Unverified50% confidenceFactExact time
AnswerLine's testing process is: prompt set → one API call per engine per prompt → count brand mentions; each engine uses a single endpoint, returns answers in JSON format, and includes cited source URLs.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
UnverifiedMost traditional LLM benchmarks focus on relatively closed tasks such as single-turn question answering, code generation, and reasoning problems.65% similarVerifiedEach extracted test point uses a unified JSON format containing the module chapter, test point title, test status and operation steps, expected results, priority, and test design method.65% similarUnverifiedThe team proposed adding a dedicated test that enumerates each link in the chain by name, asserting that each exists in the registration path, actually runs, and fails when its test target is disabled.65% similarUnverifiedEach question in the benchmark has a single correct answer derived by Python computation; the scorer requires models to end with ANSWER:<value>, EMI allows a rounding tolerance of ±₹2, and the formatting group requires exact string matching.64% similarUnverifiedopen-code-review resolves the deduplication problem of the rule engine and the LLM repeatedly reporting the same issue through a confidence scoring mechanism.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1011690API
curl https://kongchang.com/api/v1/knowledge/claims/1011690MCP
get_claim(id=1011690)