Sign in to view source links and access this dataset
Description
PlanningBench is a synthetic planning benchmark and data construction framework for evaluating and training large language models. The dataset, created by Tencent, focuses on complex, text-based planning tasks that require coordinating goals, constraints, and resources. It was last updated on May 28, 2026.
Use Cases
Benchmarking LLM planning capabilities based on tasks involving goals, constraints, and resources.
Training LLMs to generate verifiable plans from textual descriptions of objectives and dependencies.
Evaluating model performance on multi-faceted planning tasks that include time windows and priorities.
Strengths
Framework is designed for generating scalable and verifiable planning data.
Focuses on a specific, complex task domain (text-based planning) for LLM evaluation.
Limitations
Description metadata is limited; actual data quality requires manual inspection after download.
Column-level documentation is absent; field semantics must be inferred after download.
Row count is unknown, which may limit suitability assessment.
Provenance
Source
Tencent (author listed as 'tencent') via Hugging Face.
Collection Method
Synthetically generated via a data construction framework.
Freshness
Last updated 2026-05-28 08:26:38; freshness should be verified.
License is unknown; terms of use must be verified on the dataset page.