Mathematical Reasoning on GSM8K Zero (ACC, Output Tokens, Expense)
99.5ACCVanilla CoT
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Vanilla CoTPrompting Strategy=Vanilla CoT, Model=GPT-4o-mini2024.12 | 99.5 | 252.96 | 886.79 | |
| TALE-EPPrompting Strategy=TALE-EP, Model=GPT-4o-mini2024.12 | 98.72 | 22.67 | 276.12 | |
| Directly AnsweringPrompting Strategy=Directly Answering, Model=GPT-4o-mini2024.12 | 97.21 | 18.85 | 91.69 |