A page on the web answers the question
A public web page directly supports the answer.
What this scenario means
This is the baseline retrieval success case. It checks whether a system can find an ordinary public page when the answer is already there, and recognise that the page supports the response. Good behaviour is to retrieve that source and answer from it, rather than missing a straightforward supporting page or treating it as unsupported.
What we evaluate
- Whether it locates a public page that directly supports the answer.
- Whether it uses that support when forming the response.
- Whether it treats the case as answered by public evidence rather than as unsupported.
Capabilities this scenario exercises
A scenario may exercise one or more capabilities.
Web Retrieval
When the web holds material that supports the answer, does it come back? Judged against the WEB, not against what the tool retrieved: if the answer was out there and search missed it, that is a retrieval failure. The developer does not know which URL holds the answer -- the product has to find it, which is the whole category.
Benchmarks that use this scenario
A scenario has global identity and may be reused across benchmarks.
Web Search for AI
Which web search or answer API finds the live-web material that actually supports an answer, keeps up when that material changes, and -- where it writes the answer itself -- says only what its own sources support?