BERTA measured on 9 of 194 Embeddings benchmarks9
BenchmarkByScoreRank
No benchmark matches
price not verifiedprice
65.7MTEB Russian v1.1
Mar 2025released
768Dimensions
1K tokensMax input
en, ruLanguages
Alternatives?
ModelScoreCostPriceWhat changes
ModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
ModelScoreCostPriceWhat changes
aGiga Embeddings Instruct 10B A1.8B 0826unstatedOpen+8%——Memory (4-bit): 0.1 GB → 6.3 GBaGiga Embeddings Instruct 3B 0826unstatedOpen+7%——Memory (4-bit): 0.1 GB → 1.9 GBaGiga Embeddings InstructunstatedOpen+7%——Memory (4-bit): 0.1 GB → 1.9 GBRun 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
LicenceMITfree for commercial use
Benchmarks
in Embeddings & RetrievalFAQ
How much does BERTA cost?›
There is no per-unit API price: price not verified.
How good is BERTA, and what is it best at?›
#15 of 194 in Embeddings.
Is BERTA better than F2LLM v2 4B?›
On MTEB Russian v1.1 · Mean over tasks · Russian, BERTA scores 69.4 vs 69.5 — about the same.
When was BERTA released? Is there a newer version?›
Released 2025-03-10. It is the current version in its line.
Is BERTA open source?›
Yes, the weights are open (MIT licence).
Can I run BERTA locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is BERTA?›
BERTA is an open-weights embeddings & retrieval model from sergeyzh, released Mar 2025.
What are the best alternatives to BERTA?›
Qwen 3 Embedding 8B (better), Giga Embeddings Instruct 10B A1.8B 0826 (open weights).