ModelQwen3-Embedding-4B
Qwen3-Embedding-4B
A text embedding model of approximately 4 billion parameters in the Qwen series, used as a larger-scale baseline for measuring the retrieval performance of small models.
Timeline (last 90 days)
Oct 26
Yalda Embedding approaches the performance of Qwen3-Embedding-4B, winning on four tasks and tying on one, with a macro average only 0.0075 behind.
Unverified50%