Travel Planning Agent on TravelPlanner
0.833Commonsense Score (CS)MACLA
Evaluation Results
| Method | Links | |
|---|---|---|
| MACLARefinement Category=Process Refinement, Backbone=Llama-2-7B2025.12 | 0.833 | |
| GPT-4Refinement Category=Prompt-based, Backbone=GPT-42025.12 | 0.719 | |
| Claude-3.5-SonnetRefinement Category=Process Refinement, Backbone=Claude-3.5-Sonnet, Scale=Proprietary2025.12 | 0.655 | |
| Qwen2.5-72BRefinement Category=Process Refinement, Backbone=Qwen2.5-72B, Scale=72B2025.12 | 0.638 |