Zeta Alpha E5 Mistral measured on 6 of 261 Embeddings benchmarks6
BenchmarkByScoreRank
No benchmark matches
self-host onlyprice
88.3MTEB English v2
Aug 2024released
4,096Dimensions
4K tokensMax input
enLanguages
Alternatives?
ModelScoreCostPriceWhat changes
VBetterVoyage Large 2 Instructunstated+3%—$0.12Languages: not verifiedKOpenQZhou Embeddingunstated+5%——jBetterIngot 8B R3unstated+6%——Languages: not verifiedTBetterConan Embedding v2unstated+6%——iOpenJasper Token Compression 600Munstated+2%——ModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
VVoyage Large 2 Instructunstated+3%—$0.12Languages: not verifiedjIngot 8B R3unstated+6%——Languages: not verifiedTConan Embedding v2unstated+6%——KQZhou EmbeddingunstatedOpen+5%——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
LicenceMITfree for commercial use
Benchmarks
in Embeddings & RetrievalBEIR · Retrieval · English59.5#13
FAQ
How much does Zeta Alpha E5 Mistral cost?›
There is no per-unit API price: self-host only.
Is Zeta Alpha E5 Mistral free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is Zeta Alpha E5 Mistral, and what is it best at?›
#13 of 238 in Embeddings.
Is Zeta Alpha E5 Mistral better than Speed Embedding 7B Instruct?›
On MTEB English v2 · Pair Classification · English, Zeta Alpha E5 Mistral scores 88.3 vs 88.3 — about the same.
When was Zeta Alpha E5 Mistral released? Is there a newer version?›
Released 2024-08-30. It is the current version in its line.
Is Zeta Alpha E5 Mistral open source?›
Yes, the weights are open (MIT licence).
Can I run Zeta Alpha E5 Mistral locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is Zeta Alpha E5 Mistral?›
Zeta Alpha E5 Mistral is an open-weights embeddings & retrieval model from zeta-alpha-ai, released Aug 2024.
What are the best alternatives to Zeta Alpha E5 Mistral?›
Voyage Large 2 Instruct (better), QZhou Embedding (open weights).