BURMESE-SAN: Burmese NLP Benchmark for Evaluating Large Language Models

TL;DR

BURMESE-SAN is a comprehensive benchmark for evaluating large language models on Burmese language tasks, covering understanding, reasoning, and generation, and highlighting the importance of model design and fine-tuning.

Contribution

This work introduces the first holistic Burmese NLP benchmark with diverse subtasks, constructed through native speaker input, and provides a large-scale evaluation of LLMs on Burmese.

Findings

Model performance improves with regional fine-tuning and newer architectures.

Language complexity impacts model performance more than size alone.

Benchmark is publicly available for ongoing evaluation.

Abstract

We introduce BURMESE-SAN, the first holistic benchmark that systematically evaluates large language models (LLMs) for Burmese across three core NLP competencies: understanding (NLU), reasoning (NLR), and generation (NLG). BURMESE-SAN consolidates seven subtasks spanning these competencies, including Question Answering, Sentiment Analysis, Toxicity Detection, Causal Reasoning, Natural Language Inference, Abstractive Summarization, and Machine Translation, several of which were previously unavailable for Burmese. The benchmark is constructed through a rigorous native-speaker-driven process to ensure linguistic naturalness, fluency, and cultural authenticity while minimizing translation-induced artifacts. We conduct a large-scale evaluation of both open-weight and commercial LLMs to examine challenges in Burmese modeling arising from limited pretraining coverage, rich morphology, and syntactic variation. Our results show that Burmese performance depends more on architectural design, language representation, and instruction tuning than on model scale alone. In particular, Southeast Asia regional fine-tuning and newer model generations yield substantial gains. Finally, we release BURMESE-SAN as a public leaderboard to support systematic evaluation and sustained progress in Burmese and other low-resource languages. https://leaderboard.sea-lion.ai/detailed/MY