Mdbr Leaf MT measured on 17 of 261 Embeddings benchmarks17
BenchmarkByScoreRank
No benchmark matches
price not verifiedprice
51.4MTEB English v2
Aug 2025released
1K tokensMax input
enLanguages
Rankingconfiguration unstated?
Full ranking →···
102Granite Embedding 278M Multilingual51.4103Mdbr Leaf MT51.4104EmbeddingGemma 251.3Strong at
Alternatives?
ModelScoreCostPriceWhat changes
ModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
ModelScoreCostPriceWhat changes
IYuan Embedding 2.0 EnunstatedOpen+38%——Memory (4-bit): 0 GB → 0.4 GBModelScoreCostPriceWhat changes
VVoyage 3unstated+4%—$0.06Languages: not verifiedVVoyage 3 Liteunstated-2%—$0.02Languages: not verifiedVVoyage 4n/a—$0.06Languages: not verifiedVVoyage 4 Largeunstatedn/a—$0.12Languages: not verifiedVVoyage 4 Liten/a—$0.02Languages: not verifiedVVoyage 4 NanoOpenn/a——Languages: not verified+1VMdbr Leaf IrOpenn/a——VVoyage 3.5unstatedn/a—$0.06Languages: not verifiedAll Voyage AI (MongoDB) 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 Mdbr Leaf MT cost?›
There is no per-unit API price: price not verified.
How good is Mdbr Leaf MT, and what is it best at?›
#97 of 200 in Embeddings.
Is Mdbr Leaf MT better than Granite Embedding 278M Multilingual?›
On MTEB English v2 · Retrieval · English, Mdbr Leaf MT scores 51.4 vs 51.4 — about the same.
When was Mdbr Leaf MT released? Is there a newer version?›
Released 2025-08-27. It is the current version in its line.
Is Mdbr Leaf MT open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Mdbr Leaf MT locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is Mdbr Leaf MT?›
Mdbr Leaf MT is an open-weights embeddings & retrieval model from Voyage AI (MongoDB), released Aug 2025.
What are the best alternatives to Mdbr Leaf MT?›
EmbeddingGemma 300M (better), Yuan Embedding 2.0 En (open weights).