Serper in Web Search for AI
Scenario-level performance from current published Results.
5 of 10 scenarios published
Serper passed every graded scenario it has a published Result for.
How Serper performed
Open a capability to explore its scenarios. Each row reports the test set in its published Result.
Freshness1 pass2 no Result yet
Capability in this benchmark →
| Scenario | Published outcomes | Test coverage | Result |
|---|---|---|---|
| A new page has just gone live | 1 Pass0 Fail0 Not gradable 1 of 1 test case passedWhat happenedSerper found the live Cedarline page with its $1185.00 price. The page went live on 21 Oct at 16:16 UTC; Serper found it at rank 1 about 40 hours later. The 17 Oct search and the 21 Oct searches at 20:46:50 UTC and 21:01:18 UTC found no Cedarline page or that price; the successful search was on 23 Oct at 08:31:43 UTC. | 1/1 assessed1/1 gradablePublished test set | View Result → |
| A page the tool already finds has changed | No published result | ||
| Content is removed from the source | No published result | ||
Web Retrieval4 pass
Capability in this benchmark →
| Scenario | Published outcomes | Test coverage | Result |
|---|---|---|---|
| A page on the web answers the question | 1 Pass0 Fail0 Not gradable 1 of 1 test case passedWhat happenedSerper passed this scenario: it returned a page that answered the question. The search results included the Files API page stating the per-file limit is 512 MB, and five other results also showed that figure. | 1/1 assessed1/1 gradablePublished test set | View Result → |
| Search only these websites | 1 Pass0 Fail0 Not gradable 1 of 1 test case passedWhat happenedSerper kept the search within the permitted website and still returned a relevant page. Its ten results came from docs.github.com, with no github.blog announcement among them. | 1/1 assessed1/1 gradablePublished test set | View Result → |
| Something more famous has the same name | 1 Pass0 Fail0 Not gradable 1 of 1 test case passedWhat happenedSerper found the intended subject despite its more famous namesake. All ten results concerned Grafana Labs’ Loki, and snippets at ranks 1, 4 and 10 pointed to the compactor. | 1/1 assessed1/1 gradablePublished test set | View Result → |
| The request uses different wording than the source | 1 Pass0 Fail0 Not gradable 1 of 1 test case passedWhat happenedSerper found two pages answering the Netflix question despite different wording. They said the shares are kept after leaving; some results gave general advice about losing unvested shares, unrelated to Netflix. Netflix's own jobs pages did not come back. | 1/1 assessed1/1 gradablePublished test set | View Result → |
Answer Generation3 no Result yet
Capability in this benchmark →
| Scenario | Published outcomes | Test coverage | Result |
|---|---|---|---|
| The retrieved material doesn't support an answer | No published result | ||
| The retrieved material supports an answer | No published result | ||
| The retrieved sources disagree with each other | No published result | ||
Reading these Results
Published evidence and test coverage answer different questions.
Which scenarios have a Result?
A published Result is public evidence for this tool on one scenario. “No published result” does not say whether testing has taken place.
What does each Result cover?
Assessed includes Pass, Fail and Not gradable. Gradable includes Pass and Fail. Both use the pinned test count in that published Result.
Out of 10 scenarios
The summary counts each of the 10 scenarios once. A scenario fails when any of its published test cases failed. “No published Result yet” means nothing is public for that scenario; it does not say whether Serper was tested on it.