List your company

Travel Planning Agent on TravelPlanner

0.833Commonsense Score (CS)MACLA
0.63020.682850.73550.78815Dec 22, 2025

Evaluation results

MethodLinks
MACLARefinement Category=Process Refinement, Backbone=Llama-2-7B2025.120.833
GPT-4Refinement Category=Prompt-based, Backbone=GPT-42025.120.719
Claude-3.5-SonnetRefinement Category=Process Refinement, Backbone=Claude-3.5-Sonnet, Scale=Proprietary2025.120.655
Qwen2.5-72BRefinement Category=Process Refinement, Backbone=Qwen2.5-72B, Scale=72B2025.120.638