Document question answering AI Models

Models listed

50

Reviewed and live in this category

Worth weighing up

What goes in and out, licence terms, and whether you can host it yourself

How we treat data

Published specs only — we don't estimate numbers a vendor hasn't stated

Document question answering models are a source-backed task collection in this directory. The current editorial inventory contains 25 mapped model records. Task membership is a discovery signal, not a performance ranking, deployment recommendation, or proof that every checkpoint accepts the same inputs and returns the same outputs.

Start with the model list, then open each record that matches your data, operating constraints, and intended workflow. Check the primary source, documented modalities, license, release information, and implementation notes before using a model in production.

This collection keeps unsupported pricing, availability, and benchmark claims blank. Each page remains outside the public index until an editor approves its content and related model records.

Document question answering model list

Scan the table below, then open any model for pricing, limits and the full write-up.

50 models
ModelCapabilityContextInput $/1MOutput $/1MSpeed
2KKLabs/Kaleidoscope_large_v1
2KKLabs
5.0
2KKLabs/Kaleidoscope_small_v1
2KKLabs
5.0
ahirtonlopes/layoutlmv2-base-uncased_finetuned_docvqa
ahirtonlopes
5.0
am-infoweb/layoutlmv2-finetuned_docvqa
am-infoweb
5.0
am-infoweb/layoutlmv3-finetuned_docvqa
am-infoweb
5.0
AntonioTH/Layout-finetuned-fr-model-50instances20-100epochs-5e-05lr
AntonioTH
5.0
aslessor/layoutlm-invoices
aslessor
5.0
DmitrySpartak/layoutlm-invoices
DmitrySpartak
5.0
dperales/layoutlmv2-base-uncased_finetuned_docvqa
dperales
5.0
faisalraza/layoutlm-invoices
faisalraza
5.0
fimu-docproc-research/CIVQA_layoutXLM_model
fimu-docproc-research
5.0
fxmarty/tiny-doc-qa-vision-encoder-decoder
fxmarty
5.0
gozdenergiz/layoutlmv2-base-uncased_finetuned_docvqa
gozdenergiz
5.0
impira/layoutlm-document-qa
impira
5.0
impira/layoutlm-invoices
impira
5.0
jinhybr/OCR-DocVQA-Donut
jinhybr
5.0
jonathanjordan21/donut_fine_tuning_food_composition_id
jonathanjordan21
5.0
lakshya-rawat/document-qa-model
lakshya-rawat
5.0
MariaK/layoutlmv2-base-uncased_finetuned_docvqa_v2
MariaK
5.0
Mikhail1313/layoutlmv2-base-uncased_finetuned_docvqa
Mikhail1313
5.0
nafiz09/docvqa
nafiz09
5.0
naver-clova-ix/donut-base-finetuned-docvqa
naver-clova-ix
5.0
nikravan/glm-4vq
nikravan
5.0
Oksana76B/document-question-answering
Oksana76B
5.0
optimum-intel-internal-testing/tiny-doc-qa-vision-encoder-decoder
optimum-intel-internal-testing
5.0
Or4cl3-1/multimodal-fusion-optimized
Or4cl3-1
5.0
p786/donut-base-finetuned-docvqa
p786
5.0
pacman2223/univ-docu-mod
pacman2223
5.0
padalavinaybhushan/VinayParser
padalavinaybhushan
5.0
pardeepSF/layoutlm-vqa
pardeepSF
5.0
paru4ik/content
paru4ik
5.0
PrimWong/layoutlm_qa
PrimWong
5.0
rubentito/layoutlmv3-base-mpdocvqa
rubentito
5.0
SantiagoPG/DOC_QA
SantiagoPG
5.0
Sharka/CIVQA_DVQA_Impira_QA
Sharka
5.0
Sharka/CIVQA_DVQA_LayoutLMv3
Sharka
5.0
Sharka/CIVQA_LayoutXLM
Sharka
5.0
Sharka/CIVQA_LayoutXLM_EasyOCR
Sharka
5.0
tiennvcs/layoutlmv2-base-uncased-finetuned-docvqa
tiennvcs
5.0
tiennvcs/layoutlmv2-base-uncased-finetuned-infovqa
tiennvcs
5.0
tiennvcs/layoutlmv2-large-uncased-finetuned-infovqa
tiennvcs
5.0
tiennvcs/layoutlmv2-large-uncased-finetuned-vi-infovqa
tiennvcs
5.0
TusharGoel/LayoutLM-Finetuned-DocVQA
TusharGoel
5.0
TusharGoel/LayoutLMv2-finetuned-docvqa
TusharGoel
5.0
TusharGoel/LiLT-Document-QA
TusharGoel
5.0
Xenova/donut-base-finetuned-docvqa
Xenova
5.0
xhyi/layoutlmv3_docvqa_t11c5000
xhyi
5.0
YuukiAsuna/VieTable-donut-docvqa-demo
YuukiAsuna
5.0
YuukiAsuna/Vintern-1B-v2-ViTable-docvqa
YuukiAsuna
5.0
zpm/Llama-3.1-PersianQA
zpm
5.0

50 models · click a column to sort

About the capability score: a 0–100 figure SyncDev calculates from each vendor's published specifications — context window, reasoning support, input modalities, tool calling, maximum output and how recently the model shipped. It measures breadth of capability, not benchmark performance, so a higher-scoring model is not automatically the better choice for your task.

Document question answering model questions

It groups source-backed directory records for research and comparison. Review each model page and its primary documentation because collection membership alone does not prove quality, availability, or suitability.