AraLingBench A Human-Annotated Benchmark for Evaluating Arabic Linguistic Capabilities of Large Language Models
This addresses the need for better diagnostic tools to assess true linguistic mastery in Arabic LLMs, though it is incremental as it builds on existing benchmarking approaches.
The researchers tackled the problem of evaluating the Arabic linguistic capabilities of large language models by creating AraLingBench, a human-annotated benchmark with 150 multiple-choice questions across five categories, and found that current models show strong surface proficiency but struggle with deeper grammatical and syntactic reasoning.
We present AraLingBench: a fully human annotated benchmark for evaluating the Arabic linguistic competence of large language models (LLMs). The benchmark spans five core categories: grammar, morphology, spelling, reading comprehension, and syntax, through 150 expert-designed multiple choice questions that directly assess structural language understanding. Evaluating 35 Arabic and bilingual LLMs reveals that current models demonstrate strong surface level proficiency but struggle with deeper grammatical and syntactic reasoning. AraLingBench highlights a persistent gap between high scores on knowledge-based benchmarks and true linguistic mastery, showing that many models succeed through memorization or pattern recognition rather than authentic comprehension. By isolating and measuring fundamental linguistic skills, AraLingBench provides a diagnostic framework for developing Arabic LLMs. The full evaluation code is publicly available on GitHub.