Spatial Reasoning On Embspatial Bench

Generation

Results

Performance results of various models on this benchmark

		Paper Title
SoFar	70.88	SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation
Qwen-VL-Max	49.11	Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
GPT-4V	36.07	GPT-4 Technical Report
LLaVA-1.6	35.19	Visual Instruction Tuning
MiniGPT4	23.54	MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models

0 of 5 row(s) selected.