Opensearch Neural Sparse Encoding Doc v3 Gte measured on 3 of 261 Embeddings benchmarks3
BenchmarkByScoreRank
No benchmark matches
self-host onlyprice
52.7BEIR
Jun 2025released
768Dimensions
8K tokensMax input
enLanguages
Alternatives?
ModelScoreCostPriceWhat changes
BetterQwen 3 Embedding 8BunstatedOpen+19%—$0.01Languages: not verified+1
OpenNV Embed v2unstated+20%——Memory (4-bit): 0.1 GB → 4.7 GB
BetterBge En IclunstatedOpen+18%—$0.01Languages: not verified+1BetterQwen 3 Embedding 0.6BunstatedOpen+5%—$0.01Languages: not verified+1BetterQwen 3 Embedding 4BunstatedOpen+17%—$0.02Languages: not verified+1ModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
Qwen 3 Embedding 8BunstatedOpen+19%—$0.01Languages: not verified+1Bge En IclunstatedOpen+18%—$0.01Languages: not verified+1Qwen 3 Embedding 0.6BunstatedOpen+5%—$0.01Languages: not verified+1Qwen 3 Embedding 4BunstatedOpen+17%—$0.02Languages: not verified+1iE5 Mistral 7B InstructunstatedOpen+8%—$0.022Memory (4-bit): 0.1 GB → 4.3 GBModelScoreCostPriceWhat changes
NV Embed v2unstatedOpen+20%——Memory (4-bit): 0.1 GB → 4.7 GBQwen 3 Embedding 8BunstatedOpen+19%—$0.01Languages: not verified+1Bge En IclunstatedOpen+18%—$0.01Languages: not verified+1yLENS D8000unstatedOpen+17%——Languages: not verified+1iInf Retriever v1unstatedOpen+17%——Memory (4-bit): 0.1 GB → 4.2 GBModelScoreCostPriceWhat changes
oOpensearch Neural Sparse Encoding Doc v3 DistillOpen-5%——Max input: 8K tokens → 1K tokensoOpensearch Neural Sparse Encoding Doc v2 DistillOpen-7%——Max input: 8K tokens → 1K tokensoOpensearch Neural Sparse Encoding Doc v2 MiniOpen-9%——Max input: 8K tokens → 1K tokensAll opensearch-project models →Run it yourself
estimateFits on✓ 8 GB (phone, laptop) · full quality✓ 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 & RetrievalBEIR · Retrieval · English52.7#71
FAQ
How much does Opensearch Neural Sparse Encoding Doc v3 Gte cost?›
There is no per-unit API price: self-host only.
Is Opensearch Neural Sparse Encoding Doc v3 Gte free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is Opensearch Neural Sparse Encoding Doc v3 Gte, and what is it best at?›
#69 of 194 in Embeddings.
Is Opensearch Neural Sparse Encoding Doc v3 Gte better than Multilingual E5 Large Instruct?›
On BEIR · Mean over tasks · English, Opensearch Neural Sparse Encoding Doc v3 Gte scores 52.7 vs 52.7 — about the same.
When was Opensearch Neural Sparse Encoding Doc v3 Gte released? Is there a newer version?›
Released 2025-06-18. It is the current version in its line.
Is Opensearch Neural Sparse Encoding Doc v3 Gte open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Opensearch Neural Sparse Encoding Doc v3 Gte locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is Opensearch Neural Sparse Encoding Doc v3 Gte?›
Opensearch Neural Sparse Encoding Doc v3 Gte is an open-weights embeddings & retrieval model from opensearch-project, released Jun 2025.
What are the best alternatives to Opensearch Neural Sparse Encoding Doc v3 Gte?›
Qwen 3 Embedding 8B (better), NV Embed v2 (open weights).