Opensearch Neural Sparse Encoding Multilingual v1 measured on 8 of 194 Embeddings benchmarks8
BenchmarkByScoreRank
No benchmark matches
price not verifiedprice
34.8MTEB Korean v2
Feb 2025released
1K tokensMax input
en, es, fr +12Languages
Alternatives?
ModelScoreCostPriceWhat changes
BetterQwen 3 Embedding 8BunstatedOpen+41%—$0.01Languages: not verified+1BetterQwen 3 Embedding 0.6BunstatedOpen+24%—$0.01Languages: not verified+1iBetterMultilingual E5 Large InstructunstatedOpen+19%—$0.01Memory (4-bit): 0.1 GB → 0.3 GBBetterQwen 3 Embedding 4BunstatedOpen+37%—$0.02Languages: not verified+1iBetterE5 Mistral 7B InstructunstatedOpen+21%—$0.022Languages: loses es, fr, zh +11+1ModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
Qwen 3 Embedding 8BunstatedOpen+41%—$0.01Languages: not verified+1Qwen 3 Embedding 0.6BunstatedOpen+24%—$0.01Languages: not verified+1iMultilingual E5 Large InstructunstatedOpen+19%—$0.01Memory (4-bit): 0.1 GB → 0.3 GBQwen 3 Embedding 4BunstatedOpen+37%—$0.02Languages: not verified+1iE5 Mistral 7B InstructunstatedOpen+21%—$0.022Languages: loses es, fr, zh +11+1ModelScoreCostPriceWhat changes
Qwen 3 Embedding 8BunstatedOpen+41%—$0.01Languages: not verified+1Qwen 3 Embedding 4BunstatedOpen+37%—$0.02Languages: not verified+1NKo Embed NliOpen+35%——Languages: loses en, es, fr +11+1Qwen 3 Embedding 0.6BunstatedOpen+24%—$0.01Languages: not verified+1cF2LLM v2 8BunstatedOpen+22%——Memory (4-bit): 0.1 GB → 4.5 GBModelScoreCostPriceWhat changes
oOpensearch Neural Sparse Encoding v2 DistillOpen-6%——Languages: loses es, fr, zh +11oOpensearch Neural Sparse Encoding Doc v3 GteOpenn/a——Languages: loses es, fr, zh +11oOpensearch Neural Sparse Encoding Doc v3 DistillOpenn/a——Languages: loses es, fr, zh +11oOpensearch Neural Sparse Encoding Doc v2 MiniOpenn/a——Languages: loses es, fr, zh +11oOpensearch Neural Sparse Encoding Doc v2 DistillOpenn/a——Languages: loses es, fr, zh +11All 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 & RetrievalFAQ
How much does Opensearch Neural Sparse Encoding Multilingual v1 cost?›
There is no per-unit API price: price not verified.
How good is Opensearch Neural Sparse Encoding Multilingual v1, and what is it best at?›
#66 of 156 in Embeddings.
Is Opensearch Neural Sparse Encoding Multilingual v1 better than Potion Multilingual 128M?›
On MTEB Korean v2 · Pair Classification · Korean, Opensearch Neural Sparse Encoding Multilingual v1 scores 54.8 vs 56.1 — lower.
When was Opensearch Neural Sparse Encoding Multilingual v1 released? Is there a newer version?›
Released 2025-02-21. It is the current version in its line.
Is Opensearch Neural Sparse Encoding Multilingual v1 open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Opensearch Neural Sparse Encoding Multilingual v1 locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is Opensearch Neural Sparse Encoding Multilingual v1?›
Opensearch Neural Sparse Encoding Multilingual v1 is an open-weights embeddings & retrieval model from opensearch-project, released Feb 2025.
What are the best alternatives to Opensearch Neural Sparse Encoding Multilingual v1?›
Qwen 3 Embedding 8B (better).