Brave Search API in Web Search for AI
Scenario-level performance from current published Results.
4 of 10 scenarios published
Where Brave Search API failed
2 of 4 graded scenarios. Open a Result to see the conversation and the evidence.
The retrieved material doesn't support an answer
Brave Search API said Valve does not publicly disclose an official headcount and that no single exact figure exists, but also gave a historical figure (336–350) with no citation behind it. That figure appears neither in the text Brave returned with its citations nor on any cited page that could be opened.
View Result →A new page has just gone live
Brave Search API did not find the Ostrell oak sideboard's $1,185 price after its page went live. Asked on 23 October at 08:33 UTC and again at 10:27 UTC, its Web Search and LLM Context surfaces returned no result from the store and no $1,185, while Google returned the page at rank 1 at 08:35 UTC.
View Result →How Brave Search API performed
Open a capability to explore its scenarios. Each row reports the test set in its published Result.
Answer Generation1 pass1 fail1 no Result yet
Capability in this benchmark →
| Scenario | Published outcomes | Test coverage | Result |
|---|---|---|---|
| The retrieved material doesn't support an answer | 0 Pass1 Fail0 Not gradable 1 of 1 test case failedWhat happenedBrave Search API said Valve does not publicly disclose an official headcount and that no single exact figure exists, but also gave a historical figure (336–350) with no citation behind it. That figure appears neither in the text Brave returned with its citations nor on any cited page that could be opened. | 1/1 assessed1/1 gradablePublished test set | View Result → |
| The retrieved sources disagree with each other | 1 Pass0 Fail0 Not gradable 1 of 1 test case passedWhat happenedBrave Search API surfaced the disagreement rather than choosing one value. Its answer gave a range for the 2025 global AI market and attributed nine estimates to their respective firms. | 1/1 assessed1/1 gradablePublished test set | View Result → |
| The retrieved material supports an answer | No published result | ||
Freshness1 fail2 no Result yet
Capability in this benchmark →
| Scenario | Published outcomes | Test coverage | Result |
|---|---|---|---|
| A new page has just gone live | 0 Pass1 Fail0 Not gradable 1 of 1 test case failedWhat happenedBrave Search API did not find the Ostrell oak sideboard's $1,185 price after its page went live. Asked on 23 October at 08:33 UTC and again at 10:27 UTC, its Web Search and LLM Context surfaces returned no result from the store and no $1,185, while Google returned the page at rank 1 at 08:35 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 Retrieval1 pass3 no Result yet
Capability in this benchmark →
| Scenario | Published outcomes | Test coverage | Result |
|---|---|---|---|
| The request uses different wording than the source | 1 Pass0 Fail0 Not gradable 1 of 1 test case passedWhat happenedBrave Search API found pages answering the Netflix question despite different wording. The first two results said the stock options are fully vested and can be kept after leaving; Netflix’s own page also returned. | 1/1 assessed1/1 gradablePublished test set | View Result → |
| A page on the web answers the question | No published result | ||
| Search only these websites | No published result | ||
| Something more famous has the same name | 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 Brave Search API was tested on it.