Spaces:

MIRAGE-Benchmark
/

README

Running

vdongre2 commited on Jul 1, 2025

Commit

47d1d16

verified ·

1 Parent(s): 8d5bc26

Update README.md

Files changed (1) hide show

README.md CHANGED Viewed

@@ -7,4 +7,7 @@ sdk: static
 pinned: false
 ---
-Edit this `README.md` markdown file to author your organization card.

 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