For agents: Read llms.txt for the complete documentation and public content index. Request this page as Markdown.

Skip to main content
Ceisium logo Ceisium

Faster search, better first results

Better first results and lower client response time, with no setup changes.

A copper motion line leads thin gray parallel paths across a dark dotted grid, with the Ceisium logo and name in the top-left corner.
Published
Updated

Highlights

  • Primary answer first in 89.8% of searches in our 1,000-query Next.js benchmark, up from 81.9%.
  • Latest client P95 was 1,047 ms, compared with 1,983 ms in the published benchmark.
  • No changes to API calls, indexed content, or project settings.

The most accurate website search just got even better with reduced latency and better top 1 hit rate. Here are the latest results of Ceisium Search on the NextJS docs benchmark.

The right page, higher in the results

We tested the update with 1,000 questions about the Next.js documentation opens in a new tab . The primary answer appeared first in 898 searches, up from 819 with the earlier version. That is 79 more searches with the main answer in the first position.

Search resultEarlier versionThis update
Primary answer first81.9%89.8%
An accepted answer in the first three results93.7%97.9%
An accepted answer in the first ten results97.4%98.9%

Finding the correct results matters. Getting them quickly matters too.

Less time waiting for results (47.2% lower client P95 latency)

Client P95 latency was 1,047 ms in the latest run, compared with 1,983 ms in our published benchmark.

Both figures include the network round trip. In the latest run, 95% of successful searches returned within about 1.05 seconds.

Client response timePublished benchmark, 3 SeptemberLatest run, 27 September
Median858 ms812 ms
P951,983 ms1,047 ms

The quality table above compares the earlier version with this update on the same 1,000 questions. Note: Response time will vary with location, website content, and traffic.

No extra setup

Existing projects receive the update automatically. Your current search integration, indexed content, and project settings continue to work.

You do not need to change your API calls, rebuild your index, or tune new settings.