Evaluating MLLMs with Multimodal Multi-image Reasoning Benchmark
This addresses the need for better evaluation of MLLMs in multi-image reasoning, though it is incremental as it builds on existing benchmark efforts.
The paper tackles the lack of benchmarks for evaluating Multimodal Large Language Models (MLLMs) on reasoning over multiple images by introducing the Multimodal Multi-image Reasoning Benchmark (MMRB), which includes 92 sub-tasks and shows that open-source MLLMs significantly lag behind commercial ones in these tasks.
With enhanced capabilities and widespread applications, Multimodal Large Language Models (MLLMs) are increasingly required to process and reason over multiple images simultaneously. However, existing MLLM benchmarks focus either on single-image visual reasoning or on multi-image understanding tasks with only final-answer evaluation, leaving the reasoning capabilities of MLLMs over multi-image inputs largely underexplored. To address this gap, we introduce the $\textbf{Multimodal Multi-image Reasoning Benchmark (MMRB)}$, the first benchmark designed to evaluate structured visual reasoning across multiple images. MMRB comprises $\textbf{92 sub-tasks}$ covering spatial, temporal, and semantic reasoning, with multi-solution, CoT-style annotations generated by GPT-4o and refined by human experts. A derivative subset is designed to evaluate multimodal reward models in multi-image scenarios. To support fast and scalable evaluation, we propose a sentence-level matching framework using open-source LLMs. Extensive baseline experiments on $\textbf{40 MLLMs}$, including 9 reasoning-specific models and 8 reward models, demonstrate that open-source MLLMs still lag significantly behind commercial MLLMs in multi-image reasoning tasks. Furthermore, current multimodal reward models are nearly incapable of handling multi-image reward ranking tasks.