Unverified50% confidenceBenchmarkExact time
The analyzers executed by the policy engine hit the answer + evidence contract in all 110 out of 110 tests.
1
Sources
50%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn actual testing, one Deep Research call invoked 104 agents for targeted research, completing fact-checking based on 22 sources and 59 claims.68% similarUnverifiedEach model configuration was tested under two reasoning intensities, HIGH and XH (Extra High), with each configuration run independently 10 times.66% similarUnverifiedThe benchmark uses a unified set of 100 questions, with only one search issued per question and the same answering model used across all configurations to process the returned content.66% similarUnverifiedAgent可靠性验证方法论包括：每个任务重复运行10次以上、以程序化方式检查最终状态、对每次工具调用按schema校验、统计高负载下被截断的调用数量63% similarUnverifiedThe evaluation comprised 108 checks across three major modules: backend API and full pipeline at 65 points, frontend pages and real interaction at 25 points, and build and packaging at 10 points.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/898640API
curl https://kongchang.com/api/v1/knowledge/claims/898640MCP
get_claim(id=898640)