Hakim measured on 9 of 194 Embeddings benchmarks9
BenchmarkByScoreRank
No benchmark matches
price not verifiedprice
69.4MTEB Persian v2
May 2025released
1K tokensMax input
Alternatives?
ModelScoreCostPriceWhat changes
BetterEmbeddingGemma 300MunstatedOpen+3%—$0.002
OpenBge M3unstated+7%—$0.01iBetterMultilingual E5 LargeunstatedOpen+7%—$0.01iBetterMultilingual E5 Large InstructunstatedOpen+4%—$0.01iBetterE5 Mistral 7B InstructunstatedOpen+4%—$0.022ModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
EmbeddingGemma 300MunstatedOpen+3%—$0.002Bge M3unstatedOpen+7%—$0.01iMultilingual E5 LargeunstatedOpen+7%—$0.01iMultilingual E5 Large InstructunstatedOpen+4%—$0.01iE5 Mistral 7B InstructunstatedOpen+4%—$0.022
Benchmarks
in Embeddings & RetrievalFAQ
How much does Hakim cost?›
There is no per-unit API price: price not verified.
How good is Hakim, and what is it best at?›
#31 of 149 in Embeddings.
Is Hakim better than Granite Embedding 278M Multilingual?›
On MTEB Persian v2 · Reranking · Persian, Hakim scores 69.4 vs 69.6 — about the same.
When was Hakim released? Is there a newer version?›
Released 2025-05-10. It is the current version in its line.
Is Hakim open source?›
No, Hakim is a closed model available through an API. The closest open-weights option here is Bge M3.
What is Hakim?›
Hakim is a closed embeddings & retrieval model from MCINext, released May 2025.
What are the best alternatives to Hakim?›
EmbeddingGemma 300M (better), Bge M3 (open weights).