ARB: A Comprehensive Arabic Multimodal Reasoning Benchmark
This addresses the problem of underrepresented languages in AI evaluation for researchers and developers, though it is incremental as it extends existing benchmarking approaches to a new language.
The authors tackled the lack of benchmarks for evaluating step-by-step reasoning in Arabic multimodal AI by introducing ARB, a comprehensive benchmark spanning 11 domains with 1,356 samples and 5,119 reasoning steps, and found that 12 state-of-the-art models still struggle with coherence, faithfulness, and cultural grounding.
As Large Multimodal Models (LMMs) become more capable, there is growing interest in evaluating their reasoning processes alongside their final outputs. However, most benchmarks remain focused on English, overlooking languages with rich linguistic and cultural contexts, such as Arabic. To address this gap, we introduce the Comprehensive Arabic Multimodal Reasoning Benchmark (ARB), the first benchmark designed to evaluate step-by-step reasoning in Arabic across both textual and visual modalities. ARB spans 11 diverse domains, including visual reasoning, document understanding, OCR, scientific analysis, and cultural interpretation. It comprises 1,356 multimodal samples paired with 5,119 human-curated reasoning steps and corresponding actions. We evaluated 12 state-of-the-art open- and closed-source LMMs and found persistent challenges in coherence, faithfulness, and cultural grounding. ARB offers a structured framework for diagnosing multimodal reasoning in underrepresented languages and marks a critical step toward inclusive, transparent, and culturally aware AI systems. We release the benchmark, rubric, and evaluation suit to support future research and reproducibility. Code available at: https://github.com/mbzuai-oryx/ARB