README.md

metadata

title: README
emoji: 🏆
colorFrom: pink
colorTo: yellow
sdk: static
pinned: false

MIRAGE: A Benchmark for Multimodal Information-Seeking and Reasoning in Agricultural Expert-Guided Conversations is a comprehensive benchmark for evaluating AI systems in multimodal consultation scenarios. The benchmark consists of two main components:

• MMST (Multi-Modal Single-Turn) - Single-turn multimodal reasoning tasks
• MMMT (Multi-Modal Multi-Turn) - Multi-turn conversational tasks with visual context