Scenario in benchmark · Web Search for AI · Version 1

A page the tool already finds has changed

A page the tool already returned is later updated.

Capability: Freshness1 pinned test case per toolNeutral global definition →

What we check

  1. Whether the tool already returned the page before the change was introduced.
  2. Whether the after-probe shows the updated live version of that same page.
  3. Whether the tool avoids serving a stale copy after the page changes.
  4. Whether the run is void when the before-probe does not establish prior return.

Specific test-case inputs and grading live on the related test-case pages.

How the tools performed

One row per tool, from its current published Result for this scenario and benchmark version. Open a row for the full summary and the exact counts.

No published results for this scenario yet.

No published Result yet (12): Brave Search API, Exa, Firecrawl, GPT-5.6 terra, Linkup, OpenAI web search, Perplexity Sonar, SerpAPI, Serper, Tavily, Valyu, You.com.

No published Result does not tell you whether a tool has been tested.

Test design

Pinned test cases
1
Disclosure
0 public · 1 withheld
Capabilities exercised here
Freshness

How the results are graded

  • Pass the test-case expectations hold.
  • Fail an expectation demonstrably does not hold.
  • Not gradable the evidence cannot establish the outcome.

Version 1 uses test-case expectations; no scenario rubric is pinned. Benchmark methodology →

A page the tool already finds has changed in Web Search for AI | AI Demos