List your company
ResearchFormerly WizWand

Scene Text-Centric Visual Question Answering on OCRVQA

64.4AccuracyMonkey
-0.18416.58333.3550.117Jul 23, 2024
Updated 8mo ago

Evaluation results

MethodLinks
MonkeyModel Generation Capability=Text only2024.0764.4
mPLUG-Owl2Model Generation Capability=Text only2024.0758.7
LLaVA1.5-7BModel Generation Capability=Text only2024.0758.1
TextHarmony-ChatModel Generation Capability=Text and image, Slide-LoRA=true2024.0757.6
DocPediaModel Generation Capability=Text only2024.0757.2
TextHarmonyModel Generation Capability=Text and image, Slide-LoRA=true2024.0755.3
TextHarmony*Model Generation Capability=Text and image, Slide-LoRA=false2024.0751.9
InternLM-XComposer2Model Generation Capability=Text only2024.0749.6
UniDocModel Generation Capability=Text only2024.0736.8
InternVLModel Generation Capability=Text only2024.0730.5
LLaVARModel Generation Capability=Text only2024.0724
SEED-LLaMA-14BModel Generation Capability=Text and image2024.0716.3
MM-InterleavedModel Generation Capability=Text and image2024.0711.7
MiniGPT5Model Generation Capability=Text and image2024.072.3