Visual Question Answering Vqa On

Metrics

ANLS

Results

Performance results of various models on this benchmark

Model Name	ANLS	Paper Title	Repository
GPT-3.5 + LATIN-Prompt	48.98	Layout and Task Aware Instruction Prompt for Zero-shot Document Image Question Answering	-
Gemini Ultra (pixel only)	80.3	Gemini: A Family of Highly Capable Multimodal Models	-
DUBLIN	36.82	DUBLIN -- Document Understanding By Language-Image Network	-
PaLI-X (Single-task FT)	49.2	PaLI-X: On Scaling up a Multilingual Vision and Language Model	-
Pix2Struct-base	38.2	Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding	-
PaLI-3	57.8	PaLI-3 Vision Language Models: Smaller, Faster, Stronger	-
DUBLIN (variable resolution)	42.6	DUBLIN -- Document Understanding By Language-Image Network	-
PaLI-X (Multi-task FT)	50.7	PaLI-X: On Scaling up a Multilingual Vision and Language Model	-
PaLI-X (Single-task FT w/ OCR)	54.8	PaLI-X: On Scaling up a Multilingual Vision and Language Model	-
SMoLA-PaLI-X Specialist	66.2	Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts	-
Pix2Struct-large	40	Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding	-
DocFormerv2-large	48.8	DocFormerv2: Local Features for Document Understanding	-
MatCha	37.2	MatCha: Enhancing Visual Language Pretraining with Math Reasoning and Chart Derendering	-
ChatGPT 3.5 with LAPDoc Prompt (SpatialFormat)	54.9	LAPDoc: Layout-Aware Prompting for Documents	-
Claude + LATIN-Prompt	54.51	Layout and Task Aware Instruction Prompt for Zero-shot Document Image Question Answering	-
TILT-Large	61.20	Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer	-
UDOP	47.4	Unifying Vision, Text, and Layout for Universal Document Processing	-
ScreenAI 5B (4.62 B params, w/ OCR)	65.90	ScreenAI: A Vision-Language Model for UI and Infographics Understanding	-
SMoLA-PaLI-X Generalist	65.6	Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts	-
PaLI-3 (w/ OCR)	62.4	PaLI-3 Vision Language Models: Smaller, Faster, Stronger	-

0 of 21 row(s) selected.