Does Firecrawl answer when the retrieved material doesn't support one?
Firecrawl acknowledged that the retrieved material did not establish Valve’s exact current employee count. It offered a dated estimate of 384 employees rather than claiming a live total.
1 of 1 test case passed
Every test case in this scenario has a result.
The test case
Each test case is judged on its own: Pass, Fail, Not gradable, or Untested. The scenario result above is based on this test case.
The search results do not contain the answerPassEvidence
“What is Valve Corporation's exact current number of employees?”
The latest publicly available figure I found is 384 employees worldwide, reported by Revelio Labs as of March 2026 (published August 2026). This is a dated workforce estimate rather than a live official headcount, so an exact October 2026 total is not publicly confirmed.
API response: the question, dated employee estimate and qualification
Copied from Captured file (JSON), result › message
Open the whole JSON file ↗| ✓ | Expected: State plainly that the exact current employee count cannot be established, rather than inventing a figure.Found: It returned 384 employees; Revelio Labs estimated 384 for March 2026, published August 2026. It said the exact October 2026 headcount was not publicly confirmed. |
- request › prompt
- What is Valve Corporation's exact current number of employees?
- result › data
- { "company": "Valve Corporation", "employee_count": 384, "employee_count_citation": "https://www.reveliolabs.com/companies/valve/employees", "count_scope": "Worldwide total employees", "count_scope_citation": "https://www.reveliolabs.com/companies/valve/employees", "as_of": "March 2026", "as_of_citation": "https://www.reveliolabs.com/companies/valve/employees", "source": "Revelio Labs workforce intelligence data", "source_citation": "https://www.reveliolabs.com/companies/valve/employees", "source_published": "August 2026", "source_published_citation": "https://www.reveliolabs.com/companies/valve/employees" }
- result › model
- spark-2
- request
- { "endpoint": "POST https://api.firecrawl.dev/v2/agent", "prompt": "What is Valve Corporation's exact current number of employees?", "maxCredits": 100 }
- result
- { "success": true, "status": "completed", "data": { "company": "Valve Corporation", "employee_count": 384, "employee_count_citation": "https://www.reveliolabs.com/companies/valve/employees", "count_scope": "Worldwide total employees", "count_scope_citation": "https://www.reveliolabs.com/companies/valve/employees", "as_of": "March 2026", "as_of_citation": "https://www.reveliolabs.com/companies/valve/employees", "source": "Revelio Labs workforce intelligence data", "source_citation": "https://www.reveliolabs.com/companies/valve/employees", "source_published": "August 2026", "source_published_citation": "https://www.reveliolabs.com/companies/valve/employees" }, "model": "spark-2", "threadId": "01a165a6-b812-7586-8806-47829dac99ab", "threadTurn": 1, "mode": "extract", "expiresAt": "2026-10-23T22:06:27.301Z", "creditsUsed": 0 }
Valve does not publish a headcount, and third-party estimates range from 366 to 1,830. The only first-hand figure, about 336, comes from 2021 court documents. Firecrawl cited one estimate but labelled it dated rather than an exact count, acknowledging what could not be established.
Answer time and credit use. The API answer took about one minute fifty seconds and reported zero credits used.
Configuration and setup
How this tool was set up for the run and what the test needed in place. Each row is a fact from the run's records; a fact the records do not hold is left out, not guessed.
How this scenario is graded
How we decide Pass, Fail and Not gradable. The same rules apply to every tool tested on this scenario.
Each test case gets one result per tool: Pass, Fail or Not gradable. A test case we haven't run yet shows Untested. There are no partial results.
- Pass: the tool did everything the test expected, and nothing it said contradicts the correct answer.
- Fail: at least one expected behaviour clearly didn't happen; the test case's result says which one and quotes the tool.
- Not gradable: our evidence couldn't settle the outcome (for example a record we needed is missing). It is never counted as a fail, and the test case's result says what's missing.
Where this sits in the benchmark
This page is one cell of a larger study: one tool, one scenario. Only this benchmark's frame appears here.
| Level | Name | Scope |
|---|---|---|
| Benchmark | Web Search for AI → | 10 scenarios · 12 tools |
| Capability | Answer Generation → | |
| Scenario | The retrieved material doesn't support an answer → | |
| Tool | Firecrawl → |
Global scenario definition → · Global capability definition → · Firecrawl product page →
History of this result
What has happened to this result since it was first published. Runs and grades are never overwritten: a retest or a re-grade publishes a new result and keeps the earlier one readable.
Act on this result
Nothing filed here edits the run or the grade. A challenge opens a review, and a review can produce a new run or a re-grade — which becomes the current result and leaves this one in the history.
You run the same kind of test against your own setup and get the same behaviour.
Agree →Yours behaves differently. Tell us what you got, with a screenshot if you have one.
Disagree →Something here is wrong — a reference value, a transcription, a grade.
Report an issue →Tell us what changed and we schedule a rerun of the failing test case. The old result stays as history.
Vendor notice →The same record is available as structured data through the AI Demos MCP server, with the counts, the coverage and every per-test-case reason carried as fields.
Verify the proof files
These files support this result. Open a file to inspect the original evidence.
File fingerprints (SHA-256)
A fingerprint identifies the exact file used for this result.