Reasoning on MMLU, MATH, GSM8K, BBH Micro-averaged (test)
1.38Accuracy ImprovementP(True)
Evaluation Results
| Method | Links | |
|---|---|---|
| P(True)Confidence Method=P(True), Budget=52025.02 | 1.38 | |
| P(True)Confidence Method=P(True), Budget=102025.02 | 1.03 | |
| Response ProbabilityConfidence Method=Response Probability, Budget=52025.02 | 0.88 | |
| Response ProbabilityConfidence Method=Response Probability, Budget=102025.02 | 0.69 | |
| Verbal 1-100Confidence Method=Verbal 1-100, Budget=52025.02 | 0.68 | |
| Verbal 1-100Confidence Method=Verbal 1-100, Budget=102025.02 | 0.46 | |
| Verbal BinaryConfidence Method=Verbal Binary, Budget=52025.02 | 0.35 | |
| Verbal BinaryConfidence Method=Verbal Binary, Budget=102025.02 | 0.2 |