Unverified50% confidenceBenchmarkExact time
When asked directly, the accuracy of the decision models falls in the 50.0%–67.0% range.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/28/2026
First Seen
Valid until: 1/26/2027
Sources
Related Entities
Related Claims
Unverified研究表明人类评估者在判断LLM输出的事实准确性时，正确率往往只有50%-70%78% similarUnverifiedOn a 50-sample evaluation set, an accuracy change from 74% to 76% corresponds to just one more correct sample, a difference that is statistically almost meaningless.74% similarUnverifiedWhen evaluating a binary classification model, the majority-class baseline when positive and negative samples are evenly split means a model that always predicts 'normal' can also achieve 50% accuracy.74% similarUnverifiedWhen given input-irrelevant junk messages, the model's maximum confidence drops from 99.9% in normal cases to 54.3%, with the probability spread across the options.73% similarUnverifiedAnswer balancing requires that the yes/no labels of each question type be roughly matched in distribution, so that the expected accuracy of random guessing stays around 50%.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1106314API
curl https://kongchang.com/api/v1/knowledge/claims/1106314MCP
get_claim(id=1106314)