General Reasoning on MMLU-CF (Cost Metrics)
0.98Relative CostAnalogical Prompting
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Analogical PromptingEvaluation Model=GPT-4o-mini2026.03 | 0.98 | — | |
| CoTEvaluation Model=GPT-4o-mini2026.03 | 1 | 1,200 | |
| TDA-RCEvaluation Model=GPT-4o-mini2026.03 | 1.06 | — | |
| Role / Persona PromptingEvaluation Model=GPT-4o-mini2026.03 | 1.07 | — | |
| Prompt CanvasEvaluation Model=GPT-4o-mini2026.03 | 1.07 | — | |
| Instruction InductionEvaluation Model=GPT-4o-mini2026.03 | 1.08 | — | |
| HoTEvaluation Model=GPT-4o-mini2026.03 | 1.12 | — | |
| Self-RefineEvaluation Model=GPT-4o-mini2026.03 | 1.83 | — | |
| AoTEvaluation Model=GPT-4o-mini2026.03 | 2.89 | — | |
| AFlowEvaluation Model=GPT-4o-mini2026.03 | 3.18 | — | |
| ToTEvaluation Model=GPT-4o-mini2026.03 | 4.12 | — | |
| GoTEvaluation Model=GPT-4o-mini2026.03 | 4.32 | — | |
| CoT-SCEvaluation Model=GPT-4o-mini, n=52026.03 | 5.03 | — | |
| FoTEvaluation Model=GPT-4o-mini, n=82026.03 | 7.96 | — |