alt Hacker NewsIt may be worth pointing out that a few open weights models score higher than gemini-embedding-001 on MTEB:
https://huggingface.co/spaces/mteb/leaderboard
Particularly Qwen3-Embedding-8B and Qwen3-Embedding-4B:
It may be worth pointing out that a few open weights models score higher than gemini-embedding-001 on MTEB:
https://huggingface.co/spaces/mteb/leaderboard
Particularly Qwen3-Embedding-8B and Qwen3-Embedding-4B:
i don't think many people are having luck replicating those benchmarks, the models are a bit weird