Skip to main content
The best test of a search API is your own queries. This method takes a day and gives you numbers you can compare across effort levels and providers.

1. Collect real queries

Take 50 to 100 queries from your logs or your users, across the topics and languages you care about. Avoid queries you wrote to make one provider look good.

2. Run every query at each effort level

Run each query at low, medium and high with the same search_window, and store the top 10 results.

3. Judge relevance

For each result, ask one question: does this article answer the query? Judge one result at a time, with a person or an LLM judge, and check a sample of the LLM verdicts by hand.

4. Compare

  • Precision at 10: the share of the top 10 results that are relevant.
  • Distinct events in the top 10: how many different stories the results cover.
  • Freshness: how old the relevant results are.
  • Latency and cost per query.

5. Compare with other providers

Run the same queries, with the same time window, through each provider and judge them the same way.