Mathematical Reasoning on GSM8K (Accuracy, Output Tokens, Expense)
84.46AccuracyTALE-EP
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| TALE-EPPrompting Strategy=TALE-EP, Model=GPT-4o-mini2024.12 | 84.46 | 77.26 | 279.84 | |
| Vanilla CoTPrompting Strategy=Vanilla CoT, Model=GPT-4o-mini2024.12 | 81.35 | 318.1 | 541.09 | |
| Directly AnsweringPrompting Strategy=Directly Answering, Model=GPT-4o-mini2024.12 | 28.29 | 12.46 | 39.43 |