String vs Linkup for AI agents
String and Linkup both ran scrape and search, with the same tasks, the same model (Claude Haiku 5.5), the same prompt and the same limits. A task counts only when a script confirms every answer. Beyond that, only String ran map.
The benchmark tests each provider's gap to its track's leader, with 95% intervals from resampling whole sites. It doesn't test every pair directly, so this page says when a gap is real and when it isn't one anybody can claim.
Scrape 40 tasks · Test heading and structure preservation on documentation pages, plus package versions and JS fields.
Linkup finished clearly fewer tasks than Context.dev, the leader, and String did not. The two weren't tested against each other directly, so this page doesn't call a winner between them.
Linkup cost 1.23¢ per finished task and String 1.33¢, counting all API and model spend, failures included.
Search 30 tasks · Find facts, registry versions and documentation headings on the live web.
Linkup led this track and finished 17 points more tasks than String. That gap is big enough to rule out chance.
String cost 1.32¢ per finished task and Linkup 2.19¢, counting all API and model spend, failures included.
More
Every provider on each track: scrape, search. How a gap is tested: methodology.