MoD Embedding measured on 14 of 261 Embeddings benchmarks14
BenchmarkByScoreRank
Reranking9
Other5
No benchmark matches
self-host onlyprice
52.7RTEB French beta
Dec 2025released
2,560Dimensions
41K tokensMax input
en, zhLanguages
Alternatives?
ModelScoreCostPriceWhat changes
VBetterVoyage 4 Lite+4%—$0.02Max input: 41K tokens → 32K tokens+1ModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
VVoyage 4 Lite+4%—$0.02Max input: 41K tokens → 32K tokens+1VVoyage 4+7%—$0.06Max input: 41K tokens → 32K tokens+1VVoyage 3.5unstated+6%—$0.06Max input: 41K tokens → 32K tokens+1VVoyage 4 Largeunstated+12%—$0.12Max input: 41K tokens → 32K tokens+1VVoyage 3 Large+8%—$0.18Max input: 41K tokens → 32K tokens+1Run 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 MoD Embedding cost?›
There is no per-unit API price: self-host only.
Is MoD Embedding free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is MoD Embedding, and what is it best at?›
#29 of 212 in Embeddings.
Is MoD Embedding better than Gemini Embedding 2 Preview?›
On RTEB Finnish beta · Mean over tasks · English, MoD Embedding scores 78 vs 78.6 — about the same.
When was MoD Embedding released? Is there a newer version?›
Released 2025-12-14. It is the current version in its line.
Is MoD Embedding open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run MoD Embedding locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is MoD Embedding?›
MoD Embedding is an open-weights embeddings & retrieval model from bflhc, released Dec 2025.
What are the best alternatives to MoD Embedding?›
Voyage 4 Lite (better), Nemotron 3 Embed 8B BF16 (open weights).