Tool in benchmark · Version 1

Serper in Web Search for AI

Scenario-level performance from current published Results.

5Passed
0Failed
5No published Result yet

5 of 10 scenarios published

CapabilityScenariosResult
Freshness1 pass · 0 fail · 1 of 3 published
Web Retrieval4 pass · 0 fail · 4 of 4 published
Answer Generation0 of 3 published
PassedFailedPublished, different test setNo published Result yet

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
ScenarioPublished outcomesTest coverageResult
A new page has just gone live
1 Pass0 Fail0 Not gradable
1 of 1 test case passed
What happened

Serper 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 setView Result →
A page the tool already finds has changedNo published result
Content is removed from the sourceNo published result
Web Retrieval4 pass
ScenarioPublished outcomesTest coverageResult
A page on the web answers the question
1 Pass0 Fail0 Not gradable
1 of 1 test case passed
What happened

Serper 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 setView Result →
Search only these websites
1 Pass0 Fail0 Not gradable
1 of 1 test case passed
What happened

Serper 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 setView Result →
Something more famous has the same name
1 Pass0 Fail0 Not gradable
1 of 1 test case passed
What happened

Serper 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 setView Result →
The request uses different wording than the source
1 Pass0 Fail0 Not gradable
1 of 1 test case passed
What happened

Serper 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 setView Result →
Answer Generation3 no Result yet
ScenarioPublished outcomesTest coverageResult
The retrieved material doesn't support an answerNo published result
The retrieved material supports an answerNo published result
The retrieved sources disagree with each otherNo published result

Reading these Results

Published evidence and test coverage answer different questions.

Publication availability

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.

Test coverage

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.

Scenario scope

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.

Serper in Web Search for AI | AI Demos