MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agents
This addresses the problem of assessing multimodal reasoning in AI agents for researchers, but it is incremental as it extends existing benchmarks.
The authors tackled the lack of multimodal evaluation for web browsing agents by introducing MM-BrowseComp, a benchmark with 224 questions requiring image and video retrieval, and found that top models like OpenAI o3 achieved only 29.02% accuracy.
AI agents with advanced reasoning and tool use capabilities have demonstrated impressive performance in web browsing for deep search. While existing benchmarks such as BrowseComp evaluate these browsing abilities, they primarily focus on textual information, overlooking the prevalence of multimodal content. To bridge this gap, we introduce MM-BrowseComp, a novel benchmark comprising 224 challenging, hand-crafted questions specifically designed to assess agents' multimodal retrieval and reasoning capabilities. These questions often incorporate images in prompts, and crucial information encountered during the search and reasoning process may also be embedded within images or videos on webpages. Consequently, methods relying solely on text prove insufficient for our benchmark. Additionally, we provide a verified checklist for each question, enabling fine-grained analysis of multimodal dependencies and reasoning paths. Our comprehensive evaluation of state-of-the-art models on MM-BrowseComp reveals that even top models like OpenAI o3 with tools achieve only 29.02\% accuracy, highlighting the suboptimal multimodal capabilities and lack of native multimodal reasoning in current models.