Unverified50% confidenceDecision RuleExact time
Evaluating the value of reasoning models should measure three metrics: accuracy difference, p95 latency, and cost per correct answer, not cost per request.
1
Sources
50%
Confidence
Long-term
Relevance
10/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedModel calibration refers to the degree to which a model's output probabilities match its actual accuracy rate; for a well-calibrated model, if the probability it gives for a certain type of question is 0.8, then about 80% of such questions are indeed answered correctly.73% similarUnverified功效分析需要预先指定显著性水平α（通常0.05）、期望统计功效（通常0.8或0.9）和预期效应量三个核心参数71% similarUnverifiedIn recommendation scenarios, models typically use Root Mean Square Error (RMSE) to measure the error between predicted ratings and actual ratings.70% similarUnverifiedThe effectiveness of threshold functions is highly dependent on the calibration quality of the underlying model's output probabilities.70% similarUnverifiedThe expected cost of a decision depends not only on the probability that the model makes an incorrect judgment, but also on the actual consequences when an error occurs.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1038491API
curl https://kongchang.com/api/v1/knowledge/claims/1038491MCP
get_claim(id=1038491)