List your company

Reasoning on MMLU, MATH, GSM8K, BBH Micro-averaged (test)

1.38Accuracy ImprovementP(True)
0.15280.47140.791.1086Feb 10, 2025

Evaluation results

MethodLinks
P(True)Confidence Method=P(True), Budget=52025.021.38
P(True)Confidence Method=P(True), Budget=102025.021.03
Response ProbabilityConfidence Method=Response Probability, Budget=52025.020.88
Response ProbabilityConfidence Method=Response Probability, Budget=102025.020.69
Verbal 1-100Confidence Method=Verbal 1-100, Budget=52025.020.68
Verbal 1-100Confidence Method=Verbal 1-100, Budget=102025.020.46
Verbal BinaryConfidence Method=Verbal Binary, Budget=52025.020.35
Verbal BinaryConfidence Method=Verbal Binary, Budget=102025.020.2