Bge En Icl
Jul 2024
Bge En IclCompare inon
Bge En Icl measured on 6 of 261 Embeddings benchmarks6
BenchmarkByScoreRank
No benchmark matches
Alternatives?
ModelScoreCostPriceWhat changes
sCheaperAll Mpnet Base v2unstatedOpensame-50%$0.005Max input: 33K tokens → 0K tokens
BetterQwen 3 Embedding 8BunstatedOpen+8%same$0.01Memory (4-bit): 4.3 GB → 4.5 GBIOpenYuan Embedding 2.0 Enunstated+11%——sCheaperAll MiniLM L12 v2unstatedOpensame-50%$0.005Max input: 33K tokens → 0K tokens
CheaperEmbeddingGemma 300MunstatedOpensame-80%$0.002Max input: 33K tokens → 2K tokensModelScoreCostPriceWhat changes
sAll Mpnet Base v2unstatedOpensame-50%$0.005Max input: 33K tokens → 0K tokenssAll MiniLM L12 v2unstatedOpensame-50%$0.005Max input: 33K tokens → 0K tokensEmbeddingGemma 300MunstatedOpensame-80%$0.002Max input: 33K tokens → 2K tokenstGte BaseunstatedOpensame-50%$0.005Max input: 33K tokens → 1K tokenssAll MiniLM L6 v2unstatedOpensame-50%$0.005Max input: 33K tokens → 0K tokensModelScoreCostPriceWhat changes
Qwen 3 Embedding 8BunstatedOpen+8%same$0.01Memory (4-bit): 4.3 GB → 4.5 GBQwen 3 Embedding 4BunstatedOpen+6%+100%$0.02VVoyage Large 2 Instructunstated+5%+1,100%$0.12Max input: 33K tokens → 16K tokensIYuan Embedding 2.0 EnunstatedOpen+11%——KQZhou EmbeddingunstatedOpen+8%——ModelScoreCostPriceWhat changes
IYuan Embedding 2.0 EnunstatedOpen+11%——KQZhou EmbeddingunstatedOpen+8%——Qwen 3 Embedding 8BunstatedOpen+8%same$0.01Memory (4-bit): 4.3 GB → 4.5 GBQwen 3 Embedding 4BunstatedOpen+6%+100%$0.02iJasper Token Compression 600MunstatedOpen+6%——ModelScoreCostPriceWhat changes
Bge Large En v1.5unstatedOpensamesame$0.01Max input: 33K tokens → 1K tokensBge Multilingual Gemma2unstatedOpensame+1,022%$0.11Max input: 33K tokens → 8K tokens+1Bge Large EnunstatedOpensame——Max input: 33K tokens → 1K tokensBge Small En v1.5unstatedOpensame+100%$0.02Max input: 33K tokens → 1K tokensBge Base En v1.5unstatedOpen-3%-50%$0.005Max input: 33K tokens → 1K tokensBge Base EnunstatedOpen-3%——Max input: 33K tokens → 1K tokensBge Small EnunstatedOpen-3%——Max input: 33K tokens → 1K tokensBge M3unstatedOpenn/a—$0.01Max input: 33K tokens → 8K tokensAll BAAI models →Run it yourself
estimateFits on✓ 8 GB (phone, laptop) · 8-bit✓ 16 GB · full quality✓ 24 GB GPU · full quality✓ 48 GB GPU · full quality✓ 80 GB GPU · full quality
LicenceApache-2.0free for commercial use
Benchmarks
in Embeddings & RetrievalFAQ
How much does Bge En Icl cost?›
$0.01 per 1M tokens.
Is Bge En Icl free to use?›
There is no free API; the cheapest paid price is $0.01 per 1M input tokens. The weights are open, so you can run it yourself.
How good is Bge En Icl, and what is it best at?›
#14 of 238 in Embeddings.
Is Bge En Icl better than F2LLM 0.6B?›
On MTEB English v2 · Reranking · English, Bge En Icl scores 47.9 vs 47.9 — about the same.
How can I use Bge En Icl?›
Through the BAAI API.
When was Bge En Icl released? Is there a newer version?›
Released 2024-07-25. It is the current version in its line.
Is Bge En Icl open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Bge En Icl locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is Bge En Icl?›
Bge En Icl is an open-weights embeddings & retrieval model from BAAI, released Jul 2024.
What are the best alternatives to Bge En Icl?›
All Mpnet Base v2 (cheaper), Qwen 3 Embedding 8B (better), Yuan Embedding 2.0 En (open weights).