Popular Path Search on Toro
90F1 ScoreCOMPASSLLM
Evaluation Results
| Method | Links | |
|---|---|---|
| COMPASSLLMType=LLM based, Base Model=GPT o3 mini2025.10 | 90 | |
| APEType=LLM based, Base Model=GPT o3 mini2025.10 | 89 | |
| ReActType=LLM based, Base Model=GPT o3 mini2025.10 | 87 | |
| LLM A*Type=LLM based, Base Model=GPT o3 mini2025.10 | 87 | |
| CoTType=LLM based, Base Model=GPT o3 mini2025.10 | 84 | |
| SCType=LLM based, Base Model=GPT o3 mini2025.10 | 84 | |
| ReflexionType=LLM based, Base Model=GPT o3 mini2025.10 | 81 | |
| PathGPTType=LLM based, Base Model=Llama 3.1 8b2025.10 | 76 | |
| PathGPTType=LLM based, Base Model=GPT o3 mini2025.10 | 76 | |
| NMLRType=ML/DL based2025.10 | 69 | |
| DirectType=LLM based, Base Model=GPT o3 mini2025.10 | 68 | |
| APEType=LLM based, Base Model=GPT 4o2025.10 | 65 | |
| COMPASSLLMType=LLM based, Base Model=GPT 4o2025.10 | 65 | |
| ReActType=LLM based, Base Model=GPT 4o2025.10 | 64 | |
| ReflexionType=LLM based, Base Model=GPT 4o2025.10 | 64 | |
| COMPASSLLMType=LLM based, Base Model=Llama 3.1 8b2025.10 | 62 | |
| CoTType=LLM based, Base Model=GPT 4o2025.10 | 62 | |
| MarkovType=ML/DL based2025.10 | 60 | |
| DeepAltTrip-LSTMType=ML/DL based2025.10 | 59 | |
| DeepAltTrip-SampType=ML/DL based2025.10 | 59 | |
| ReActType=LLM based, Base Model=Llama 3.1 8b2025.10 | 59 | |
| ReflexionType=LLM based, Base Model=Llama 3.1 8b2025.10 | 59 | |
| SCType=LLM based, Base Model=GPT 4o2025.10 | 59 | |
| NASRType=ML/DL based2025.10 | 58 | |
| PathGPTType=LLM based, Base Model=GPT 4o2025.10 | 58 | |
| CoTType=LLM based, Base Model=Llama 3.1 8b2025.10 | 57 | |
| SCType=LLM based, Base Model=Llama 3.1 8b2025.10 | 54 | |
| LLM A*Type=LLM based, Base Model=GPT 4o2025.10 | 54 | |
| LLM A*Type=LLM based, Base Model=Llama 3.1 8b2025.10 | 52 | |
| DirectType=LLM based, Base Model=GPT 4o2025.10 | 50 | |
| DirectType=LLM based, Base Model=Llama 3.1 8b2025.10 | 45 | |
| APEType=LLM based, Base Model=Llama 3.1 8b2025.10 | 38 |