Bangla language benchmark tests planning and decision making skills
BANGLAPLAN: A Benchmark for Constraint-Based Planning and Decision-Making in Bangla
Computation and Language
Summary
Planning everyday tasks like scheduling or resource sharing can be tricky, especially when there are rules to follow. The authors created BANGLAPLAN, a collection of 1,000 problems in the Bangla language that test how well computers can plan or say when something is impossible. They checked how various large language models perform at these tasks and found big differences in success. The benchmark helps measure and improve computers’ planning abilities specifically for Bangla speakers.
What this means in practice
- •For chatbot developers: Improve Bengali language assistants to plan appointments or trips respecting schedules and constraints.
- •For logistics coordinators: Use Bangla-specific benchmarks to fine-tune models for route planning and resource allocation in Bangladesh.
Authors
Md Rayhanul Masud, S M Maksudul Alam, Mohammad Jaminur Islam
Abstract
Large language models (LLMs) increasingly help users arrange appointments, plan journeys, and allocate limited resources. These tasks require models to satisfy constraints on time, cost, capacity, and order, or determine that no feasible solution exists. Bangla is the world's seventh most widely spoken language, and existing benchmarks cover many language and reasoning tasks. However, benchmarks for evaluating planning and decision-making in Bangla under explicit constraints remain lacking. We introduce BANGLAPLAN, a benchmark of 1,000 problems across ten task families grounded in everyday life and institutions in Bangladesh. It includes feasible and infeasible problems in four language registers: everyday, formal, colloquial, and Bangla--English mixed. Answers cover eight structured types, including schedules, routes, allocations, and ordered steps, in a common JSON format. We construct the benchmark through language-model-assisted drafting and independent human validation. We evaluate 11 open-weight and proprietary model configurations using exact match, separately reporting feasible-case accuracy, infeasibility detection, and format errors. We find a large performance gap: GPT-6.1 Sol achieves 98.7% accuracy and Qwen3.5-27B with thinking reaches 80.3%, while direct-answer configurations score at most 30.9%. Seven of eleven configurations perform below the always-``infeasible'' baseline. Our findings also suggest that harder problems primarily reduce plan-construction accuracy, while infeasibility detection remains more robust. BANGLAPLAN provides a reproducible basis for evaluating planning and decision-making in Bangla. BANGLAPLAN is available at: https://github.com/mrayhanulmasud/banglaplan.