Code Generation on MBPP (Pass@1, Average)
86.95Pass@1DAAO
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| DAAOLLM=LLM Pool2025.09 | 86.95 | 83.26 | |
| MasRouterLLM=LLM Pool2025.09 | 84 | 80.66 | |
| MaASLLM=gemini-1.5-flash2025.09 | 82.69 | 80.18 | |
| MaASLLM=gpt-4o-mini2025.09 | 82.17 | 80.43 | |
| AFlowLLM=gpt-4o-mini2025.09 | 81.67 | 79.73 | |
| AFlowLLM=gemini-1.5-flash2025.09 | 76 | 77.29 | |
| ComplexCoTLLM=gpt-4o-mini2025.09 | 75.8 | 75.57 | |
| VanillaLLM=qwen-2-72b2025.09 | 73.9 | 70.05 | |
| PromptLLMLLM=LLM Pool2025.09 | 73.6 | 75.86 | |
| VanillaLLM=gemini-1.5-flash2025.09 | 73 | 74.08 | |
| CoTLLM=gemini-1.5-flash2025.09 | 73 | 74.04 | |
| SC(CoT)LLM=gpt-4o-mini2025.09 | 73 | 75.42 | |
| RouteLLMLLM=LLM Pool2025.09 | 72.6 | 75.5 | |
| VanillaLLM=gpt-4o-mini2025.09 | 72.2 | 73.89 | |
| SC(CoT)LLM=gemini-1.5-flash2025.09 | 72 | 74.13 | |
| ComplexCoTLLM=gemini-1.5-flash2025.09 | 71.8 | 73.39 | |
| CoTLLM=gpt-4o-mini2025.09 | 69.6 | 73.64 | |
| VanillaLLM=llama-3.1-70b2025.09 | 68.2 | 72.01 | |
| ADASLLM=gpt-4o-mini2025.09 | 68.13 | 72.23 | |
| ADASLLM=gemini-1.5-flash2025.09 | 68 | 72.05 |