Sentence similarity 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

Sentence similarity 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.

Sentence similarity model list

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

50 models
ModelCapabilityContextInput $/1MOutput $/1MSpeed
Alibaba-NLP/gte-large-en-v1.5
Alibaba-NLP
8.78.2K$0.09$0.00
BAAI/bge-m3
BAAI
8.58.2K$0.02$0.00
Alibaba-NLP/gte-multilingual-base
Alibaba-NLP
5.0
Alibaba-NLP/gte-Qwen2-1.5B-instruct
Alibaba-NLP
5.0
bkai-foundation-models/vietnamese-bi-encoder
bkai-foundation-models
5.0
cl-nagoya/ruri-v3-310m
cl-nagoya
5.0
datasocietyco/bge-base-en-v1.5-course-recommender-v5
datasocietyco
5.0
google/embeddinggemma-300m
google
5.0
intfloat/e5-base
intfloat
5.0
intfloat/e5-base-v2
intfloat
5.0
intfloat/e5-large-v2
intfloat
5.0512$0.02$0.00
intfloat/e5-small-v2
intfloat
5.0
intfloat/multilingual-e5-base
intfloat
5.0
intfloat/multilingual-e5-small
intfloat
5.0
jhgan/ko-sroberta-multitask
jhgan
5.0
NeuML/pubmedbert-base-embeddings
NeuML
5.0
nomic-ai/nomic-embed-text-v1
nomic-ai
5.0
nomic-ai/nomic-embed-text-v1.5
nomic-ai
5.0
nomic-ai/nomic-embed-text-v2-moe
nomic-ai
5.0
Qdrant/all-MiniLM-L6-v2-onnx
Qdrant
5.0
Qdrant/bge-small-en-v1.5-onnx-Q
Qdrant
5.0
Qdrant/bm25
Qdrant
5.0
Qwen/Qwen3-VL-Embedding-2B
Qwen
5.0
Qwen/Qwen3-VL-Embedding-8B
Qwen
5.0
sentence-transformers/all-distilroberta-v1
sentence-transformers
5.0
sentence-transformers/all-MiniLM-L12-v2
sentence-transformers
5.0
sentence-transformers/all-MiniLM-L6-v2
sentence-transformers
5.0
sentence-transformers/all-mpnet-base-v2
sentence-transformers
5.0
sentence-transformers/all-roberta-large-v1
sentence-transformers
5.0
sentence-transformers/distiluse-base-multilingual-cased-v1
sentence-transformers
5.0
sentence-transformers/distiluse-base-multilingual-cased-v2
sentence-transformers
5.0
sentence-transformers/LaBSE
sentence-transformers
5.0
sentence-transformers/msmarco-bert-base-dot-v5
sentence-transformers
5.0
sentence-transformers/multi-qa-MiniLM-L6-cos-v1
sentence-transformers
5.0
sentence-transformers/multi-qa-mpnet-base-dot-v1
sentence-transformers
5.0512$0.01$0.00
sentence-transformers/paraphrase-MiniLM-L3-v2
sentence-transformers
5.0
sentence-transformers/paraphrase-MiniLM-L6-v2
sentence-transformers
5.0
sentence-transformers/paraphrase-mpnet-base-v2
sentence-transformers
5.0
sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
sentence-transformers
5.0
sentence-transformers/paraphrase-multilingual-mpnet-base-v2
sentence-transformers
5.0
sentence-transformers-testing/stsb-bert-tiny-safetensors
sentence-transformers-testing
5.0
shibing624/text2vec-base-chinese
shibing624
5.0
Snowflake/snowflake-arctic-embed-l-v2.0
Snowflake
5.0
Snowflake/snowflake-arctic-embed-s
Snowflake
5.0
Snowflake/snowflake-arctic-embed-xs
Snowflake
5.0
snunlp/KR-SBERT-V40K-klueNLI-augSTS
snunlp
5.0
TaylorAI/bge-micro-v2
TaylorAI
5.0
thenlper/gte-base
thenlper
5.0
thenlper/gte-large
thenlper
5.0
thenlper/gte-small
thenlper
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.

Sentence similarity 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.