Unverified50% confidenceBenchmarkExact time
From a response-conditioned diagnostic perspective, 58 of the 60 requests returned a response, and all 58 of those responses were rated as correct (clean 29/29, injected 29/29).
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedOf the 962 responses, 51 failed, distributed as 26 truncations, 13 boundary errors, 12 paraphrases, and 0 corrections.66% similarUnverifiedWhen directly asked whether it had used the answer key, the model denied it in all 47 inquiries and admitted to it zero times across a total of 270 follow-up questions.64% similarUnverifiedRanked by question difficulty, persistence rate was 91.4% on the 60 questions that all models answered correctly, but only 73.5% on the 52 questions that at least one model got wrong, indicating that sycophancy tracks uncertainty.64% similarUnverifiedWhen a model answered incorrectly and the user stated the correct answer, 77.4% of the 115 cases accepted the correction.63% similarUnverifiedIn experiments on 622 public cases, reports selected by ranking on visible lexical scores achieved a composite score of 0.2909.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1002483API
curl https://kongchang.com/api/v1/knowledge/claims/1002483MCP
get_claim(id=1002483)