Task Planning on Hugging Face
77.79Node-F1SGC
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| SGCLLM=GPT-4-turbo2024.05 | 77.79 | 52.2 | 2.03 | |
| DirectLLM=GPT-4-turbo2024.05 | 77.6 | 52.18 | 2.19 | |
| BeamSearchLLM=GPT-4-turbo2024.05 | 77.56 | 52.54 | 8.98 | |
| SGCLLM=GPT-3.5-turbo2024.05 | 76.37 | 50.04 | 2.02 | |
| AdaptiveSearchLLM=GPT-4-turbo2024.05 | 76.17 | 51.3 | 8.94 | |
| BeamSearchLLM=GPT-3.5-turbo2024.05 | 75.51 | 49.62 | 14.22 | |
| Greedy SearchLLM=GPT-4-turbo2024.05 | 74.75 | 50.44 | 5.78 | |
| DirectLLM=GPT-3.5-turbo2024.05 | 73.85 | 45.73 | 2.14 | |
| AdaptiveSearchLLM=GPT-3.5-turbo2024.05 | 72.18 | 47.55 | 7.47 | |
| Greedy SearchLLM=GPT-3.5-turbo2024.05 | 67.75 | 43.88 | 5.29 | |
| SGCLLM=Mistral 7B2024.05 | 67.43 | 42.08 | 2.32 | |
| AdaptiveSearchLLM=Mistral 7B2024.05 | 67.3 | 38.9 | 7.68 | |
| BeamSearchLLM=Mistral 7B2024.05 | 67.13 | 36.73 | 25.66 | |
| GreedySearchLLM=Mistral 7B2024.05 | 65.91 | 38.13 | 6.52 | |
| SGCLLM=CodeLlama 13B2024.05 | 65.51 | 39.44 | 2.31 | |
| BeamSearchLLM=CodeLlama 13B2024.05 | 62.65 | 34.31 | 20.14 | |
| Greedy SearchLLM=CodeLlama 13B2024.05 | 61.67 | 34.02 | 5.95 | |
| AdaptiveSearchLLM=CodeLlama 13B2024.05 | 60.85 | 31.66 | 11.1 | |
| DirectLLM=Mistral 7B2024.05 | 60.6 | 30.23 | 2.49 | |
| SGCLLM=Vicuna 13B2024.05 | 59.62 | 31.98 | 2.31 | |
| DirectLLM=CodeLlama 13B2024.05 | 57.55 | 28.88 | 2.45 | |
| BeamSearchLLM=Vicuna 13B2024.05 | 56.64 | 26.93 | 24.11 | |
| AdaptiveSearchLLM=Vicuna 13B2024.05 | 54.36 | 25.67 | 9.81 | |
| Greedy SearchLLM=Vicuna 13B2024.05 | 52.94 | 25.73 | 6.23 | |
| DirectLLM=Vicuna 13B2024.05 | 50.46 | 21.27 | 2.5 |