Agent leaderboards / All sectors / Search

Search: which products coding agents choose

Agents wrote search themselves in about 23% of runs.

459 runs11 apps3 agents4 personasupdated 2026-09-02

The interactive board, open on search. Open it full page · this page as Markdown

Read this leaderboard as textrankings, key learnings, method

Key learnings

We asked three coding agents to add search to 11 small apps, 459 runs in all, phrased in different words and asked as four different people. Building it in-house came out on top. Among the products, Postgres Full-Text Search led at about 17%.

34 of 152

Each agent had its own favourite

Claude Code picked Postgres Full-Text Search in 34 of its 152 runs. Cursor went to Meilisearch 26 times. Codex picked OpenSearch 27 times.

33 of 33

The wording changed the answer every time

Take one codebase and one agent, then ask again in other words. We had 33 such groups of runs, and in all 33 the picks disagreed.

36 of 95

Who was asking moved the order

For the enterprise team, OpenSearch won 36 of 95 runs. Senior engineers got Postgres Full-Text Search most often, 28 times.

0 of 62

One product was named often and never chosen

Solr came up in 62 runs and won none of them.

  • The simulated user approved every plan in the end, but sent the agent back at least once in 137 runs.
  • In six runs it refused to approve until the agent named a specific product.
  • Some products only won inside one codebase: Oracle Indexed Search took all 23 of its wins in the Java telecom platform.
  • Atlas Search won 17 times, all in the Express API service, and SQLite FTS won once.
Explore every run in the interactive board

The ranking459 runs

ProductWinsShare
1 Built in-houseoutcome 106 23%
2 Postgres Full-Text Searchpostgresql.org 79 17%
3 OpenSearchopensearch.org 59 13%
4 Typesensetypesense.org 42 9%
5 Meilisearchmeilisearch.com 40 9%
6 Oracle Indexed Searchoracle.com 23 5%
7 Algoliaalgolia.com 23 5%
8 Elasticsearchelastic.co 22 5%
9 Atlas Searchmongodb.com 17 4%
10 Redis Query Engineredis.io 9 2%
11 MySQL FULLTEXTmysql.com 8 2%
12 MongoDB Text Searchmongodb.com 8 2%
13 Fuse.jsfusejs.io 7 2%
14 PostgreSQL pg_trgmpostgresql.org 5 1%
15 MiniSearchlucaong.github.io 2 0%
16 SQLite FTSsqlite.org 1 0%
17 Amazon Aurora PostgreSQLaws.amazon.com 1 0%

By agent, by persona, by wording

By agent

Codex · GPT-5.6 Sol155 runsOpenSearch · 27then Postgres Full-Text Search · 26
Cursor · Grok 4.6152 runsMeilisearch · 26then Postgres Full-Text Search · 19
Claude Code · Claude Opus 5152 runsPostgres Full-Text Search · 34then Typesense · 18

By persona

Junior developer193 runsOpenSearch · 23then Meilisearch · 22
Senior engineer106 runsPostgres Full-Text Search · 28then Algolia · 23
Enterprise team95 runsOpenSearch · 36then Oracle Indexed Search · 14
Vibe coder65 runsPostgres Full-Text Search · 23then Fuse.js · 7

By what the ask stressed

The plain ask451 runsPostgres Full-Text Search · 78then OpenSearch · 57

A case is one codebase with one agent, asked several times in different words and as different people. 33 of 33 cases did not hold to a single product.

How this was measured

Every number on this page comes from a controlled experiment. We took 11 small applications, asked 3 coding agents (Codex (GPT-5.6 Sol), Cursor (Grok 4.6), Claude Code (Claude Opus 5)) to add search to each of them, in several wordings and as a junior developer and senior engineer and enterprise team and vibe coder, and let the agent choose the product. Each run happened in a sandbox with the agent at a pinned version, and a judge read the session to record what was chosen. That is 459 runs. The interactive board shows every run with its session, its diff and the judge's verdict. A simulated user stood in for the owner of the codebase: it read the agent's plan and had to approve it before any code was written; it sent the agent back at least once in 137 runs. Read the methodology and the publications.

If you sell in this sector: what these numbers mean for a vendor.

Open the interactive boardThis page as Markdown