Vendor Profile · Illustrative prototype
Brave
Brave 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
Brave ranks #3 of 4 for agent web-search accuracy at 58.9% hit@5, and is not yet agent-ready in live onboarding trials.
hit@5
58.9%
web search
cost / correct
—
not yet measured
agent-ready
No
onboarding harness
§ A
Web Search — Brave
| Metric | Brave | Leaderboard best | Direction |
|---|---|---|---|
| hit@1 % | 48.8 | Exa 62.2 | higher is better |
| hit@5 % | 58.9 | Exa 80.9 | higher is better |
| fresh<30d % | — | — | higher is better |
| retrievability h | — | — | lower is better |
| cost/correct $ | — | — | lower is better |
| p50 latency ms | — | — | lower is better |
§ C
Brave vs Exa Brave vs SerpAPI Brave vs Tavily Brave vs Firecrawl Brave vs Jina Brave vs SerperCompare Brave
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.