Counterfactual Reasoning on MMLU-CF
71.6EMGHS-TDA
Evaluation Results
| Method | Links | |
|---|---|---|
| GHS-TDABackbone=GPT-4o-mini2026.02 | 71.6 | |
| GHS-TDABackbone=DeepSeek-V32026.02 | 71.6 | |
| CoT-SCBackbone=DeepSeek-V3, Reasoning Paradigm=chain-based, n=52026.02 | 71.5 | |
| GHS-TDABackbone=Qwen-Turbo2026.02 | 71.2 | |
| CoT-SCBackbone=GPT-4o-mini, Reasoning Paradigm=chain-based, n=52026.02 | 71.1 | |
| AoTBackbone=GPT-4o-mini, Reasoning Paradigm=atomic reasoning2026.02 | 70.9 | |
| CoT-SCBackbone=Qwen-Turbo, Reasoning Paradigm=chain-based, n=52026.02 | 70.8 | |
| AoTBackbone=DeepSeek-V3, Reasoning Paradigm=atomic reasoning2026.02 | 70.8 | |
| FoTBackbone=GPT-4o-mini, Reasoning Paradigm=forest-based, n=82026.02 | 70.6 | |
| AoTBackbone=Qwen-Turbo, Reasoning Paradigm=atomic reasoning2026.02 | 70.5 | |
| FoTBackbone=DeepSeek-V3, Reasoning Paradigm=forest-based, n=82026.02 | 70.5 | |
| FoTBackbone=Qwen-Turbo, Reasoning Paradigm=forest-based, n=82026.02 | 70.4 | |
| ToTBackbone=DeepSeek-V3, Reasoning Paradigm=tree-based2026.02 | 70.4 | |
| GoTBackbone=DeepSeek-V3, Reasoning Paradigm=graph-based2026.02 | 70.3 | |
| GoTBackbone=GPT-4o-mini, Reasoning Paradigm=graph-based2026.02 | 70.2 | |
| GoTBackbone=Qwen-Turbo, Reasoning Paradigm=graph-based2026.02 | 70.1 | |
| Self-RefineBackbone=DeepSeek-V3, Reasoning Paradigm=chain-based2026.02 | 70.1 | |
| ToTBackbone=GPT-4o-mini, Reasoning Paradigm=tree-based2026.02 | 69.9 | |
| CoTBackbone=DeepSeek-V3, Reasoning Paradigm=chain-based2026.02 | 69.9 | |
| AFlowBackbone=DeepSeek-V3, Reasoning Paradigm=search-based2026.02 | 69.8 | |
| Self-RefineBackbone=GPT-4o-mini, Reasoning Paradigm=chain-based2026.02 | 69.7 | |
| CoTBackbone=GPT-4o-mini, Reasoning Paradigm=chain-based2026.02 | 69.6 | |
| ToTBackbone=Qwen-Turbo, Reasoning Paradigm=tree-based2026.02 | 69.6 | |
| AFlowBackbone=GPT-4o-mini, Reasoning Paradigm=search-based2026.02 | 69.5 | |
| Self-RefineBackbone=Qwen-Turbo, Reasoning Paradigm=chain-based2026.02 | 69.5 | |
| CoTBackbone=Qwen-Turbo, Reasoning Paradigm=chain-based2026.02 | 69.4 | |
| AFlowBackbone=Qwen-Turbo, Reasoning Paradigm=search-based2026.02 | 69.3 | |
| Analogical PromptingBackbone=DeepSeek-V3, Reasoning Paradigm=chain-based2026.02 | 66.1 | |
| Analogical PromptingBackbone=GPT-4o-mini, Reasoning Paradigm=chain-based2026.02 | 65.8 | |
| Analogical PromptingBackbone=Qwen-Turbo, Reasoning Paradigm=chain-based2026.02 | 65.2 |