FaMTEB
The Persian version of MTEB (Massive Text Embedding Benchmark), aggregating a variety of Persian embedding evaluation tasks to measure the performance of embedding models on Persian retrieval.
Timeline (last 90 days)
On the eight Persian retrieval tasks of FaMTEB, Yalda Embedding achieves a macro average score of 0.5488, the highest among the 0.6B models evaluated.
FaMTEB is the Persian version of MTEB, gathering a variety of Persian embedding evaluation tasks, among which the retrieval tasks measure a model's ability in query-document matching.
All Facts (2)
On the eight Persian retrieval tasks of FaMTEB, Yalda Embedding achieves a macro average score of 0.5488, the highest among the 0.6B models evaluated.
50%UnverifiedFaMTEB is the Persian version of MTEB, gathering a variety of Persian embedding evaluation tasks, among which the retrieval tasks measure a model's ability in query-document matching.
50%