Token Consumption and Relative Cost on MuSiQue (Multi-hop Reasoning)
1Relative CostCoT
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| CoTEvaluation Model=GPT-4o-mini2026.03 | 1 | 467 | |
| Analogical PromptingEvaluation Model=GPT-4o-mini2026.03 | 1.09 | — | |
| TDA-RCEvaluation Model=GPT-4o-mini2026.03 | 1.16 | — | |
| Role / Persona PromptingEvaluation Model=GPT-4o-mini2026.03 | 1.19 | — | |
| Instruction InductionEvaluation Model=GPT-4o-mini2026.03 | 1.22 | — | |
| Prompt CanvasEvaluation Model=GPT-4o-mini2026.03 | 1.22 | — | |
| HoTEvaluation Model=GPT-4o-mini2026.03 | 1.31 | — | |
| Self-RefineEvaluation Model=GPT-4o-mini2026.03 | 2.91 | — | |
| AoTEvaluation Model=GPT-4o-mini2026.03 | 3.82 | — | |
| AFlowEvaluation Model=GPT-4o-mini2026.03 | 5.13 | — | |
| CoT-SCEvaluation Model=GPT-4o-mini, n=52026.03 | 5.26 | — | |
| ToTEvaluation Model=GPT-4o-mini2026.03 | 7.61 | — | |
| GoTEvaluation Model=GPT-4o-mini2026.03 | 7.83 | — | |
| FoTEvaluation Model=GPT-4o-mini, n=82026.03 | 8.22 | — |