Zero-shot classification AI Models

Models listed

25

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

Zero-shot classification 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.

Zero-shot classification model list

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

25 models
ModelCapabilityContextInput $/1MOutput $/1MSpeed
cross-encoder/nli-deberta-v3-base
cross-encoder
5.0
cross-encoder/nli-deberta-v3-large
cross-encoder
5.0
cross-encoder/nli-deberta-v3-small
cross-encoder
5.0
cross-encoder/nli-deberta-v3-xsmall
cross-encoder
5.0
cross-encoder/nli-distilroberta-base
cross-encoder
5.0
cross-encoder/nli-MiniLM2-L6-H768
cross-encoder
5.0
facebook/bart-large-mnli
facebook
5.0
joeddav/bart-large-mnli-yahoo-answers
joeddav
5.0
joeddav/xlm-roberta-large-xnli
joeddav
5.0
knowledgator/gliclass-large-v1.0
knowledgator
5.0
MoritzLaurer/bge-m3-zeroshot-v2.0
MoritzLaurer
5.0
MoritzLaurer/DeBERTa-v3-base-mnli-fever-anli
MoritzLaurer
5.0
MoritzLaurer/deberta-v3-base-zeroshot-v1.1-all-33
MoritzLaurer
5.0
MoritzLaurer/deberta-v3-base-zeroshot-v2.0
MoritzLaurer
5.0
MoritzLaurer/DeBERTa-v3-large-mnli-fever-anli-ling-wanli
MoritzLaurer
5.0
MoritzLaurer/deberta-v3-large-zeroshot-v1
MoritzLaurer
5.0
MoritzLaurer/deberta-v3-large-zeroshot-v2.0
MoritzLaurer
5.0
MoritzLaurer/DeBERTa-v3-xsmall-mnli-fever-anli-ling-binary
MoritzLaurer
5.0
MoritzLaurer/deberta-v3-xsmall-zeroshot-v1.1-all-33
MoritzLaurer
5.0
MoritzLaurer/mDeBERTa-v3-base-mnli-xnli
MoritzLaurer
5.0
MoritzLaurer/mDeBERTa-v3-base-xnli-multilingual-nli-2mil7
MoritzLaurer
5.0
MoritzLaurer/multilingual-MiniLMv2-L12-mnli-xnli
MoritzLaurer
5.0
typeform/distilbert-base-uncased-mnli
typeform
5.0
valhalla/distilbart-mnli-12-1
valhalla
5.0
Xenova/bart-large-mnli
Xenova
5.0

25 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.

Zero-shot classification 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.