Kai Wang

Conventional, classification-based AI-generated image detection methods cannot explain why an image is considered real or AI-generated in a way a human expert would, which reduces the trustworthiness and persuasiveness of these detection tools for real-world applications. Leveraging Multimodal Large Language Models (MLLMs) has recently become a trending solution to this issue. Further, to evaluate the quality of generated explanations, a common approach is to adopt an "MLLM as a judge" methodology to evaluate explanations generated by other MLLMs. However, how well those MLLMs perform when judging explanations for AI-generated image detection generated by themselves or other MLLMs has not been well studied. We therefore propose **XAIGID-RewardBench**, the first benchmark designed to evaluate the ability of current MLLMs to judge the quality of explanations about whether an image is real or AI-generated. The benchmark consists of approximately 4,000 annotated triplets sourced from various image generation models and MLLMs as policy models (detectors) to assess the capabilities of current MLLMs as reward models (judges). Gemini 2.5 Flash achieves the highest four-way accuracy at 68.8\%, while Qwen2.5-VL-72B-Instruct achieves the highest Both-Clear accuracy at 86.4\%; these results show that current judges remain imperfect. Our benchmark also features a 59.8\% raw four-way agreement and 87.4\% clear-winner conditional agreement between human annotators. In addition, we provide an analysis of common pitfalls that these models frequently encounter. Code and benchmark are available at https://github.com/RewardBench/XAIGID-RewardBench.