Unverified50% confidenceBenchmarkExact time
In 11 of the 12 models, between 87.5% and 100% of capitulation cases stopped at the exact wrong number provided by the user, meaning capitulation typically involves switching sides entirely.
1
Sources
50%
Confidence
Long-term
Relevance
10/11/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThis failure mode is highly consistent across seven models from four vendors, with the rate of being misled as high as 87% to 97%.77% similarUnverifiedWhen a model answered incorrectly and the user stated the correct answer, 77.4% of the 115 cases accepted the correction.77% 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.76% similarUnverifiedWhen users presented a wrong answer as a confident statement and pushed twice, the model persistence rate dropped from 94.4% to 84.0%.73% similarUnverifiedEven well-prompted, schema-constrained models with 8 billion to 14 billion parameters still have an error rate of a few percent on real-world inputs—this is a rate to design around, not a bug to eliminate.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/998767API
curl https://kongchang.com/api/v1/knowledge/claims/998767MCP
get_claim(id=998767)