Problem Solving on List Function (test)
203AccuracyHCoT(Split-16+8)
Evaluation Results
| Method | Links | |
|---|---|---|
| HCoT(Split-16+8)Base-model=DeepSeek R1, Problem-solving approach=HCoT(Split-16+8)2026.04 | 203 | |
| HCoT(24-solutions)Base-model=DeepSeek R1, Problem-solving approach=HCoT(24-solutions)2026.04 | 198 | |
| HCoT(24-solutions-best-of-2)Base-model=DeepSeek R1, Problem-solving approach=HCoT(24-solutions-best-of-2)2026.04 | 197 | |
| HCoT(Split-12+12)Base-model=DeepSeek R1, Problem-solving approach=HCoT(Split-12+12)2026.04 | 195 | |
| HCoT(16-solutions)Base-model=DeepSeek R1, Problem-solving approach=HCoT(16-solutions)2026.04 | 194 | |
| IO-PromptBase-model=DeepSeek R1, Problem-solving approach=IO-Prompt2026.04 | 190 | |
| Auto CoT-PromptBase-model=DeepSeek R1, Problem-solving approach=Auto CoT-Prompt2026.04 | 183 | |
| HCoT(Split-12+12)Base-model=DeepSeek V3, Problem-solving approach=HCoT(Split-12+12)2026.04 | 178 | |
| HCoT(Split-16+8)Base-model=DeepSeek V3, Problem-solving approach=HCoT(Split-16+8)2026.04 | 173 | |
| HCoT(24-solutions-best-of-2)Base-model=DeepSeek V3, Problem-solving approach=HCoT(24-solutions-best-of-2)2026.04 | 166 | |
| HCoT(24-solutions)Base-model=DeepSeek V3, Problem-solving approach=HCoT(24-solutions)2026.04 | 165 | |
| HCoT(16-solutions)Base-model=DeepSeek V3, Problem-solving approach=HCoT(16-solutions)2026.04 | 163 | |
| ToT-PromptBase-model=DeepSeek V3, Problem-solving approach=ToT-Prompt2026.04 | 161 | |
| IO-PromptBase-model=DeepSeek V3, Problem-solving approach=IO-Prompt2026.04 | 151 | |
| Auto CoT-PromptBase-model=DeepSeek V3, Problem-solving approach=Auto CoT-Prompt2026.04 | 151 | |
| ToT-PromptBase-model=DeepSeek R1, Problem-solving approach=ToT-Prompt2026.04 | 136 | |
| HCoT(Split-16+8)Base-model=GPT-4o-2024-08-06, Problem-solving approach=HCoT(Split-16+8)2026.04 | 108 | |
| HCoT(16-solutions)Base-model=GPT-4o-2024-08-06, Problem-solving approach=HCoT(16-solutions)2026.04 | 106 | |
| HCoT(Split-12+12)Base-model=GPT-4o-2024-08-06, Problem-solving approach=HCoT(Split-12+12)2026.04 | 102 | |
| HCoT(24-solutions)Base-model=GPT-4o-2024-08-06, Problem-solving approach=HCoT(24-solutions)2026.04 | 98 | |
| HCoT(24-solutions-best-of-2)Base-model=GPT-4o-2024-08-06, Problem-solving approach=HCoT(24-solutions-best-of-2)2026.04 | 98 | |
| Auto CoT-PromptBase-model=GPT-4o-2024-08-06, Problem-solving approach=Auto CoT-Prompt2026.04 | 92 | |
| IO-PromptBase-model=GPT-4o-2024-08-06, Problem-solving approach=IO-Prompt2026.04 | 87 | |
| ToT-PromptBase-model=GPT-4o-2024-08-06, Problem-solving approach=ToT-Prompt2026.04 | 87 |