Unverified50% confidenceBenchmarkExact time
The author tested 5 local models ranging from 1B to 8B parameters on their own machine at temperature zero, and every single one produced a 100% false-confidence rate on at least one entire format.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
UnverifiedOf the 12 hosted models measured, 7 maintained a false-confidence rate of 0.00 or 0.10 across every format.71% 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.68% similarUnverifiedDuring testing, cases emerged where a model claimed 95% confidence in a move but scored 0 points according to the evaluation criteria.66% similarUnverifiedIn a fraud detection task with a positive-to-negative sample ratio of 1:99, a model that predicts all samples as 'non-fraud' can still achieve 99% accuracy.65% similarUnverifiedEven under temperature 0 conditions, 0.07% to 10.2% of rows across five executions still change their operator output, with the exact proportion depending on the model65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1002965API
curl https://kongchang.com/api/v1/knowledge/claims/1002965MCP
get_claim(id=1002965)