracle-is-invisible", "title": "I asked 6 AIs to pick a database, 430 times – Postgres wins, Oracle is invisible", "summary": "PostgreSQL is the database most often recommended by six AI assistants across 12 use cases, with an average recommendation rate of 58%, according to an independent measurement by AI responses. MySQL (37%), SQLite (33%), MongoDB (33%), and Supabase (33%) follow, while Oracle Database appears in only 1% of responses, making it effectively invisible. The analysis of 430 responses found that in 4 of 12 use cases, the recommended tool varies by assistant, meaning the choice depends on both the stated need and the AI used.", "body_md": "AI responses, an independent measurement\n\n# Which database do AI assistants recommend\n\n## PostgreSQL leads overall, but the winner changes with the need.\n\nAcross the 12 situations tested, PostgreSQL is the tool most often recommended by the 6 assistants. But in 4 of 12 situations, the tool highlighted varies by AI. The choice therefore depends as much on the stated need as on the assistant used.\n\n**58%**\n\n**37%**\n\n**33%**\n\n**4/12** use cases where AIs disagree\n\n**430** responses actually analyzed\n\n##\nThe panel**The 14 compared tools**\nView panel\n\n## Which tools do AIs recommend most often? [¶](#part-de-voix)\n\nThe average recommendation rate is calculated across all tested situations, weighted equally. One assistant may recommend several tools, so these percentages are not expected to add up to 100%.\n\n| # | Tool | Average recommendation rate | |\n|---|---|---|---|\n| 1 | PostgreSQL | 58% | |\n| 2 | MySQL | 37% | |\n| 3 | SQLite | 33% | |\n| 4 | MongoDB | 33% | |\n| 5 | Supabase | 33% | |\n| 6 | CockroachDB | 27% | |\n| 7 | Redis | 24% | |\n| 8 | DynamoDB | 22% | |\n| 9 | Firebase Firestore | 12% | |\n| 10 | ClickHouse | 12% | |\n| 11 | DuckDB | 3% | |\n| 12 | MariaDB | 2% | |\n| 13 | Microsoft SQL Server | 1% | |\n| 14 | Oracle Database | 1% |\n\n## The tool each model spontaneously surfaces [¶](#par-modele)\n\nUse case by use case, the tool each model most often puts first (every use case counts the same, chatty or not).\n\nTool most often highlighted by each assistant:\n**PostgreSQL** (5) · **CockroachDB** (1)\n\n## For the same use case, a different dominant tool depending on the model [¶](#divergences)\n\n## Which use cases AIs associate with which tool [¶](#terrains)\n\nFor each cell, the percentage shows the share of responses recommending the tool. Select a dot for details. ‘n’ is the number of responses analyzed; results based on few responses are indicative.\n\n↔ Swipe the matrix to explore use cases.\n\n| Tool | Database for a SaaS startup MVP | Database for a side project | First database for a beginner learning backend development | Database for a mobile app backend | Database for analytics and reporting | Database for a high-traffic app at scale | Database for an enterprise app with strict compliance | Database for an e-commerce store | Database for a real-time collaborative app | Database for an AI app with vector search (RAG) | Embedded or local-first database for a desktop app | Database for a serverless or edge deployment |\n|---|---|---|---|---|---|---|---|---|---|---|---|---|\n| ClickHouse | ||||||||||||\n| CockroachDB | ||||||||||||\n| DuckDB | ||||||||||||\n| DynamoDB | ||||||||||||\n| Firebase Firestore | ||||||||||||\n| MariaDB | ||||||||||||\n| Microsoft SQL Server | ||||||||||||\n| MongoDB | ||||||||||||\n| MySQL | ||||||||||||\n| Oracle Database | ||||||||||||\n| PostgreSQL | ||||||||||||\n| Redis | ||||||||||||\n| SQLite | ||||||||||||\n| Supabase |\n\nClick a dot to show the detail of an association.\n\n[Your tool ranks poorly, or is missing? Submit it for the next wave →](#proposer)\n\n[Are you a brand? See what AI says about you →](/en/mesurer)\n\n## Why do AIs recommend each tool? [¶](#pourquoi)\n\nThe main argument the models invoke for each tool, the price they quote, and the caveat they attach.\n\n*×7*\n\n*×3*\n\n*×38*\n\n*×8*\n\n*×7*\n\n*×4*\n\n*×2*\n\n*×25*\n\n*×5*\n\n*×5*\n\n*×3*\n\n*×15*\n\n*×2*\n\n*×16*\n\n*×9*\n\n*×7*\n\n*×7*\n\n*×18*\n\n*×11*\n\n*×8*\n\n*×6*\n\n*×21*\n\n*×19*\n\n*×12*\n\n*×11*\n\n*×13*\n\n*×7*\n\n*×4*\n\n*×4*\n\n*×49*\n\n*×4*\n\n*×2*\n\n*×2*\n\n*×19*\n\n*×8*\n\n*×6*\n\n*×3*\n\n## Which assistants give a clear recommendation? [¶](#prescription)\n\nShare of answers where the model commits to one tool, vs “it depends…”, vs doesn't commit.\n\n*n=70*63 37\n\n*n=72*54 46\n\n*n=72*53 42 6\n\n*n=72*51 47 1\n\n*n=72*39 58 3\n\n*n=72*39 61\n\n## The same need, a different profile, a different tool [¶](#profils)\n\nFor each buyer profile, the tools the models surface most (existing answers sliced by profile).\n\n*n=30*\n\n- ClickHouse97%\n- PostgreSQL33%\n- MySQL27%\n\n**alternative**\n\n*n=24*\n\n- PostgreSQL21%\n- Redis17%\n- MySQL12%\n\n**alternative**\n\n*n=24*\n\n- Supabase96%\n- PostgreSQL46%\n- Firebase Firestore42%\n\n**alternative**\n\n*n=23*\n\n- MySQL87%\n- PostgreSQL83%\n- MongoDB70%\n\n**alternative**\n\n*n=18*\n\n- PostgreSQL83%\n- CockroachDB67%\n- MongoDB44%\n\n**alternative**\n\n*n=18*\n\n- Redis89%\n- DynamoDB78%\n- CockroachDB61%\n\n**alternative**\n\n## Other tools that appeared spontaneously [¶](#hors-panel)\n\nComparable tools the models cited spontaneously, beyond the tracked panel: worth watching (or adding to the comparison).\n\n## How do AIs present each tool? [¶](#tonalite)\n\nBreakdown of favorable / neutral / critical verified mentions. Click a tool for a favorable and a critical verbatim.\n\n## How it is measured, and what it is not [¶](#methode)\n\n### What we measure\n\n*· claude-sonnet-5*\n\n*· deepseek-v4-pro*\n\n*· gemini-3.5-flash*\n\n*· mistral-medium-3-5*\n\n*· gpt-5.2-chat*\n\n*· grok-4.3*\n\n430 responses · 6 models · 12 use cases · 14 tools · query cost $5.31\n\nEach question asks for advice without offering a list of tools. We measure the tools the assistant chooses to mention spontaneously, then how it presents them.\n\n### What these results do not prove\n\n- Not a ranking of the tools' actual quality.\n- Not a feature or pricing comparison.\n- We measure model behavior, not the truth. Low-n rates are indicative.\n\n### To cite this page\n\n“According to the Opinion Radar observatory dated July 20, 2026, PostgreSQL has the highest average recommendation rate in the tested situations (58%), ahead of MySQL (37%).”\n\nReference link: this page (public methodology included). Attribute the claims to the AI models, never to the tools themselves.\n\n### Ask the question yourself\n\nYou can reuse these questions to check the result. AI responses may nevertheless vary between attempts and change over time.\n\n### Your tool isn't measured, or ranks poorly?\n\nSubmit it: it joins the queue for the next wave and will be measured under the same conditions as the panel.\n\n### Discover what AIs recommend, and why\n\nAre you a brand or a vendor? Measure precisely where AIs mention you (or don't) and why.\n\n[Measure my tool →](/en/mesurer)", "url": "https://wpnews.pro/news/i-asked-6-ais-to-pick-a-database-430-times-postgres-wins-oracle-is-invisible", "canonical_source": "https://www.opinion-radar.com/o/which-database-do-ai-assistants-recommend-0d7fb0?lang=en", "published_at": "2026-07-21 13:02:30+00:00", "updated_at": "2026-07-21 13:13:00.404014+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-products", "ai-tools", "large-language-models"], "entities": ["PostgreSQL", "MySQL", "SQLite", "MongoDB", "Supabase", "CockroachDB", "Redis", "Oracle Database"], "alternates": {"html": "https://wpnews.pro/news/i-asked-6-ais-to-pick-a-database-430-times-postgres-wins-oracle-is-invisible", "markdown": "https://wpnews.pro/news/i-asked-6-ais-to-pick-a-database-430-times-postgres-wins-oracle-is-invisible.md", "text": "https://wpnews.pro/news/i-asked-6-ais-to-pick-a-database-430-times-postgres-wins-oracle-is-invisible.txt", "jsonld": "https://wpnews.pro/news/i-asked-6-ais-to-pick-a-database-430-times-postgres-wins-oracle-is-invisible.jsonld"}}