ARB: A Comprehensive Arabic Multimodal Reasoning Benchmark

TL;DR

The paper introduces ARB, a new benchmark for evaluating step-by-step multimodal reasoning in Arabic, addressing a significant gap in multilingual AI evaluation and highlighting challenges in coherence and cultural grounding.

Contribution

It presents the first comprehensive Arabic multimodal reasoning benchmark, including diverse domains, reasoning steps, and an evaluation framework for AI models.

Findings

Persistent challenges in coherence and faithfulness among models.

Models struggle with cultural grounding in Arabic.

ARB enables diagnosis of multimodal reasoning in Arabic.

Abstract

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