Logical Reasoning on Deduction (test)
99.61AccuracyHBLR
Evaluation results
| Method | Links | |
|---|---|---|
| HBLRModel=DeepSeek-R1, Prompting Strategy=HBLR2025.12 | 99.61 | |
| LogicModel=DeepSeek-R1, Prompting Strategy=Logic2025.12 | 99.5 | |
| SymbCoTModel=DeepSeek-R1, Prompting Strategy=SymbCoT2025.12 | 99.03 | |
| HBLRModel=GPT-4, Prompting Strategy=HBLR2025.12 | 97.83 | |
| LogicModel=GPT-4, Prompting Strategy=Logic2025.12 | 95.99 | |
| SymbCoTModel=GPT-4, Prompting Strategy=SymbCoT2025.12 | 93 | |
| HBLRModel=DeepSeek-V3, Prompting Strategy=HBLR2025.12 | 92.63 | |
| LogicModel=DeepSeek-V3, Prompting Strategy=Logic2025.12 | 90.63 | |
| SymbCoTModel=DeepSeek-V3, Prompting Strategy=SymbCoT2025.12 | 89.91 | |
| CoTModel=DeepSeek-R1, Prompting Strategy=CoT2025.12 | 86.45 | |
| DirectModel=DeepSeek-R1, Prompting Strategy=Direct2025.12 | 76.17 | |
| CoTModel=GPT-4, Prompting Strategy=CoT2025.12 | 75.25 | |
| CoTModel=DeepSeek-V3, Prompting Strategy=CoT2025.12 | 72.67 | |
| DirectModel=GPT-4, Prompting Strategy=Direct2025.12 | 71.33 | |
| LogicModel=GPT-3.5-Turbo, Prompting Strategy=Logic2025.12 | 69.06 | |
| DirectModel=DeepSeek-V3, Prompting Strategy=Direct2025.12 | 67.25 | |
| HBLRModel=GPT-3.5-Turbo, Prompting Strategy=HBLR2025.12 | 49.77 | |
| SymbCoTModel=GPT-3.5-Turbo, Prompting Strategy=SymbCoT2025.12 | 45.85 | |
| CoTModel=GPT-3.5-Turbo, Prompting Strategy=CoT2025.12 | 43.67 | |
| DirectModel=GPT-3.5-Turbo, Prompting Strategy=Direct2025.12 | 39.15 |