Table 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

Table 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.

Table 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
AIAT/Kiddee-qatable1
AIAT
5.0
benschlagman/tapas_fine_tuning
benschlagman
5.0
google/tapas-base-finetuned-sqa
google
5.0
google/tapas-base-finetuned-wikisql-supervised
google
5.0
google/tapas-base-finetuned-wtq
google
5.0
google/tapas-large-finetuned-sqa
google
5.0
google/tapas-large-finetuned-wikisql-supervised
google
5.0
google/tapas-large-finetuned-wtq
google
5.0
google/tapas-medium-finetuned-sqa
google
5.0
google/tapas-medium-finetuned-wikisql-supervised
google
5.0
google/tapas-medium-finetuned-wtq
google
5.0
google/tapas-mini-finetuned-sqa
google
5.0
google/tapas-mini-finetuned-wtq
google
5.0
google/tapas-small-finetuned-sqa
google
5.0
google/tapas-small-finetuned-wikisql-supervised
google
5.0
google/tapas-small-finetuned-wtq
google
5.0
google/tapas-tiny-finetuned-sqa
google
5.0
google/tapas-tiny-finetuned-wtq
google
5.0
Jonah-M/ProTrix-Q5_K_M-GGUF
Jonah-M
5.0
juliagsy/tapas_fine_tuning
juliagsy
5.0
lysandre/tapas-temporary-repo
lysandre
5.0
lysandre/tiny-tapas-random-sqa
lysandre
5.0
lysandre/tiny-tapas-random-wtq
lysandre
5.0
Mazenz/DeepAnalyze-8B-Q8_0-GGUF
Mazenz
5.0
MichiganNLP/TAMA-QWen2.5
MichiganNLP
5.0
MichiganNLP/TAMA-QWen3
MichiganNLP
5.0
microsoft/tapex-base
microsoft
5.0
microsoft/tapex-base-finetuned-wikisql
microsoft
5.0
microsoft/tapex-base-finetuned-wtq
microsoft
5.0
microsoft/tapex-large
microsoft
5.0
microsoft/tapex-large-finetuned-tabfact
microsoft
5.0
microsoft/tapex-large-finetuned-wikisql
microsoft
5.0
microsoft/tapex-large-finetuned-wtq
microsoft
5.0
microsoft/tapex-large-sql-execution
microsoft
5.0
mradermacher/tablemind-qwen2.5-1.5b-GGUF
mradermacher
5.0
neulab/omnitab-large
neulab
5.0
neulab/omnitab-large-16shot
neulab
5.0
neulab/omnitab-large-finetuned-wtq
neulab
5.0
nielsr/tapex-large-finetuned-wtq
nielsr
5.0
pkupie/ProTrix
pkupie
5.0
QuantFactory/TableLLM-13b-GGUF
QuantFactory
5.0
rizki-syazali/tapasid_finetuned_itqa
rizki-syazali
5.0
samandar1105/tablemind-qwen2.5-1.5b
samandar1105
5.0
vahrush/NTB_probe_sec
vahrush
5.0
vaishali/multitabqa-base
vaishali
5.0
vaishali/multitabqa-base-atis
vaishali
5.0
vaishali/multitabqa-base-geoquery
vaishali
5.0
vaishali/multitabqa-base-sql
vaishali
5.0
Yale-LILY/reastap-large
Yale-LILY
5.0
Yale-LILY/reastap-large-finetuned-wikisql
Yale-LILY
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.

Table 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.