Vendor Profile · Illustrative prototype
Firecrawl
Firecrawl on the arlen/bench leaderboards — agent web-search accuracy, extraction fidelity, freshness, cost per verified-correct answer, and agent-readiness, scored against golden truth.
Answer firstillustrative
Firecrawl ranks #5 of 6 for agent web-search accuracy at 74.8% hit@5; #1 of 7 for extraction fidelity at 0.91, and is agent-ready — an autonomous agent obtained a working API key in live trials with zero humans.
hit@5
74.8%
web search
cost / correct
$0.0087
web search
extraction fidelity
0.91
web extraction
agent-ready
Yes
onboarding harness
§ A
Web Search — Firecrawl
| Metric | Firecrawl | Leaderboard best | Direction |
|---|---|---|---|
| hit@1 % | 58.3 | Exa 71.2 | higher is better |
| hit@5 % | 74.8 | Exa 87.6 | higher is better |
| fresh<30d % | 68.8 | Tavily 86.4 | higher is better |
| retrievability h | 15.4 | Tavily 7.8 | lower is better |
| cost/correct $ | $0.0087 | Serper $0.0041 | lower is better |
| p50 latency ms | 926 | Brave 301 | lower is better |
§ B
Web Extraction — Firecrawl
| Metric | Firecrawl | Leaderboard best | Direction |
|---|---|---|---|
| fidelity 0-1 | 0.91 | leads | higher is better |
| JS gap Δ | 0.03 | leads | lower is better |
| block rate % | 4.1 | Apify 3.3 | lower is better |
| cost/correct $ | $0.0031 | Jina $0.0009 | lower is better |
| schema validity % | 96.2 | leads | higher is better |
§ C
Firecrawl vs Exa Firecrawl vs Tavily Firecrawl vs Serper Firecrawl vs Brave Firecrawl vs SerpAPICompare Firecrawl
Illustrative prototype. No verified vendor run has been published yet; every figure here is a placeholder and must not be cited as a measured result. Numbers are replaced when a snapshot’s first full run lands.