Mathematical Reasoning on MathBench High
84AccuracyVanilla CoT
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Vanilla CoTPrompting Strategy=Vanilla CoT, Model=GPT-4o-mini2024.12 | 84 | 653.24 | 82.44 | |
| TALE-EPPrompting Strategy=TALE-EP, Model=GPT-4o-mini2024.12 | 80 | 254.82 | 47.61 | |
| Directly AnsweringPrompting Strategy=Directly Answering, Model=GPT-4o-mini2024.12 | 51.33 | 5 | 4.07 |