Skip to content

Dataset · Qwen

DeepPlanning benchmark for agents

Qwen/DeepPlanning

Multi-day travel and shopping planning tasks with verifiable constraints for evaluating LLM agents.

What's inside

Text-based DeepPlanningBench benchmark in English and Chinese, with 1k to 10k examples. Includes realistic multi-day travel planning and multi-item shopping tasks requiring proactive information gathering, local and global constraints.

What you can do with it

  • Evaluate LLM agents on multi-day travel planning.
  • Test adherence to verifiable constraints in shopping tasks.
  • Compare models on the agent planning benchmark.
Tasks
Text generation
Languages
English, Chinese
Size
1K–10K rows
Downloads this month
11.3K
Likes
228

Models trained on it

How to load it

from datasets import load_dataset

ds = load_dataset("Qwen/DeepPlanning")