Fill-mask AI Models

Models listed

50

Published 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

Fill-mask 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.

Fill-mask model list

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

50 models
albert/albert-base-v2
albert
0.0————
almanach/camembert-base
almanach
0.0————
answerdotai/ModernBERT-base
answerdotai
0.0————
answerdotai/ModernBERT-large
answerdotai
0.0————
aubmindlab/bert-base-arabertv02
aubmindlab
0.0————
biohub/ESMC-6B
biohub
0.0————
dascim/juribert-base
dascim
0.0————
dccuchile/bert-base-spanish-wwm-uncased
dccuchile
0.0————
distilbert/distilbert-base-cased
distilbert
0.0————
distilbert/distilbert-base-german-cased
distilbert
0.0————
distilbert/distilbert-base-multilingual-cased
distilbert
0.0————
distilbert/distilbert-base-uncased
distilbert
0.0————
distilbert/distilroberta-base
distilbert
0.0————
emilyalsentzer/Bio_ClinicalBERT
emilyalsentzer
0.0————
emilyalsentzer/Bio_Discharge_Summary_BERT
emilyalsentzer
0.0————
facebook/esm2_t12_35M_UR50D
facebook
0.0————
facebook/esm2_t33_650M_UR50D
facebook
0.0————
facebook/esm2_t36_3B_UR50D
facebook
0.0————
facebook/esm2_t6_8M_UR50D
facebook
0.0————
FacebookAI/roberta-base
FacebookAI
0.0————
FacebookAI/roberta-large
FacebookAI
0.0————
FacebookAI/xlm-roberta-base
FacebookAI
0.0————
FacebookAI/xlm-roberta-large
FacebookAI
0.0————
google-bert/bert-base-cased
google-bert
0.0————
google-bert/bert-base-chinese
google-bert
0.0————
google-bert/bert-base-german-cased
google-bert
0.0————
google-bert/bert-base-multilingual-cased
google-bert
0.0————
google-bert/bert-base-multilingual-uncased
google-bert
0.0————
google-bert/bert-base-uncased
google-bert
0.0————
google-bert/bert-large-cased
google-bert
0.0————
google-bert/bert-large-uncased
google-bert
0.0————
hfl/chinese-bert-wwm
hfl
0.0————
jhu-clsp/mmBERT-base
jhu-clsp
0.0————
julien-c/dummy-unknown
julien-c
0.0————
ku-nlp/deberta-v2-large-japanese-char-wwm
ku-nlp
0.0————
microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract
Microsoft Research
0.0————
microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext
Microsoft Research
0.0————
microsoft/deberta-base
Microsoft Research
0.0————
microsoft/deberta-v3-base
Microsoft Research
0.0————
microsoft/deberta-v3-large
Microsoft Research
0.0————
microsoft/deberta-v3-small
Microsoft Research
0.0————
microsoft/mdeberta-v3-base
Microsoft Research
0.0————
neuralmind/bert-base-portuguese-cased
neuralmind
0.0————
neuralmind/bert-large-portuguese-cased
neuralmind
0.0————
rinna/japanese-roberta-base
rinna
0.0————
tohoku-nlp/bert-base-japanese
tohoku-nlp
0.0————
tohoku-nlp/bert-base-japanese-char-v2
tohoku-nlp
0.0————
tohoku-nlp/bert-base-japanese-whole-word-masking
tohoku-nlp
0.0————
yikuan8/Clinical-Longformer
yikuan8
0.0————
yiyanghkust/finbert-pretrain
yiyanghkust
0.0————

1–50 of 50 models · select a column to sort

About this order: Recommended shows our editorial shortlist first, followed by recent releases. The spec score is 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.

Fill-mask 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.