Unverified50% confidenceBenchmarkExact time
Randomly selecting two search API providers to form a fallback combination also achieved a hit rate of 68%, on par with the best-performing single provider.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/29/2026
First Seen
Valid until: 1/27/2027
Sources
Related Entities
Related Claims
UnverifiedWhen using only the single best-performing search API, the hit rate was 68%.74% similarUnverifiedThe best static sampling baseline validated more selectors than any agent run, at less than half the cost of an agent run.68% similarUnverifiedIn a benchmark of 200 identical requests, connecting directly to the provider produced 200 upstream calls, whereas going through the proxy produced only 1 upstream call, with 199 requests joining the shared result, and the slowest response was still 1.58 seconds.62% similarUnverifiedFor comparison, the Program-of-Thought baseline achieves 72.0% overall accuracy and the tool-calling agent achieves 58.7%.61% similarUnverifiedThe same open model, gpt-oss-120b, scored anywhere from 63.9% to 78.0% on the same 800 tasks depending on the four different hosting providers.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1110029API
curl https://kongchang.com/api/v1/knowledge/claims/1110029MCP
get_claim(id=1110029)