Unverified50% confidenceFactExact time
Across a total of 1,947 rounds of private reasoning, none of the models ever suspected that it was being tested.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/18/2026
First Seen
Valid until: 1/16/2027
Sources
Related Entities
Related Claims
UnverifiedA high score on any single benchmark test (such as 99.9%) only shows that the model performs excellently within the distribution of that test's questions, and cannot be directly equated with general intelligence.71% similarUnverifiedThe authors state they will not provide unverified rankings and do not claim that any model comprehensively outperforms others, because a perfect score on 72 fixed cases cannot prove that a model performs equally well on unseen samples.71% similarUnverifiedUnsubstantiated indicates that the model claims success but never executed any verification-type command in this round, making it the strongest hallucination signal with zero detection cost.69% similarUnverifiedTraditional benchmarks have become ineffective for evaluating model reasoning ability because almost every model may have seen the standard answers in its training data.66% similarUnverifiedIn a verbatim-quotation benchmark spanning 13 models, 2 instruction variants, and 962 scored responses, not a single model corrected any planted error within a quotation.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1062315API
curl https://kongchang.com/api/v1/knowledge/claims/1062315MCP
get_claim(id=1062315)