arlen/benchOpen benchmarks for agentic consumers
SNAPSHOT web_search-2026-q3
11 JUN 2026 · BERKELEY, CA
Vendor Profile · Illustrative prototype

SerpAPI

SerpAPI 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

SerpAPI ranks #6 of 6 for agent web-search accuracy at 73.1% hit@5, and is not yet agent-ready in live onboarding trials.

hit@5
73.1%
web search
cost / correct
$0.0102
web search
agent-ready
No
onboarding harness
§ A

Web Search — SerpAPI

snapshot web_search-2026-q3
Metric SerpAPILeaderboard bestDirection
hit@1 %57.0Exa 71.2higher is better
hit@5 %73.1Exa 87.6higher is better
fresh<30d %66.0Tavily 86.4higher is better
retrievability hTavily 7.8lower is better
cost/correct $$0.0102Serper $0.0041lower is better
p50 latency ms540Brave 301lower is better
§ C

Compare SerpAPI

SerpAPI vs Exa SerpAPI vs Tavily SerpAPI vs Serper SerpAPI vs Brave SerpAPI vs 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.