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.
What we check
- Whether the tool already returned the page before the change was introduced.
- Whether the after-probe shows the updated live version of that same page.
- Whether the tool avoids serving a stale copy after the page changes.
- 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 →