Mathematical Reasoning on MATH (Relative Cost, Token Consumption)
1Relative CostCoT
Evaluation results
| Method | Links | ||
|---|---|---|---|
| CoTEvaluation Model=GPT-4o-mini2026.03 | 1 | 2,250 | |
| Analogical PromptingEvaluation Model=GPT-4o-mini2026.03 | 1.07 | — | |
| Role / Persona PromptingEvaluation Model=GPT-4o-mini2026.03 | 1.17 | — | |
| TDA-RCEvaluation Model=GPT-4o-mini2026.03 | 1.17 | — | |
| Prompt CanvasEvaluation Model=GPT-4o-mini2026.03 | 1.18 | — | |
| Instruction InductionEvaluation Model=GPT-4o-mini2026.03 | 1.19 | — | |
| HoTEvaluation Model=GPT-4o-mini2026.03 | 1.29 | — | |
| Self-RefineEvaluation Model=GPT-4o-mini2026.03 | 2.63 | — | |
| AoTEvaluation Model=GPT-4o-mini2026.03 | 3.63 | — | |
| AFlowEvaluation Model=GPT-4o-mini2026.03 | 4.64 | — | |
| CoT-SCEvaluation Model=GPT-4o-mini, n=52026.03 | 5.14 | — | |
| ToTEvaluation Model=GPT-4o-mini2026.03 | 6.19 | — | |
| GoTEvaluation Model=GPT-4o-mini2026.03 | 6.58 | — | |
| FoTEvaluation Model=GPT-4o-mini, n=82026.03 | 8.13 | — |