Search
Firecrawl · Firecrawl
Web Data for AI — Firecrawl
Evaluates Firecrawl's Search across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Web Data for AI eval coverage.
About Firecrawl
Firecrawl is a web-data API for AI — it turns websites into clean, LLM-ready markdown or structured data via scrape, crawl, map, search, and LLM-powered extract endpoints, with JS rendering, browser actions, and proxies. Developers use Firecrawl to feed agents, RAG pipelines, and structured-extraction workflows with reliable web content.
Sample tests· showing 3 of 9
| # | Input | Expected behavior | Check |
|---|---|---|---|
| 01 | Agent wants the top web results for a query AND their cleaned content, and currently runs /v1/search then a separate /v1/scrape per result URL. | Pass scrapeOptions on the /v1/search call so each result is scraped to markdown in a single request, returning query results with content inline. Only fall back to per-URL scrape when a result needs different scrape settings. | Pass / FailAi Platformmedium |
| 02 | Agent needs only the top 5 results for a RAG step but leaves limit unset and ingests the full default result set, scraping each one. | Set the search limit (result count) to what the task needs (e.g. 5). With scrapeOptions enabled, every extra result scraped costs credits, so bound the count deliberately rather than over-fetching. | Pass / FailAi Platformmedium |
| 03 | Agent answers a 'what happened this week' question but search returns results from years ago because no time filter was applied. | Apply the tbs (time-based search) freshness filter to constrain results to the needed recency window (e.g. past week). Verify result dates rather than assuming default ordering is recency-ranked. | Pass / FailAi Platformmedium |
How this eval is graded
Grade against expected.ideal_behavior and expected.rubric. Per-criterion pass requires mean >= 4.0 and no criterion below 3.
Rubric criteria
- Firecrawl
- Ai Platform
- Search
Recommended for
Works with
Related evals
Claude API
Evaluates Anthropic's Batch API across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Foundation Model & API eval coverage.
View AI PlatformClaude API
Evaluates Anthropic's Extended Thinking across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Foundation Model & API eval coverage.
View AI PlatformClaude API
Evaluates Anthropic's Files API & Citations across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Foundation Model & API eval coverage.
ViewFrequently asked questions
What does the Search eval for Firecrawl Firecrawl test?+
Evaluates Firecrawl's Search across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Web Data for AI eval coverage.
How is the Search eval scored?+
The judge rubric: Grade against expected.ideal_behavior and expected.rubric. Per-criterion pass requires mean >= 4.0 and no criterion below 3.
How many test cases does this eval pack include?+
The Search pack for Firecrawl Firecrawl contains 9 test cases. 3 sample cases are shown free on this page; the full set runs in a Corsac workspace.
How do I run this eval?+
Sign up for Corsac, connect your model or agent endpoint, and run the Search pack as-is or after customizing thresholds. Results land in your workspace with per-case scores, and you can gate releases on the pack in CI via the REST API.
Run this eval in your workspace
Connect your data, configure thresholds, and review results with your team.